Hugging Face's logo

oyildirim
/
CyberStrike-OffSec-35B

Text Generation
Transformers
Safetensors
qwen3_5_moe
image-text-to-text
offensive-security
pentesting
tool-calling
cyberstrike
qwen3
conversational
Model card Files
xet
 Community
3
oyildirim commited on
Commit
0e77e0e
·
verified ·
1 Parent(s): af693b8

Upload folder using huggingface_hub

Browse files
Files changed (35) hide show
  1. .gitattributes +1 -0
  2. README.md +207 -0
  3. chat_template.jinja +53 -0
  4. config.json +126 -0
  5. generation_config.json +13 -0
  6. model-00001-of-00026.safetensors +3 -0
  7. model-00002-of-00026.safetensors +3 -0
  8. model-00003-of-00026.safetensors +3 -0
  9. model-00004-of-00026.safetensors +3 -0
  10. model-00005-of-00026.safetensors +3 -0
  11. model-00006-of-00026.safetensors +3 -0
  12. model-00007-of-00026.safetensors +3 -0
  13. model-00008-of-00026.safetensors +3 -0
  14. model-00009-of-00026.safetensors +3 -0
  15. model-00010-of-00026.safetensors +3 -0
  16. model-00011-of-00026.safetensors +3 -0
  17. model-00012-of-00026.safetensors +3 -0
  18. model-00013-of-00026.safetensors +3 -0
  19. model-00014-of-00026.safetensors +3 -0
  20. model-00015-of-00026.safetensors +3 -0
  21. model-00016-of-00026.safetensors +3 -0
  22. model-00017-of-00026.safetensors +3 -0
  23. model-00018-of-00026.safetensors +3 -0
  24. model-00019-of-00026.safetensors +3 -0
  25. model-00020-of-00026.safetensors +3 -0
  26. model-00021-of-00026.safetensors +3 -0
  27. model-00022-of-00026.safetensors +3 -0
  28. model-00023-of-00026.safetensors +3 -0
  29. model-00024-of-00026.safetensors +3 -0
  30. model-00025-of-00026.safetensors +3 -0
  31. model-00026-of-00026.safetensors +3 -0
  32. model.safetensors.index.json +1052 -0
  33. processor_config.json +60 -0
  34. tokenizer.json +3 -0
  35. tokenizer_config.json +300 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ tags:
6
+ - cybersecurity
7
+ - offensive-security
8
+ - penetration-testing
9
+ - red-team
10
+ - mitre-attack
11
+ - cve
12
+ - security
13
+ base_model: Qwen/Qwen3.6-35B-A3B
14
+ pipeline_tag: text-generation
15
+ model-index:
16
+ - name: CyberStrike-OffSec-35B
17
+ results:
18
+ - task:
19
+ type: text-generation
20
+ name: Cybersecurity Knowledge
21
+ dataset:
22
+ name: SecEval
23
+ type: XuanwuAI/SecEval
24
+ metrics:
25
+ - name: Overall Accuracy
26
+ type: accuracy
27
+ value: 81.39
28
+ - task:
29
+ type: text-generation
30
+ name: Cybersecurity Knowledge
31
+ dataset:
32
+ name: CyberMetric-10000
33
+ type: khangmacon/cybermetric-10000
34
+ metrics:
35
+ - name: Overall Accuracy
36
+ type: accuracy
37
+ value: 86.61
38
+ - task:
39
+ type: text-generation
40
+ name: MITRE ATT&CK Extraction
41
+ dataset:
42
+ name: SECURE-MAET
43
+ type: custom
44
+ metrics:
45
+ - name: MAET Accuracy
46
+ type: accuracy
47
+ value: 93.94
48
+ - task:
49
+ type: text-generation
50
+ name: CWE Extraction
51
+ dataset:
52
+ name: SECURE-CWET
53
+ type: custom
54
+ metrics:
55
+ - name: CWET Accuracy
56
+ type: accuracy
57
+ value: 93.05
58
+ - task:
59
+ type: text-generation
60
+ name: General Knowledge
61
+ dataset:
62
+ name: MMLU
63
+ type: cais/mmlu
64
+ metrics:
65
+ - name: Overall Accuracy
66
+ type: accuracy
67
+ value: 76.94
68
+ ---
69
+
70
+ # CyberStrike-OffSec-35B
71
+
72
+ **The #1 ranked open-source model for cybersecurity knowledge and offensive security.**
73
+
74
+ CyberStrike-OffSec-35B is a Mixture-of-Experts language model fine-tuned specifically for penetration testing, vulnerability analysis, and offensive security operations. Built on Qwen3.6-35B-A3B (35B total / 3B active parameters), it achieves state-of-the-art results on multiple cybersecurity benchmarks, outperforming GPT-4-turbo and GPT-4 on domain-specific evaluations.
75
+
76
+ ## Benchmark Results
77
+
78
+ ### SecEval -- #1 on Leaderboard (Outperforms GPT-4-turbo)
79
+
80
+ | Rank | Model | Overall |
81
+ |------|-------|---------|
82
+ | **#1** | **CyberStrike-OffSec-35B** | **81.39%** |
83
+ | #2 | GPT-4-turbo | 79.07% |
84
+ | #3 | GPT-3.5-turbo | 62.09% |
85
+
86
+ **SecEval Domain Breakdown:**
87
+
88
+ | Domain | CyberStrike | GPT-4-turbo | Delta |
89
+ |--------|-------------|-------------|-------|
90
+ | Network Security | **85.09%** | 75.65% | +9.44 |
91
+ | Vulnerability | **83.33%** | 76.05% | +7.28 |
92
+ | Web Security | **85.34%** | 82.15% | +3.19 |
93
+ | Application Security | **82.29%** | 75.25% | +7.04 |
94
+ | PenTest | **82.26%** | 80.00% | +2.26 |
95
+ | Software Security | **79.75%** | 73.28% | +6.47 |
96
+ | System Security | **77.82%** | 73.61% | +4.21 |
97
+ | Cryptography | **75.00%** | 64.29% | +10.71 |
98
+ | Memory Safety | **71.43%** | 70.83% | +0.60 |
99
+
100
+ ### SECURE -- #1 on Both Tasks (Outperforms GPT-4)
101
+
102
+ | Benchmark | CyberStrike | GPT-4 | Llama3-70B |
103
+ |-----------|-------------|-------|------------|
104
+ | **MAET** (MITRE ATT&CK) | **93.94%** | 88.6% | 86.3% |
105
+ | **CWET** (CWE Knowledge) | **93.05%** | 89.6% | 90.4% |
106
+
107
+ ### CyberMetric-10000 -- #4 out of 25 Models
108
+
109
+ | Rank | Model | Score |
110
+ |------|-------|-------|
111
+ | #1 | GPT-4o | 88.89% |
112
+ | #2 | GPT-4-turbo | 88.50% |
113
+ | #3 | GEMINI-pro 1.0 | 87.50% |
114
+ | **#4** | **CyberStrike-OffSec-35B** | **86.61%** |
115
+ | #5 | Mixtral-8x7B-Instruct | 87.00% |
116
+
117
+ ### General Benchmarks (lm-evaluation-harness, 0-shot)
118
+
119
+ | Benchmark | Score |
120
+ |-----------|-------|
121
+ | MMLU (overall) | 76.94% |
122
+ | MMLU Computer Security | 86.00% |
123
+ | MMLU Security Studies | 80.00% |
124
+ | HellaSwag (acc_norm) | 79.61% |
125
+ | ARC Easy | 81.86% |
126
+ | ARC Challenge (acc_norm) | 59.13% |
127
+ | WinoGrande | 72.22% |
128
+ | TruthfulQA MC2 | 49.64% |
129
+
130
+ ## Training
131
+
132
+ ### Stage 1: Supervised Fine-Tuning (SFT)
133
+
134
+ - **Base model:** Qwen3.6-35B-A3B (MoE: 35B total, 3B active)
135
+ - **Training data:** Custom offensive security dataset covering penetration testing, exploit development, red teaming, MITRE ATT&CK techniques, CVE analysis, cloud security, and more
136
+ - **Method:** QLoRA (4-bit quantization), LoRA r=64, alpha=128
137
+ - **Hardware:** NVIDIA H200 140GB
138
+
139
+ ### Stage 2: Direct Preference Optimization (DPO)
140
+
141
+ - **Training data:** 115,250 chosen/rejected pairs across 12 preference axes:
142
+ - MITRE ATT&CK depth, CVE analysis, OWASP methodology, Cloud security
143
+ - Tool usage, ReAct reasoning, Multi-turn engagement, Code-first approach
144
+ - Techstack analysis, Sub-agent coordination, Business logic, NIST compliance
145
+ - **Method:** QLoRA, LoRA r=32, alpha=64, beta=0.1
146
+ - **Epochs:** 1 (9,142 steps)
147
+ - **Hardware:** NVIDIA H200 140GB
148
+
149
+ ## Usage
150
+
151
+ ```python
152
+ from transformers import AutoTokenizer, AutoModelForCausalLM
153
+ import torch
154
+
155
+ model = AutoModelForCausalLM.from_pretrained(
156
+ "oyildirim/CyberStrike-OffSec-35B",
157
+ torch_dtype=torch.bfloat16,
158
+ device_map="auto",
159
+ trust_remote_code=True,
160
+ )
161
+ tokenizer = AutoTokenizer.from_pretrained(
162
+ "oyildirim/CyberStrike-OffSec-35B",
163
+ trust_remote_code=True,
164
+ )
165
+
166
+ messages = [
167
+ {"role": "user", "content": "Explain how SQL injection works and demonstrate WAF evasion techniques."}
168
+ ]
169
+
170
+ text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
171
+ inputs = tokenizer(text, return_tensors="pt").to(model.device)
172
+
173
+ outputs = model.generate(**inputs, max_new_tokens=2048, do_sample=True, temperature=0.7)
174
+ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
175
+ ```
176
+
177
+ ## Architecture
178
+
179
+ - **Type:** Mixture-of-Experts (MoE)
180
+ - **Total Parameters:** 35B
181
+ - **Active Parameters:** ~3B per token
182
+ - **Context Length:** 4096 tokens (training), supports longer via RoPE
183
+ - **Precision:** BF16
184
+ - **Model Shards:** 26 safetensors files (~67GB total)
185
+
186
+ ## Intended Use
187
+
188
+ This model is designed for **authorized security testing, penetration testing, red team operations, security research, CTF competitions, and cybersecurity education**. It should only be used in legal and ethical contexts with proper authorization.
189
+
190
+ ## Limitations
191
+
192
+ - Optimized for cybersecurity domain; general-purpose performance is lower than frontier models
193
+ - 0-shot general benchmarks (MMLU, ARC, etc.) may improve with few-shot prompting
194
+ - MoE architecture requires sufficient RAM/VRAM for full model loading (~67GB in BF16)
195
+
196
+ ## Citation
197
+
198
+ If you use this model in your research, please cite:
199
+
200
+ ```bibtex
201
+ @misc{cyberstrike2025,
202
+ title={CyberStrike-OffSec-35B: A Domain-Specialized LLM for Offensive Security},
203
+ author={Orhan Yildirim},
204
+ year={2025},
205
+ url={https://huggingface.co/oyildirim/CyberStrike-OffSec-35B}
206
+ }
207
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} {{- '<|im_start|>user' }}
42
+ {%- endif %}
43
+ {{- '\n<tool_response>\n' }}
44
+ {{- message.content }}
45
+ {{- '\n</tool_response>' }}
46
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
47
+ {{- '<|im_end|>\n' }}
48
+ {%- endif %}
49
+ {%- endif %}
50
+ {%- endfor %}
51
+ {%- if add_generation_prompt %}
52
+ {{- '<|im_start|>assistant\n' }}
53
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5MoeForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": null,
6
+ "torch_dtype": "bfloat16",
7
+ "eos_token_id": 248046,
8
+ "image_token_id": 248056,
9
+ "model_name": "/workspace/cyberstrike-sft-v2-merged",
10
+ "model_type": "qwen3_5_moe",
11
+ "pad_token_id": 248044,
12
+ "text_config": {
13
+ "attention_bias": false,
14
+ "attention_dropout": 0.0,
15
+ "attn_output_gate": true,
16
+ "bos_token_id": 248044,
17
+ "torch_dtype": "bfloat16",
18
+ "eos_token_id": 248044,
19
+ "full_attention_interval": 4,
20
+ "head_dim": 256,
21
+ "hidden_act": "silu",
22
+ "hidden_size": 2048,
23
+ "initializer_range": 0.02,
24
+ "layer_types": [
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "full_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "full_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "full_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "full_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "full_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "full_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "full_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "full_attention",
57
+ "linear_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "full_attention",
61
+ "linear_attention",
62
+ "linear_attention",
63
+ "linear_attention",
64
+ "full_attention"
65
+ ],
66
+ "linear_conv_kernel_dim": 4,
67
+ "linear_key_head_dim": 128,
68
+ "linear_num_key_heads": 16,
69
+ "linear_num_value_heads": 32,
70
+ "linear_value_head_dim": 128,
71
+ "mamba_ssm_dtype": "float32",
72
+ "max_position_embeddings": 262144,
73
+ "model_type": "qwen3_5_moe_text",
74
+ "moe_intermediate_size": 512,
75
+ "mtp_num_hidden_layers": 1,
76
+ "mtp_use_dedicated_embeddings": false,
77
+ "num_attention_heads": 16,
78
+ "num_experts": 256,
79
+ "num_experts_per_tok": 8,
80
+ "num_hidden_layers": 40,
81
+ "num_key_value_heads": 2,
82
+ "output_router_logits": false,
83
+ "pad_token_id": null,
84
+ "partial_rotary_factor": 0.25,
85
+ "rms_norm_eps": 1e-06,
86
+ "rope_parameters": {
87
+ "mrope_interleaved": true,
88
+ "mrope_section": [
89
+ 11,
90
+ 11,
91
+ 10
92
+ ],
93
+ "partial_rotary_factor": 0.25,
94
+ "rope_theta": 10000000,
95
+ "rope_type": "default"
96
+ },
97
+ "router_aux_loss_coef": 0.001,
98
+ "shared_expert_intermediate_size": 512,
99
+ "tie_word_embeddings": false,
100
+ "use_cache": false,
101
+ "vocab_size": 248320
102
+ },
103
+ "tie_word_embeddings": false,
104
+ "unsloth_version": "2026.6.8",
105
+ "use_cache": false,
106
+ "video_token_id": 248057,
107
+ "vision_config": {
108
+ "deepstack_visual_indexes": [],
109
+ "depth": 27,
110
+ "torch_dtype": "bfloat16",
111
+ "hidden_act": "gelu_pytorch_tanh",
112
+ "hidden_size": 1152,
113
+ "in_channels": 3,
114
+ "initializer_range": 0.02,
115
+ "intermediate_size": 4304,
116
+ "model_type": "qwen3_5_moe",
117
+ "num_heads": 16,
118
+ "num_position_embeddings": 2304,
119
+ "out_hidden_size": 2048,
120
+ "patch_size": 16,
121
+ "spatial_merge_size": 2,
122
+ "temporal_patch_size": 2
123
+ },
124
+ "vision_end_token_id": 248054,
125
+ "vision_start_token_id": 248053
126
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 248046,
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.5.0"
13
+ }
model-00001-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6602566885b6c572b8eef38431b004f45d679da0e19b825f86ea38d813a1cdb1
3
+ size 3996199712
model-00002-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a77d1d49a9aa1496be4892ff23acfb3ea5c27305f39abf5a7907045a45f8be
3
+ size 1284907696
model-00003-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b45e9d8bfd927f71c0a68873b2ae8eb05a480b4cfd54496df1df902c57e8388
3
+ size 3357898360
model-00004-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:becb3a53790f6754e3355d0b38cca4c3e4a2daabcf50cbd4f58459ca42c448e4
3
+ size 3370808712
model-00005-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70e55d7a704efb979648bfc85a5b415f84553c1aef5313755279178b3bccb62e
3
+ size 3357898360
model-00006-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9c95bbd25e8108d95431ec9cbf1227c45a6b96f3b6bb45499c1ad0b64bd1343
3
+ size 3959424904
model-00007-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4851875369ccfbb6930896d5ddd59bd1e354918bd85f413a33ac542855c2946b
3
+ size 1096788232
model-00008-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:619211950a5b4ad3c0c61800863d8b376c29311c0da015144528b5d8f1d91b09
3
+ size 3946842008
model-00009-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5a18edf2c0eee02c679b1929831d09c5c73cbc49207b1e6f682db15acafeec0
3
+ size 1096460848
model-00010-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5abffb66cdef834214dee880840014d14334918d9cf6269c1776c4ce0e841af9
3
+ size 3946841992
model-00011-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b47796f5d718897b205dde649df5da6658918bd1114349f365561b7a83d674
3
+ size 1096460752
model-00012-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeddcf46eb5326029bc25688ff614979d75a4002e0f6f37306e302238737c0e2
3
+ size 3409971080
model-00013-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052d12b51c5f0d2411d2c980aa25b24ae5f0817e10093ec3b2b43ba1f2cb8d74
3
+ size 1633331664
model-00014-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eba45ad33468ad16f4812f9efbfbcd1b6cf9dfbe1175a167afca57aef44d0d1f
3
+ size 3422553872
model-00015-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bd161827b12ea1173bcd9bde54c040d5284e746f5a216599d527fef40dff2d9
3
+ size 1633659224
model-00016-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3855189805c03a784e3f5045ee34d96f86aa0deac9cdc48cf03e1adcbe78d8e2
3
+ size 3946842136
model-00017-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9a13cb975248c02b358dac4b109a48403b6832d07ca5f9291064b8dbcffac45
3
+ size 1096460608
model-00018-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdb392d86782ae7cf6b5c39b7339789f85961205bdbb97ac1e14c08b8c0fd351
3
+ size 3946841992
model-00019-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcb53967203b5a17aa2570f96ca905af36d19b5bda524d19d3e78adfa7a45f5b
3
+ size 1096460808
model-00020-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d7c83c6d63ff987831c8d02063a5c36698018b6115bb0684ac5e38a55d0c61
3
+ size 3409971072
model-00021-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66d61e04db114b8d9e1b6ca999939f82bb7a352f64495d752d6ede254d52f45a
3
+ size 1633331744
model-00022-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba7d14b08c4a9adb3b4210f9b2bedcbf536a31aab17368ed502fb78bc2906640
3
+ size 3370808752
model-00023-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e2e6ec524f29985cd8d74a468a1849c930a5bafc0dcdbf24e847f65188da847
3
+ size 3357898392
model-00024-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d8e60bdcbc15c18730389fb0f83f613ec2bbbf558141c9bec5329c9444d9288
3
+ size 3370808752
model-00025-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42bcda40fc169c6551fd77065117a9c8e45879dc61ee24fe01d8f8865308443e
3
+ size 3832888256
model-00026-of-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bffd4b74b1102bb2e025745d1dae9f2f882d7aa3ae5ace94830232734f0e48e
3
+ size 2231416848
model.safetensors.index.json ADDED
@@ -0,0 +1,1052 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 71903645408.0
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00026-of-00026.safetensors",
7
+ "model.language_model.embed_tokens.weight": "model-00001-of-00026.safetensors",
8
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00026.safetensors",
9
+ "model.language_model.layers.0.linear_attn.A_log": "model-00002-of-00026.safetensors",
10
+ "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00002-of-00026.safetensors",
11
+ "model.language_model.layers.0.linear_attn.dt_bias": "model-00002-of-00026.safetensors",
12
+ "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00002-of-00026.safetensors",
13
+ "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00002-of-00026.safetensors",
14
+ "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00026.safetensors",
15
+ "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00026.safetensors",
16
+ "model.language_model.layers.0.linear_attn.norm.weight": "model-00002-of-00026.safetensors",
17
+ "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00026.safetensors",
18
+ "model.language_model.layers.0.mlp.experts.down_proj": "model-00002-of-00026.safetensors",
19
+ "model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00026.safetensors",
20
+ "model.language_model.layers.0.mlp.gate.weight": "model-00002-of-00026.safetensors",
21
+ "model.language_model.layers.0.mlp.shared_expert.down_proj.weight": "model-00002-of-00026.safetensors",
22
+ "model.language_model.layers.0.mlp.shared_expert.gate_proj.weight": "model-00002-of-00026.safetensors",
23
+ "model.language_model.layers.0.mlp.shared_expert.up_proj.weight": "model-00002-of-00026.safetensors",
24
+ "model.language_model.layers.0.mlp.shared_expert_gate.weight": "model-00002-of-00026.safetensors",
25
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00002-of-00026.safetensors",
26
+ "model.language_model.layers.1.input_layernorm.weight": "model-00002-of-00026.safetensors",
27
+ "model.language_model.layers.1.linear_attn.A_log": "model-00002-of-00026.safetensors",
28
+ "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00002-of-00026.safetensors",
29
+ "model.language_model.layers.1.linear_attn.dt_bias": "model-00002-of-00026.safetensors",
30
+ "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00002-of-00026.safetensors",
31
+ "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00002-of-00026.safetensors",
32
+ "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00026.safetensors",
33
+ "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00026.safetensors",
34
+ "model.language_model.layers.1.linear_attn.norm.weight": "model-00002-of-00026.safetensors",
35
+ "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00026.safetensors",
36
+ "model.language_model.layers.1.mlp.experts.down_proj": "model-00001-of-00026.safetensors",
37
+ "model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00026.safetensors",
38
+ "model.language_model.layers.1.mlp.gate.weight": "model-00002-of-00026.safetensors",
39
+ "model.language_model.layers.1.mlp.shared_expert.down_proj.weight": "model-00002-of-00026.safetensors",
40
+ "model.language_model.layers.1.mlp.shared_expert.gate_proj.weight": "model-00002-of-00026.safetensors",
41
+ "model.language_model.layers.1.mlp.shared_expert.up_proj.weight": "model-00002-of-00026.safetensors",
42
+ "model.language_model.layers.1.mlp.shared_expert_gate.weight": "model-00002-of-00026.safetensors",
43
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00002-of-00026.safetensors",
44
+ "model.language_model.layers.10.input_layernorm.weight": "model-00007-of-00026.safetensors",
45
+ "model.language_model.layers.10.linear_attn.A_log": "model-00007-of-00026.safetensors",
46
+ "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00007-of-00026.safetensors",
47
+ "model.language_model.layers.10.linear_attn.dt_bias": "model-00007-of-00026.safetensors",
48
+ "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00007-of-00026.safetensors",
49
+ "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00007-of-00026.safetensors",
50
+ "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00006-of-00026.safetensors",
51
+ "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00006-of-00026.safetensors",
52
+ "model.language_model.layers.10.linear_attn.norm.weight": "model-00007-of-00026.safetensors",
53
+ "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00006-of-00026.safetensors",
54
+ "model.language_model.layers.10.mlp.experts.down_proj": "model-00006-of-00026.safetensors",
55
+ "model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00007-of-00026.safetensors",
56
+ "model.language_model.layers.10.mlp.gate.weight": "model-00007-of-00026.safetensors",
57
+ "model.language_model.layers.10.mlp.shared_expert.down_proj.weight": "model-00007-of-00026.safetensors",
58
+ "model.language_model.layers.10.mlp.shared_expert.gate_proj.weight": "model-00007-of-00026.safetensors",
59
+ "model.language_model.layers.10.mlp.shared_expert.up_proj.weight": "model-00007-of-00026.safetensors",
60
+ "model.language_model.layers.10.mlp.shared_expert_gate.weight": "model-00007-of-00026.safetensors",
61
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00007-of-00026.safetensors",
62
+ "model.language_model.layers.11.input_layernorm.weight": "model-00009-of-00026.safetensors",
63
+ "model.language_model.layers.11.mlp.experts.down_proj": "model-00009-of-00026.safetensors",
64
+ "model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00008-of-00026.safetensors",
65
+ "model.language_model.layers.11.mlp.gate.weight": "model-00009-of-00026.safetensors",
66
+ "model.language_model.layers.11.mlp.shared_expert.down_proj.weight": "model-00009-of-00026.safetensors",
67
+ "model.language_model.layers.11.mlp.shared_expert.gate_proj.weight": "model-00009-of-00026.safetensors",
68
+ "model.language_model.layers.11.mlp.shared_expert.up_proj.weight": "model-00009-of-00026.safetensors",
69
+ "model.language_model.layers.11.mlp.shared_expert_gate.weight": "model-00009-of-00026.safetensors",
70
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00009-of-00026.safetensors",
71
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00009-of-00026.safetensors",
72
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00008-of-00026.safetensors",
73
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00008-of-00026.safetensors",
74
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00009-of-00026.safetensors",
75
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00008-of-00026.safetensors",
76
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00008-of-00026.safetensors",
77
+ "model.language_model.layers.12.input_layernorm.weight": "model-00009-of-00026.safetensors",
78
+ "model.language_model.layers.12.linear_attn.A_log": "model-00009-of-00026.safetensors",
79
+ "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00009-of-00026.safetensors",
80
+ "model.language_model.layers.12.linear_attn.dt_bias": "model-00009-of-00026.safetensors",
81
+ "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00009-of-00026.safetensors",
82
+ "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00009-of-00026.safetensors",
83
+ "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00008-of-00026.safetensors",
84
+ "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00008-of-00026.safetensors",
85
+ "model.language_model.layers.12.linear_attn.norm.weight": "model-00009-of-00026.safetensors",
86
+ "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00008-of-00026.safetensors",
87
+ "model.language_model.layers.12.mlp.experts.down_proj": "model-00009-of-00026.safetensors",
88
+ "model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00008-of-00026.safetensors",
89
+ "model.language_model.layers.12.mlp.gate.weight": "model-00009-of-00026.safetensors",
90
+ "model.language_model.layers.12.mlp.shared_expert.down_proj.weight": "model-00009-of-00026.safetensors",
91
+ "model.language_model.layers.12.mlp.shared_expert.gate_proj.weight": "model-00009-of-00026.safetensors",
92
+ "model.language_model.layers.12.mlp.shared_expert.up_proj.weight": "model-00009-of-00026.safetensors",
93
+ "model.language_model.layers.12.mlp.shared_expert_gate.weight": "model-00009-of-00026.safetensors",
94
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00009-of-00026.safetensors",
95
+ "model.language_model.layers.13.input_layernorm.weight": "model-00009-of-00026.safetensors",
96
+ "model.language_model.layers.13.linear_attn.A_log": "model-00009-of-00026.safetensors",
97
+ "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00009-of-00026.safetensors",
98
+ "model.language_model.layers.13.linear_attn.dt_bias": "model-00009-of-00026.safetensors",
99
+ "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00009-of-00026.safetensors",
100
+ "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00009-of-00026.safetensors",
101
+ "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00008-of-00026.safetensors",
102
+ "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00008-of-00026.safetensors",
103
+ "model.language_model.layers.13.linear_attn.norm.weight": "model-00009-of-00026.safetensors",
104
+ "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00008-of-00026.safetensors",
105
+ "model.language_model.layers.13.mlp.experts.down_proj": "model-00008-of-00026.safetensors",
106
+ "model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00008-of-00026.safetensors",
107
+ "model.language_model.layers.13.mlp.gate.weight": "model-00009-of-00026.safetensors",
108
+ "model.language_model.layers.13.mlp.shared_expert.down_proj.weight": "model-00009-of-00026.safetensors",
109
+ "model.language_model.layers.13.mlp.shared_expert.gate_proj.weight": "model-00009-of-00026.safetensors",
110
+ "model.language_model.layers.13.mlp.shared_expert.up_proj.weight": "model-00009-of-00026.safetensors",
111
+ "model.language_model.layers.13.mlp.shared_expert_gate.weight": "model-00009-of-00026.safetensors",
112
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00009-of-00026.safetensors",
113
+ "model.language_model.layers.14.input_layernorm.weight": "model-00011-of-00026.safetensors",
114
+ "model.language_model.layers.14.linear_attn.A_log": "model-00011-of-00026.safetensors",
115
+ "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00011-of-00026.safetensors",
116
+ "model.language_model.layers.14.linear_attn.dt_bias": "model-00011-of-00026.safetensors",
117
+ "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00011-of-00026.safetensors",
118
+ "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00011-of-00026.safetensors",
119
+ "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00010-of-00026.safetensors",
120
+ "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00010-of-00026.safetensors",
121
+ "model.language_model.layers.14.linear_attn.norm.weight": "model-00011-of-00026.safetensors",
122
+ "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00010-of-00026.safetensors",
123
+ "model.language_model.layers.14.mlp.experts.down_proj": "model-00010-of-00026.safetensors",
124
+ "model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00010-of-00026.safetensors",
125
+ "model.language_model.layers.14.mlp.gate.weight": "model-00011-of-00026.safetensors",
126
+ "model.language_model.layers.14.mlp.shared_expert.down_proj.weight": "model-00011-of-00026.safetensors",
127
+ "model.language_model.layers.14.mlp.shared_expert.gate_proj.weight": "model-00011-of-00026.safetensors",
128
+ "model.language_model.layers.14.mlp.shared_expert.up_proj.weight": "model-00011-of-00026.safetensors",
129
+ "model.language_model.layers.14.mlp.shared_expert_gate.weight": "model-00011-of-00026.safetensors",
130
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00011-of-00026.safetensors",
131
+ "model.language_model.layers.15.input_layernorm.weight": "model-00011-of-00026.safetensors",
132
+ "model.language_model.layers.15.mlp.experts.down_proj": "model-00011-of-00026.safetensors",
133
+ "model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00010-of-00026.safetensors",
134
+ "model.language_model.layers.15.mlp.gate.weight": "model-00011-of-00026.safetensors",
135
+ "model.language_model.layers.15.mlp.shared_expert.down_proj.weight": "model-00011-of-00026.safetensors",
136
+ "model.language_model.layers.15.mlp.shared_expert.gate_proj.weight": "model-00011-of-00026.safetensors",
137
+ "model.language_model.layers.15.mlp.shared_expert.up_proj.weight": "model-00011-of-00026.safetensors",
138
+ "model.language_model.layers.15.mlp.shared_expert_gate.weight": "model-00011-of-00026.safetensors",
139
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00011-of-00026.safetensors",
140
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00011-of-00026.safetensors",
141
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00010-of-00026.safetensors",
142
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00010-of-00026.safetensors",
143
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00011-of-00026.safetensors",
144
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00010-of-00026.safetensors",
145
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00010-of-00026.safetensors",
146
+ "model.language_model.layers.16.input_layernorm.weight": "model-00011-of-00026.safetensors",
147
+ "model.language_model.layers.16.linear_attn.A_log": "model-00011-of-00026.safetensors",
148
+ "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00011-of-00026.safetensors",
149
+ "model.language_model.layers.16.linear_attn.dt_bias": "model-00011-of-00026.safetensors",
150
+ "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00011-of-00026.safetensors",
151
+ "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00011-of-00026.safetensors",
152
+ "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00010-of-00026.safetensors",
153
+ "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00010-of-00026.safetensors",
154
+ "model.language_model.layers.16.linear_attn.norm.weight": "model-00011-of-00026.safetensors",
155
+ "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00010-of-00026.safetensors",
156
+ "model.language_model.layers.16.mlp.experts.down_proj": "model-00011-of-00026.safetensors",
157
+ "model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00010-of-00026.safetensors",
158
+ "model.language_model.layers.16.mlp.gate.weight": "model-00011-of-00026.safetensors",
159
+ "model.language_model.layers.16.mlp.shared_expert.down_proj.weight": "model-00011-of-00026.safetensors",
160
+ "model.language_model.layers.16.mlp.shared_expert.gate_proj.weight": "model-00011-of-00026.safetensors",
161
+ "model.language_model.layers.16.mlp.shared_expert.up_proj.weight": "model-00011-of-00026.safetensors",
162
+ "model.language_model.layers.16.mlp.shared_expert_gate.weight": "model-00011-of-00026.safetensors",
163
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00011-of-00026.safetensors",
164
+ "model.language_model.layers.17.input_layernorm.weight": "model-00013-of-00026.safetensors",
165
+ "model.language_model.layers.17.linear_attn.A_log": "model-00013-of-00026.safetensors",
166
+ "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00013-of-00026.safetensors",
167
+ "model.language_model.layers.17.linear_attn.dt_bias": "model-00013-of-00026.safetensors",
168
+ "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00013-of-00026.safetensors",
169
+ "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00013-of-00026.safetensors",
170
+ "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00012-of-00026.safetensors",
171
+ "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00012-of-00026.safetensors",
172
+ "model.language_model.layers.17.linear_attn.norm.weight": "model-00013-of-00026.safetensors",
173
+ "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00012-of-00026.safetensors",
174
+ "model.language_model.layers.17.mlp.experts.down_proj": "model-00012-of-00026.safetensors",
175
+ "model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00012-of-00026.safetensors",
176
+ "model.language_model.layers.17.mlp.gate.weight": "model-00013-of-00026.safetensors",
177
+ "model.language_model.layers.17.mlp.shared_expert.down_proj.weight": "model-00013-of-00026.safetensors",
178
+ "model.language_model.layers.17.mlp.shared_expert.gate_proj.weight": "model-00013-of-00026.safetensors",
179
+ "model.language_model.layers.17.mlp.shared_expert.up_proj.weight": "model-00013-of-00026.safetensors",
180
+ "model.language_model.layers.17.mlp.shared_expert_gate.weight": "model-00013-of-00026.safetensors",
181
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00013-of-00026.safetensors",
182
+ "model.language_model.layers.18.input_layernorm.weight": "model-00013-of-00026.safetensors",
183
+ "model.language_model.layers.18.linear_attn.A_log": "model-00013-of-00026.safetensors",
184
+ "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00013-of-00026.safetensors",
185
+ "model.language_model.layers.18.linear_attn.dt_bias": "model-00013-of-00026.safetensors",
186
+ "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00013-of-00026.safetensors",
187
+ "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00013-of-00026.safetensors",
188
+ "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00012-of-00026.safetensors",
189
+ "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00012-of-00026.safetensors",
190
+ "model.language_model.layers.18.linear_attn.norm.weight": "model-00013-of-00026.safetensors",
191
+ "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00012-of-00026.safetensors",
192
+ "model.language_model.layers.18.mlp.experts.down_proj": "model-00012-of-00026.safetensors",
193
+ "model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00013-of-00026.safetensors",
194
+ "model.language_model.layers.18.mlp.gate.weight": "model-00013-of-00026.safetensors",
195
+ "model.language_model.layers.18.mlp.shared_expert.down_proj.weight": "model-00013-of-00026.safetensors",
196
+ "model.language_model.layers.18.mlp.shared_expert.gate_proj.weight": "model-00013-of-00026.safetensors",
197
+ "model.language_model.layers.18.mlp.shared_expert.up_proj.weight": "model-00013-of-00026.safetensors",
198
+ "model.language_model.layers.18.mlp.shared_expert_gate.weight": "model-00013-of-00026.safetensors",
199
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00013-of-00026.safetensors",
200
+ "model.language_model.layers.19.input_layernorm.weight": "model-00013-of-00026.safetensors",
201
+ "model.language_model.layers.19.mlp.experts.down_proj": "model-00013-of-00026.safetensors",
202
+ "model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00012-of-00026.safetensors",
203
+ "model.language_model.layers.19.mlp.gate.weight": "model-00013-of-00026.safetensors",
204
+ "model.language_model.layers.19.mlp.shared_expert.down_proj.weight": "model-00013-of-00026.safetensors",
205
+ "model.language_model.layers.19.mlp.shared_expert.gate_proj.weight": "model-00013-of-00026.safetensors",
206
+ "model.language_model.layers.19.mlp.shared_expert.up_proj.weight": "model-00013-of-00026.safetensors",
207
+ "model.language_model.layers.19.mlp.shared_expert_gate.weight": "model-00013-of-00026.safetensors",
208
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00013-of-00026.safetensors",
209
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00013-of-00026.safetensors",
210
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00012-of-00026.safetensors",
211
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00012-of-00026.safetensors",
212
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00013-of-00026.safetensors",
213
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00012-of-00026.safetensors",
214
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00012-of-00026.safetensors",
215
+ "model.language_model.layers.2.input_layernorm.weight": "model-00003-of-00026.safetensors",
216
+ "model.language_model.layers.2.linear_attn.A_log": "model-00003-of-00026.safetensors",
217
+ "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00003-of-00026.safetensors",
218
+ "model.language_model.layers.2.linear_attn.dt_bias": "model-00003-of-00026.safetensors",
219
+ "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00003-of-00026.safetensors",
220
+ "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00003-of-00026.safetensors",
221
+ "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00003-of-00026.safetensors",
222
+ "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00003-of-00026.safetensors",
223
+ "model.language_model.layers.2.linear_attn.norm.weight": "model-00003-of-00026.safetensors",
224
+ "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00003-of-00026.safetensors",
225
+ "model.language_model.layers.2.mlp.experts.down_proj": "model-00003-of-00026.safetensors",
226
+ "model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00003-of-00026.safetensors",
227
+ "model.language_model.layers.2.mlp.gate.weight": "model-00003-of-00026.safetensors",
228
+ "model.language_model.layers.2.mlp.shared_expert.down_proj.weight": "model-00003-of-00026.safetensors",
229
+ "model.language_model.layers.2.mlp.shared_expert.gate_proj.weight": "model-00003-of-00026.safetensors",
230
+ "model.language_model.layers.2.mlp.shared_expert.up_proj.weight": "model-00003-of-00026.safetensors",
231
+ "model.language_model.layers.2.mlp.shared_expert_gate.weight": "model-00003-of-00026.safetensors",
232
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00003-of-00026.safetensors",
233
+ "model.language_model.layers.20.input_layernorm.weight": "model-00015-of-00026.safetensors",
234
+ "model.language_model.layers.20.linear_attn.A_log": "model-00015-of-00026.safetensors",
235
+ "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00015-of-00026.safetensors",
236
+ "model.language_model.layers.20.linear_attn.dt_bias": "model-00015-of-00026.safetensors",
237
+ "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00015-of-00026.safetensors",
238
+ "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00015-of-00026.safetensors",
239
+ "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00014-of-00026.safetensors",
240
+ "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00014-of-00026.safetensors",
241
+ "model.language_model.layers.20.linear_attn.norm.weight": "model-00015-of-00026.safetensors",
242
+ "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00014-of-00026.safetensors",
243
+ "model.language_model.layers.20.mlp.experts.down_proj": "model-00014-of-00026.safetensors",
244
+ "model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00014-of-00026.safetensors",
245
+ "model.language_model.layers.20.mlp.gate.weight": "model-00015-of-00026.safetensors",
246
+ "model.language_model.layers.20.mlp.shared_expert.down_proj.weight": "model-00015-of-00026.safetensors",
247
+ "model.language_model.layers.20.mlp.shared_expert.gate_proj.weight": "model-00015-of-00026.safetensors",
248
+ "model.language_model.layers.20.mlp.shared_expert.up_proj.weight": "model-00015-of-00026.safetensors",
249
+ "model.language_model.layers.20.mlp.shared_expert_gate.weight": "model-00015-of-00026.safetensors",
250
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00015-of-00026.safetensors",
251
+ "model.language_model.layers.21.input_layernorm.weight": "model-00015-of-00026.safetensors",
252
+ "model.language_model.layers.21.linear_attn.A_log": "model-00015-of-00026.safetensors",
253
+ "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00015-of-00026.safetensors",
254
+ "model.language_model.layers.21.linear_attn.dt_bias": "model-00015-of-00026.safetensors",
255
+ "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00015-of-00026.safetensors",
256
+ "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00015-of-00026.safetensors",
257
+ "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00014-of-00026.safetensors",
258
+ "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00014-of-00026.safetensors",
259
+ "model.language_model.layers.21.linear_attn.norm.weight": "model-00015-of-00026.safetensors",
260
+ "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00014-of-00026.safetensors",
261
+ "model.language_model.layers.21.mlp.experts.down_proj": "model-00014-of-00026.safetensors",
262
+ "model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00015-of-00026.safetensors",
263
+ "model.language_model.layers.21.mlp.gate.weight": "model-00015-of-00026.safetensors",
264
+ "model.language_model.layers.21.mlp.shared_expert.down_proj.weight": "model-00015-of-00026.safetensors",
265
+ "model.language_model.layers.21.mlp.shared_expert.gate_proj.weight": "model-00015-of-00026.safetensors",
266
+ "model.language_model.layers.21.mlp.shared_expert.up_proj.weight": "model-00015-of-00026.safetensors",
267
+ "model.language_model.layers.21.mlp.shared_expert_gate.weight": "model-00015-of-00026.safetensors",
268
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00015-of-00026.safetensors",
269
+ "model.language_model.layers.22.input_layernorm.weight": "model-00015-of-00026.safetensors",
270
+ "model.language_model.layers.22.linear_attn.A_log": "model-00015-of-00026.safetensors",
271
+ "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00015-of-00026.safetensors",
272
+ "model.language_model.layers.22.linear_attn.dt_bias": "model-00015-of-00026.safetensors",
273
+ "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00015-of-00026.safetensors",
274
+ "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00015-of-00026.safetensors",
275
+ "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00014-of-00026.safetensors",
276
+ "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00014-of-00026.safetensors",
277
+ "model.language_model.layers.22.linear_attn.norm.weight": "model-00015-of-00026.safetensors",
278
+ "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00014-of-00026.safetensors",
279
+ "model.language_model.layers.22.mlp.experts.down_proj": "model-00015-of-00026.safetensors",
280
+ "model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00014-of-00026.safetensors",
281
+ "model.language_model.layers.22.mlp.gate.weight": "model-00015-of-00026.safetensors",
282
+ "model.language_model.layers.22.mlp.shared_expert.down_proj.weight": "model-00015-of-00026.safetensors",
283
+ "model.language_model.layers.22.mlp.shared_expert.gate_proj.weight": "model-00015-of-00026.safetensors",
284
+ "model.language_model.layers.22.mlp.shared_expert.up_proj.weight": "model-00015-of-00026.safetensors",
285
+ "model.language_model.layers.22.mlp.shared_expert_gate.weight": "model-00015-of-00026.safetensors",
286
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00015-of-00026.safetensors",
287
+ "model.language_model.layers.23.input_layernorm.weight": "model-00017-of-00026.safetensors",
288
+ "model.language_model.layers.23.mlp.experts.down_proj": "model-00016-of-00026.safetensors",
289
+ "model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00016-of-00026.safetensors",
290
+ "model.language_model.layers.23.mlp.gate.weight": "model-00017-of-00026.safetensors",
291
+ "model.language_model.layers.23.mlp.shared_expert.down_proj.weight": "model-00017-of-00026.safetensors",
292
+ "model.language_model.layers.23.mlp.shared_expert.gate_proj.weight": "model-00017-of-00026.safetensors",
293
+ "model.language_model.layers.23.mlp.shared_expert.up_proj.weight": "model-00017-of-00026.safetensors",
294
+ "model.language_model.layers.23.mlp.shared_expert_gate.weight": "model-00017-of-00026.safetensors",
295
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00017-of-00026.safetensors",
296
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00017-of-00026.safetensors",
297
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00016-of-00026.safetensors",
298
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00016-of-00026.safetensors",
299
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00017-of-00026.safetensors",
300
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00016-of-00026.safetensors",
301
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00016-of-00026.safetensors",
302
+ "model.language_model.layers.24.input_layernorm.weight": "model-00017-of-00026.safetensors",
303
+ "model.language_model.layers.24.linear_attn.A_log": "model-00017-of-00026.safetensors",
304
+ "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00017-of-00026.safetensors",
305
+ "model.language_model.layers.24.linear_attn.dt_bias": "model-00017-of-00026.safetensors",
306
+ "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00017-of-00026.safetensors",
307
+ "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00017-of-00026.safetensors",
308
+ "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00016-of-00026.safetensors",
309
+ "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00016-of-00026.safetensors",
310
+ "model.language_model.layers.24.linear_attn.norm.weight": "model-00017-of-00026.safetensors",
311
+ "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00016-of-00026.safetensors",
312
+ "model.language_model.layers.24.mlp.experts.down_proj": "model-00016-of-00026.safetensors",
313
+ "model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00016-of-00026.safetensors",
314
+ "model.language_model.layers.24.mlp.gate.weight": "model-00017-of-00026.safetensors",
315
+ "model.language_model.layers.24.mlp.shared_expert.down_proj.weight": "model-00017-of-00026.safetensors",
316
+ "model.language_model.layers.24.mlp.shared_expert.gate_proj.weight": "model-00017-of-00026.safetensors",
317
+ "model.language_model.layers.24.mlp.shared_expert.up_proj.weight": "model-00017-of-00026.safetensors",
318
+ "model.language_model.layers.24.mlp.shared_expert_gate.weight": "model-00017-of-00026.safetensors",
319
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00017-of-00026.safetensors",
320
+ "model.language_model.layers.25.input_layernorm.weight": "model-00017-of-00026.safetensors",
321
+ "model.language_model.layers.25.linear_attn.A_log": "model-00017-of-00026.safetensors",
322
+ "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00017-of-00026.safetensors",
323
+ "model.language_model.layers.25.linear_attn.dt_bias": "model-00017-of-00026.safetensors",
324
+ "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00017-of-00026.safetensors",
325
+ "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00017-of-00026.safetensors",
326
+ "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00016-of-00026.safetensors",
327
+ "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00016-of-00026.safetensors",
328
+ "model.language_model.layers.25.linear_attn.norm.weight": "model-00017-of-00026.safetensors",
329
+ "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00016-of-00026.safetensors",
330
+ "model.language_model.layers.25.mlp.experts.down_proj": "model-00016-of-00026.safetensors",
331
+ "model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00017-of-00026.safetensors",
332
+ "model.language_model.layers.25.mlp.gate.weight": "model-00017-of-00026.safetensors",
333
+ "model.language_model.layers.25.mlp.shared_expert.down_proj.weight": "model-00017-of-00026.safetensors",
334
+ "model.language_model.layers.25.mlp.shared_expert.gate_proj.weight": "model-00017-of-00026.safetensors",
335
+ "model.language_model.layers.25.mlp.shared_expert.up_proj.weight": "model-00017-of-00026.safetensors",
336
+ "model.language_model.layers.25.mlp.shared_expert_gate.weight": "model-00017-of-00026.safetensors",
337
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00017-of-00026.safetensors",
338
+ "model.language_model.layers.26.input_layernorm.weight": "model-00019-of-00026.safetensors",
339
+ "model.language_model.layers.26.linear_attn.A_log": "model-00019-of-00026.safetensors",
340
+ "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00019-of-00026.safetensors",
341
+ "model.language_model.layers.26.linear_attn.dt_bias": "model-00019-of-00026.safetensors",
342
+ "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00019-of-00026.safetensors",
343
+ "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00019-of-00026.safetensors",
344
+ "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00018-of-00026.safetensors",
345
+ "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00018-of-00026.safetensors",
346
+ "model.language_model.layers.26.linear_attn.norm.weight": "model-00019-of-00026.safetensors",
347
+ "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00018-of-00026.safetensors",
348
+ "model.language_model.layers.26.mlp.experts.down_proj": "model-00019-of-00026.safetensors",
349
+ "model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00018-of-00026.safetensors",
350
+ "model.language_model.layers.26.mlp.gate.weight": "model-00019-of-00026.safetensors",
351
+ "model.language_model.layers.26.mlp.shared_expert.down_proj.weight": "model-00019-of-00026.safetensors",
352
+ "model.language_model.layers.26.mlp.shared_expert.gate_proj.weight": "model-00019-of-00026.safetensors",
353
+ "model.language_model.layers.26.mlp.shared_expert.up_proj.weight": "model-00019-of-00026.safetensors",
354
+ "model.language_model.layers.26.mlp.shared_expert_gate.weight": "model-00019-of-00026.safetensors",
355
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00019-of-00026.safetensors",
356
+ "model.language_model.layers.27.input_layernorm.weight": "model-00019-of-00026.safetensors",
357
+ "model.language_model.layers.27.mlp.experts.down_proj": "model-00019-of-00026.safetensors",
358
+ "model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00018-of-00026.safetensors",
359
+ "model.language_model.layers.27.mlp.gate.weight": "model-00019-of-00026.safetensors",
360
+ "model.language_model.layers.27.mlp.shared_expert.down_proj.weight": "model-00019-of-00026.safetensors",
361
+ "model.language_model.layers.27.mlp.shared_expert.gate_proj.weight": "model-00019-of-00026.safetensors",
362
+ "model.language_model.layers.27.mlp.shared_expert.up_proj.weight": "model-00019-of-00026.safetensors",
363
+ "model.language_model.layers.27.mlp.shared_expert_gate.weight": "model-00019-of-00026.safetensors",
364
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00019-of-00026.safetensors",
365
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00019-of-00026.safetensors",
366
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00018-of-00026.safetensors",
367
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00018-of-00026.safetensors",
368
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00019-of-00026.safetensors",
369
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00018-of-00026.safetensors",
370
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00018-of-00026.safetensors",
371
+ "model.language_model.layers.28.input_layernorm.weight": "model-00019-of-00026.safetensors",
372
+ "model.language_model.layers.28.linear_attn.A_log": "model-00019-of-00026.safetensors",
373
+ "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00019-of-00026.safetensors",
374
+ "model.language_model.layers.28.linear_attn.dt_bias": "model-00019-of-00026.safetensors",
375
+ "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00019-of-00026.safetensors",
376
+ "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00019-of-00026.safetensors",
377
+ "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00018-of-00026.safetensors",
378
+ "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00018-of-00026.safetensors",
379
+ "model.language_model.layers.28.linear_attn.norm.weight": "model-00019-of-00026.safetensors",
380
+ "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00018-of-00026.safetensors",
381
+ "model.language_model.layers.28.mlp.experts.down_proj": "model-00018-of-00026.safetensors",
382
+ "model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00018-of-00026.safetensors",
383
+ "model.language_model.layers.28.mlp.gate.weight": "model-00019-of-00026.safetensors",
384
+ "model.language_model.layers.28.mlp.shared_expert.down_proj.weight": "model-00019-of-00026.safetensors",
385
+ "model.language_model.layers.28.mlp.shared_expert.gate_proj.weight": "model-00019-of-00026.safetensors",
386
+ "model.language_model.layers.28.mlp.shared_expert.up_proj.weight": "model-00019-of-00026.safetensors",
387
+ "model.language_model.layers.28.mlp.shared_expert_gate.weight": "model-00019-of-00026.safetensors",
388
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00019-of-00026.safetensors",
389
+ "model.language_model.layers.29.input_layernorm.weight": "model-00021-of-00026.safetensors",
390
+ "model.language_model.layers.29.linear_attn.A_log": "model-00021-of-00026.safetensors",
391
+ "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00021-of-00026.safetensors",
392
+ "model.language_model.layers.29.linear_attn.dt_bias": "model-00021-of-00026.safetensors",
393
+ "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00021-of-00026.safetensors",
394
+ "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00021-of-00026.safetensors",
395
+ "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00020-of-00026.safetensors",
396
+ "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00020-of-00026.safetensors",
397
+ "model.language_model.layers.29.linear_attn.norm.weight": "model-00021-of-00026.safetensors",
398
+ "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00020-of-00026.safetensors",
399
+ "model.language_model.layers.29.mlp.experts.down_proj": "model-00020-of-00026.safetensors",
400
+ "model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00021-of-00026.safetensors",
401
+ "model.language_model.layers.29.mlp.gate.weight": "model-00021-of-00026.safetensors",
402
+ "model.language_model.layers.29.mlp.shared_expert.down_proj.weight": "model-00021-of-00026.safetensors",
403
+ "model.language_model.layers.29.mlp.shared_expert.gate_proj.weight": "model-00021-of-00026.safetensors",
404
+ "model.language_model.layers.29.mlp.shared_expert.up_proj.weight": "model-00021-of-00026.safetensors",
405
+ "model.language_model.layers.29.mlp.shared_expert_gate.weight": "model-00021-of-00026.safetensors",
406
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00021-of-00026.safetensors",
407
+ "model.language_model.layers.3.input_layernorm.weight": "model-00003-of-00026.safetensors",
408
+ "model.language_model.layers.3.mlp.experts.down_proj": "model-00003-of-00026.safetensors",
409
+ "model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00003-of-00026.safetensors",
410
+ "model.language_model.layers.3.mlp.gate.weight": "model-00003-of-00026.safetensors",
411
+ "model.language_model.layers.3.mlp.shared_expert.down_proj.weight": "model-00003-of-00026.safetensors",
412
+ "model.language_model.layers.3.mlp.shared_expert.gate_proj.weight": "model-00003-of-00026.safetensors",
413
+ "model.language_model.layers.3.mlp.shared_expert.up_proj.weight": "model-00003-of-00026.safetensors",
414
+ "model.language_model.layers.3.mlp.shared_expert_gate.weight": "model-00003-of-00026.safetensors",
415
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00003-of-00026.safetensors",
416
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00003-of-00026.safetensors",
417
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00003-of-00026.safetensors",
418
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00003-of-00026.safetensors",
419
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00003-of-00026.safetensors",
420
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00003-of-00026.safetensors",
421
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00003-of-00026.safetensors",
422
+ "model.language_model.layers.30.input_layernorm.weight": "model-00021-of-00026.safetensors",
423
+ "model.language_model.layers.30.linear_attn.A_log": "model-00021-of-00026.safetensors",
424
+ "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00021-of-00026.safetensors",
425
+ "model.language_model.layers.30.linear_attn.dt_bias": "model-00021-of-00026.safetensors",
426
+ "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00021-of-00026.safetensors",
427
+ "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00021-of-00026.safetensors",
428
+ "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00020-of-00026.safetensors",
429
+ "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00020-of-00026.safetensors",
430
+ "model.language_model.layers.30.linear_attn.norm.weight": "model-00021-of-00026.safetensors",
431
+ "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00020-of-00026.safetensors",
432
+ "model.language_model.layers.30.mlp.experts.down_proj": "model-00021-of-00026.safetensors",
433
+ "model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00020-of-00026.safetensors",
434
+ "model.language_model.layers.30.mlp.gate.weight": "model-00021-of-00026.safetensors",
435
+ "model.language_model.layers.30.mlp.shared_expert.down_proj.weight": "model-00021-of-00026.safetensors",
436
+ "model.language_model.layers.30.mlp.shared_expert.gate_proj.weight": "model-00021-of-00026.safetensors",
437
+ "model.language_model.layers.30.mlp.shared_expert.up_proj.weight": "model-00021-of-00026.safetensors",
438
+ "model.language_model.layers.30.mlp.shared_expert_gate.weight": "model-00021-of-00026.safetensors",
439
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00021-of-00026.safetensors",
440
+ "model.language_model.layers.31.input_layernorm.weight": "model-00021-of-00026.safetensors",
441
+ "model.language_model.layers.31.mlp.experts.down_proj": "model-00020-of-00026.safetensors",
442
+ "model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00020-of-00026.safetensors",
443
+ "model.language_model.layers.31.mlp.gate.weight": "model-00021-of-00026.safetensors",
444
+ "model.language_model.layers.31.mlp.shared_expert.down_proj.weight": "model-00021-of-00026.safetensors",
445
+ "model.language_model.layers.31.mlp.shared_expert.gate_proj.weight": "model-00021-of-00026.safetensors",
446
+ "model.language_model.layers.31.mlp.shared_expert.up_proj.weight": "model-00021-of-00026.safetensors",
447
+ "model.language_model.layers.31.mlp.shared_expert_gate.weight": "model-00021-of-00026.safetensors",
448
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00021-of-00026.safetensors",
449
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00021-of-00026.safetensors",
450
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00020-of-00026.safetensors",
451
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00020-of-00026.safetensors",
452
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00021-of-00026.safetensors",
453
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00020-of-00026.safetensors",
454
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00020-of-00026.safetensors",
455
+ "model.language_model.layers.32.input_layernorm.weight": "model-00022-of-00026.safetensors",
456
+ "model.language_model.layers.32.linear_attn.A_log": "model-00022-of-00026.safetensors",
457
+ "model.language_model.layers.32.linear_attn.conv1d.weight": "model-00022-of-00026.safetensors",
458
+ "model.language_model.layers.32.linear_attn.dt_bias": "model-00022-of-00026.safetensors",
459
+ "model.language_model.layers.32.linear_attn.in_proj_a.weight": "model-00022-of-00026.safetensors",
460
+ "model.language_model.layers.32.linear_attn.in_proj_b.weight": "model-00022-of-00026.safetensors",
461
+ "model.language_model.layers.32.linear_attn.in_proj_qkv.weight": "model-00022-of-00026.safetensors",
462
+ "model.language_model.layers.32.linear_attn.in_proj_z.weight": "model-00022-of-00026.safetensors",
463
+ "model.language_model.layers.32.linear_attn.norm.weight": "model-00022-of-00026.safetensors",
464
+ "model.language_model.layers.32.linear_attn.out_proj.weight": "model-00022-of-00026.safetensors",
465
+ "model.language_model.layers.32.mlp.experts.down_proj": "model-00022-of-00026.safetensors",
466
+ "model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00022-of-00026.safetensors",
467
+ "model.language_model.layers.32.mlp.gate.weight": "model-00022-of-00026.safetensors",
468
+ "model.language_model.layers.32.mlp.shared_expert.down_proj.weight": "model-00022-of-00026.safetensors",
469
+ "model.language_model.layers.32.mlp.shared_expert.gate_proj.weight": "model-00022-of-00026.safetensors",
470
+ "model.language_model.layers.32.mlp.shared_expert.up_proj.weight": "model-00022-of-00026.safetensors",
471
+ "model.language_model.layers.32.mlp.shared_expert_gate.weight": "model-00022-of-00026.safetensors",
472
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00022-of-00026.safetensors",
473
+ "model.language_model.layers.33.input_layernorm.weight": "model-00022-of-00026.safetensors",
474
+ "model.language_model.layers.33.linear_attn.A_log": "model-00022-of-00026.safetensors",
475
+ "model.language_model.layers.33.linear_attn.conv1d.weight": "model-00022-of-00026.safetensors",
476
+ "model.language_model.layers.33.linear_attn.dt_bias": "model-00022-of-00026.safetensors",
477
+ "model.language_model.layers.33.linear_attn.in_proj_a.weight": "model-00022-of-00026.safetensors",
478
+ "model.language_model.layers.33.linear_attn.in_proj_b.weight": "model-00022-of-00026.safetensors",
479
+ "model.language_model.layers.33.linear_attn.in_proj_qkv.weight": "model-00022-of-00026.safetensors",
480
+ "model.language_model.layers.33.linear_attn.in_proj_z.weight": "model-00022-of-00026.safetensors",
481
+ "model.language_model.layers.33.linear_attn.norm.weight": "model-00022-of-00026.safetensors",
482
+ "model.language_model.layers.33.linear_attn.out_proj.weight": "model-00022-of-00026.safetensors",
483
+ "model.language_model.layers.33.mlp.experts.down_proj": "model-00022-of-00026.safetensors",
484
+ "model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00022-of-00026.safetensors",
485
+ "model.language_model.layers.33.mlp.gate.weight": "model-00022-of-00026.safetensors",
486
+ "model.language_model.layers.33.mlp.shared_expert.down_proj.weight": "model-00022-of-00026.safetensors",
487
+ "model.language_model.layers.33.mlp.shared_expert.gate_proj.weight": "model-00022-of-00026.safetensors",
488
+ "model.language_model.layers.33.mlp.shared_expert.up_proj.weight": "model-00022-of-00026.safetensors",
489
+ "model.language_model.layers.33.mlp.shared_expert_gate.weight": "model-00022-of-00026.safetensors",
490
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00022-of-00026.safetensors",
491
+ "model.language_model.layers.34.input_layernorm.weight": "model-00023-of-00026.safetensors",
492
+ "model.language_model.layers.34.linear_attn.A_log": "model-00023-of-00026.safetensors",
493
+ "model.language_model.layers.34.linear_attn.conv1d.weight": "model-00023-of-00026.safetensors",
494
+ "model.language_model.layers.34.linear_attn.dt_bias": "model-00023-of-00026.safetensors",
495
+ "model.language_model.layers.34.linear_attn.in_proj_a.weight": "model-00023-of-00026.safetensors",
496
+ "model.language_model.layers.34.linear_attn.in_proj_b.weight": "model-00023-of-00026.safetensors",
497
+ "model.language_model.layers.34.linear_attn.in_proj_qkv.weight": "model-00023-of-00026.safetensors",
498
+ "model.language_model.layers.34.linear_attn.in_proj_z.weight": "model-00023-of-00026.safetensors",
499
+ "model.language_model.layers.34.linear_attn.norm.weight": "model-00023-of-00026.safetensors",
500
+ "model.language_model.layers.34.linear_attn.out_proj.weight": "model-00023-of-00026.safetensors",
501
+ "model.language_model.layers.34.mlp.experts.down_proj": "model-00023-of-00026.safetensors",
502
+ "model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00023-of-00026.safetensors",
503
+ "model.language_model.layers.34.mlp.gate.weight": "model-00023-of-00026.safetensors",
504
+ "model.language_model.layers.34.mlp.shared_expert.down_proj.weight": "model-00023-of-00026.safetensors",
505
+ "model.language_model.layers.34.mlp.shared_expert.gate_proj.weight": "model-00023-of-00026.safetensors",
506
+ "model.language_model.layers.34.mlp.shared_expert.up_proj.weight": "model-00023-of-00026.safetensors",
507
+ "model.language_model.layers.34.mlp.shared_expert_gate.weight": "model-00023-of-00026.safetensors",
508
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00023-of-00026.safetensors",
509
+ "model.language_model.layers.35.input_layernorm.weight": "model-00023-of-00026.safetensors",
510
+ "model.language_model.layers.35.mlp.experts.down_proj": "model-00023-of-00026.safetensors",
511
+ "model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00023-of-00026.safetensors",
512
+ "model.language_model.layers.35.mlp.gate.weight": "model-00023-of-00026.safetensors",
513
+ "model.language_model.layers.35.mlp.shared_expert.down_proj.weight": "model-00023-of-00026.safetensors",
514
+ "model.language_model.layers.35.mlp.shared_expert.gate_proj.weight": "model-00023-of-00026.safetensors",
515
+ "model.language_model.layers.35.mlp.shared_expert.up_proj.weight": "model-00023-of-00026.safetensors",
516
+ "model.language_model.layers.35.mlp.shared_expert_gate.weight": "model-00023-of-00026.safetensors",
517
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00023-of-00026.safetensors",
518
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00023-of-00026.safetensors",
519
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00023-of-00026.safetensors",
520
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00023-of-00026.safetensors",
521
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00023-of-00026.safetensors",
522
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00023-of-00026.safetensors",
523
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00023-of-00026.safetensors",
524
+ "model.language_model.layers.36.input_layernorm.weight": "model-00024-of-00026.safetensors",
525
+ "model.language_model.layers.36.linear_attn.A_log": "model-00024-of-00026.safetensors",
526
+ "model.language_model.layers.36.linear_attn.conv1d.weight": "model-00024-of-00026.safetensors",
527
+ "model.language_model.layers.36.linear_attn.dt_bias": "model-00024-of-00026.safetensors",
528
+ "model.language_model.layers.36.linear_attn.in_proj_a.weight": "model-00024-of-00026.safetensors",
529
+ "model.language_model.layers.36.linear_attn.in_proj_b.weight": "model-00024-of-00026.safetensors",
530
+ "model.language_model.layers.36.linear_attn.in_proj_qkv.weight": "model-00024-of-00026.safetensors",
531
+ "model.language_model.layers.36.linear_attn.in_proj_z.weight": "model-00024-of-00026.safetensors",
532
+ "model.language_model.layers.36.linear_attn.norm.weight": "model-00024-of-00026.safetensors",
533
+ "model.language_model.layers.36.linear_attn.out_proj.weight": "model-00024-of-00026.safetensors",
534
+ "model.language_model.layers.36.mlp.experts.down_proj": "model-00024-of-00026.safetensors",
535
+ "model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00024-of-00026.safetensors",
536
+ "model.language_model.layers.36.mlp.gate.weight": "model-00024-of-00026.safetensors",
537
+ "model.language_model.layers.36.mlp.shared_expert.down_proj.weight": "model-00024-of-00026.safetensors",
538
+ "model.language_model.layers.36.mlp.shared_expert.gate_proj.weight": "model-00024-of-00026.safetensors",
539
+ "model.language_model.layers.36.mlp.shared_expert.up_proj.weight": "model-00024-of-00026.safetensors",
540
+ "model.language_model.layers.36.mlp.shared_expert_gate.weight": "model-00024-of-00026.safetensors",
541
+ "model.language_model.layers.36.post_attention_layernorm.weight": "model-00024-of-00026.safetensors",
542
+ "model.language_model.layers.37.input_layernorm.weight": "model-00024-of-00026.safetensors",
543
+ "model.language_model.layers.37.linear_attn.A_log": "model-00024-of-00026.safetensors",
544
+ "model.language_model.layers.37.linear_attn.conv1d.weight": "model-00024-of-00026.safetensors",
545
+ "model.language_model.layers.37.linear_attn.dt_bias": "model-00024-of-00026.safetensors",
546
+ "model.language_model.layers.37.linear_attn.in_proj_a.weight": "model-00024-of-00026.safetensors",
547
+ "model.language_model.layers.37.linear_attn.in_proj_b.weight": "model-00024-of-00026.safetensors",
548
+ "model.language_model.layers.37.linear_attn.in_proj_qkv.weight": "model-00024-of-00026.safetensors",
549
+ "model.language_model.layers.37.linear_attn.in_proj_z.weight": "model-00024-of-00026.safetensors",
550
+ "model.language_model.layers.37.linear_attn.norm.weight": "model-00024-of-00026.safetensors",
551
+ "model.language_model.layers.37.linear_attn.out_proj.weight": "model-00024-of-00026.safetensors",
552
+ "model.language_model.layers.37.mlp.experts.down_proj": "model-00024-of-00026.safetensors",
553
+ "model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00024-of-00026.safetensors",
554
+ "model.language_model.layers.37.mlp.gate.weight": "model-00024-of-00026.safetensors",
555
+ "model.language_model.layers.37.mlp.shared_expert.down_proj.weight": "model-00024-of-00026.safetensors",
556
+ "model.language_model.layers.37.mlp.shared_expert.gate_proj.weight": "model-00024-of-00026.safetensors",
557
+ "model.language_model.layers.37.mlp.shared_expert.up_proj.weight": "model-00024-of-00026.safetensors",
558
+ "model.language_model.layers.37.mlp.shared_expert_gate.weight": "model-00024-of-00026.safetensors",
559
+ "model.language_model.layers.37.post_attention_layernorm.weight": "model-00024-of-00026.safetensors",
560
+ "model.language_model.layers.38.input_layernorm.weight": "model-00025-of-00026.safetensors",
561
+ "model.language_model.layers.38.linear_attn.A_log": "model-00025-of-00026.safetensors",
562
+ "model.language_model.layers.38.linear_attn.conv1d.weight": "model-00025-of-00026.safetensors",
563
+ "model.language_model.layers.38.linear_attn.dt_bias": "model-00025-of-00026.safetensors",
564
+ "model.language_model.layers.38.linear_attn.in_proj_a.weight": "model-00025-of-00026.safetensors",
565
+ "model.language_model.layers.38.linear_attn.in_proj_b.weight": "model-00025-of-00026.safetensors",
566
+ "model.language_model.layers.38.linear_attn.in_proj_qkv.weight": "model-00025-of-00026.safetensors",
567
+ "model.language_model.layers.38.linear_attn.in_proj_z.weight": "model-00025-of-00026.safetensors",
568
+ "model.language_model.layers.38.linear_attn.norm.weight": "model-00025-of-00026.safetensors",
569
+ "model.language_model.layers.38.linear_attn.out_proj.weight": "model-00025-of-00026.safetensors",
570
+ "model.language_model.layers.38.mlp.experts.down_proj": "model-00025-of-00026.safetensors",
571
+ "model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00025-of-00026.safetensors",
572
+ "model.language_model.layers.38.mlp.gate.weight": "model-00025-of-00026.safetensors",
573
+ "model.language_model.layers.38.mlp.shared_expert.down_proj.weight": "model-00025-of-00026.safetensors",
574
+ "model.language_model.layers.38.mlp.shared_expert.gate_proj.weight": "model-00025-of-00026.safetensors",
575
+ "model.language_model.layers.38.mlp.shared_expert.up_proj.weight": "model-00025-of-00026.safetensors",
576
+ "model.language_model.layers.38.mlp.shared_expert_gate.weight": "model-00025-of-00026.safetensors",
577
+ "model.language_model.layers.38.post_attention_layernorm.weight": "model-00025-of-00026.safetensors",
578
+ "model.language_model.layers.39.input_layernorm.weight": "model-00026-of-00026.safetensors",
579
+ "model.language_model.layers.39.mlp.experts.down_proj": "model-00026-of-00026.safetensors",
580
+ "model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00025-of-00026.safetensors",
581
+ "model.language_model.layers.39.mlp.gate.weight": "model-00026-of-00026.safetensors",
582
+ "model.language_model.layers.39.mlp.shared_expert.down_proj.weight": "model-00026-of-00026.safetensors",
583
+ "model.language_model.layers.39.mlp.shared_expert.gate_proj.weight": "model-00026-of-00026.safetensors",
584
+ "model.language_model.layers.39.mlp.shared_expert.up_proj.weight": "model-00026-of-00026.safetensors",
585
+ "model.language_model.layers.39.mlp.shared_expert_gate.weight": "model-00026-of-00026.safetensors",
586
+ "model.language_model.layers.39.post_attention_layernorm.weight": "model-00026-of-00026.safetensors",
587
+ "model.language_model.layers.39.self_attn.k_norm.weight": "model-00026-of-00026.safetensors",
588
+ "model.language_model.layers.39.self_attn.k_proj.weight": "model-00026-of-00026.safetensors",
589
+ "model.language_model.layers.39.self_attn.o_proj.weight": "model-00026-of-00026.safetensors",
590
+ "model.language_model.layers.39.self_attn.q_norm.weight": "model-00026-of-00026.safetensors",
591
+ "model.language_model.layers.39.self_attn.q_proj.weight": "model-00026-of-00026.safetensors",
592
+ "model.language_model.layers.39.self_attn.v_proj.weight": "model-00026-of-00026.safetensors",
593
+ "model.language_model.layers.4.input_layernorm.weight": "model-00004-of-00026.safetensors",
594
+ "model.language_model.layers.4.linear_attn.A_log": "model-00004-of-00026.safetensors",
595
+ "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00004-of-00026.safetensors",
596
+ "model.language_model.layers.4.linear_attn.dt_bias": "model-00004-of-00026.safetensors",
597
+ "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00004-of-00026.safetensors",
598
+ "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00004-of-00026.safetensors",
599
+ "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00004-of-00026.safetensors",
600
+ "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00004-of-00026.safetensors",
601
+ "model.language_model.layers.4.linear_attn.norm.weight": "model-00004-of-00026.safetensors",
602
+ "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00004-of-00026.safetensors",
603
+ "model.language_model.layers.4.mlp.experts.down_proj": "model-00004-of-00026.safetensors",
604
+ "model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00004-of-00026.safetensors",
605
+ "model.language_model.layers.4.mlp.gate.weight": "model-00004-of-00026.safetensors",
606
+ "model.language_model.layers.4.mlp.shared_expert.down_proj.weight": "model-00004-of-00026.safetensors",
607
+ "model.language_model.layers.4.mlp.shared_expert.gate_proj.weight": "model-00004-of-00026.safetensors",
608
+ "model.language_model.layers.4.mlp.shared_expert.up_proj.weight": "model-00004-of-00026.safetensors",
609
+ "model.language_model.layers.4.mlp.shared_expert_gate.weight": "model-00004-of-00026.safetensors",
610
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00004-of-00026.safetensors",
611
+ "model.language_model.layers.5.input_layernorm.weight": "model-00004-of-00026.safetensors",
612
+ "model.language_model.layers.5.linear_attn.A_log": "model-00004-of-00026.safetensors",
613
+ "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00004-of-00026.safetensors",
614
+ "model.language_model.layers.5.linear_attn.dt_bias": "model-00004-of-00026.safetensors",
615
+ "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00004-of-00026.safetensors",
616
+ "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00004-of-00026.safetensors",
617
+ "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00004-of-00026.safetensors",
618
+ "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00004-of-00026.safetensors",
619
+ "model.language_model.layers.5.linear_attn.norm.weight": "model-00004-of-00026.safetensors",
620
+ "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00004-of-00026.safetensors",
621
+ "model.language_model.layers.5.mlp.experts.down_proj": "model-00004-of-00026.safetensors",
622
+ "model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00004-of-00026.safetensors",
623
+ "model.language_model.layers.5.mlp.gate.weight": "model-00004-of-00026.safetensors",
624
+ "model.language_model.layers.5.mlp.shared_expert.down_proj.weight": "model-00004-of-00026.safetensors",
625
+ "model.language_model.layers.5.mlp.shared_expert.gate_proj.weight": "model-00004-of-00026.safetensors",
626
+ "model.language_model.layers.5.mlp.shared_expert.up_proj.weight": "model-00004-of-00026.safetensors",
627
+ "model.language_model.layers.5.mlp.shared_expert_gate.weight": "model-00004-of-00026.safetensors",
628
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00004-of-00026.safetensors",
629
+ "model.language_model.layers.6.input_layernorm.weight": "model-00005-of-00026.safetensors",
630
+ "model.language_model.layers.6.linear_attn.A_log": "model-00005-of-00026.safetensors",
631
+ "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00005-of-00026.safetensors",
632
+ "model.language_model.layers.6.linear_attn.dt_bias": "model-00005-of-00026.safetensors",
633
+ "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00005-of-00026.safetensors",
634
+ "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00005-of-00026.safetensors",
635
+ "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00005-of-00026.safetensors",
636
+ "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00005-of-00026.safetensors",
637
+ "model.language_model.layers.6.linear_attn.norm.weight": "model-00005-of-00026.safetensors",
638
+ "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00005-of-00026.safetensors",
639
+ "model.language_model.layers.6.mlp.experts.down_proj": "model-00005-of-00026.safetensors",
640
+ "model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00005-of-00026.safetensors",
641
+ "model.language_model.layers.6.mlp.gate.weight": "model-00005-of-00026.safetensors",
642
+ "model.language_model.layers.6.mlp.shared_expert.down_proj.weight": "model-00005-of-00026.safetensors",
643
+ "model.language_model.layers.6.mlp.shared_expert.gate_proj.weight": "model-00005-of-00026.safetensors",
644
+ "model.language_model.layers.6.mlp.shared_expert.up_proj.weight": "model-00005-of-00026.safetensors",
645
+ "model.language_model.layers.6.mlp.shared_expert_gate.weight": "model-00005-of-00026.safetensors",
646
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00005-of-00026.safetensors",
647
+ "model.language_model.layers.7.input_layernorm.weight": "model-00005-of-00026.safetensors",
648
+ "model.language_model.layers.7.mlp.experts.down_proj": "model-00005-of-00026.safetensors",
649
+ "model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00005-of-00026.safetensors",
650
+ "model.language_model.layers.7.mlp.gate.weight": "model-00005-of-00026.safetensors",
651
+ "model.language_model.layers.7.mlp.shared_expert.down_proj.weight": "model-00005-of-00026.safetensors",
652
+ "model.language_model.layers.7.mlp.shared_expert.gate_proj.weight": "model-00005-of-00026.safetensors",
653
+ "model.language_model.layers.7.mlp.shared_expert.up_proj.weight": "model-00005-of-00026.safetensors",
654
+ "model.language_model.layers.7.mlp.shared_expert_gate.weight": "model-00005-of-00026.safetensors",
655
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00005-of-00026.safetensors",
656
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00005-of-00026.safetensors",
657
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00005-of-00026.safetensors",
658
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00005-of-00026.safetensors",
659
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00005-of-00026.safetensors",
660
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00005-of-00026.safetensors",
661
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00005-of-00026.safetensors",
662
+ "model.language_model.layers.8.input_layernorm.weight": "model-00007-of-00026.safetensors",
663
+ "model.language_model.layers.8.linear_attn.A_log": "model-00007-of-00026.safetensors",
664
+ "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00007-of-00026.safetensors",
665
+ "model.language_model.layers.8.linear_attn.dt_bias": "model-00007-of-00026.safetensors",
666
+ "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00007-of-00026.safetensors",
667
+ "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00007-of-00026.safetensors",
668
+ "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00006-of-00026.safetensors",
669
+ "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00006-of-00026.safetensors",
670
+ "model.language_model.layers.8.linear_attn.norm.weight": "model-00007-of-00026.safetensors",
671
+ "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00006-of-00026.safetensors",
672
+ "model.language_model.layers.8.mlp.experts.down_proj": "model-00006-of-00026.safetensors",
673
+ "model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00006-of-00026.safetensors",
674
+ "model.language_model.layers.8.mlp.gate.weight": "model-00007-of-00026.safetensors",
675
+ "model.language_model.layers.8.mlp.shared_expert.down_proj.weight": "model-00007-of-00026.safetensors",
676
+ "model.language_model.layers.8.mlp.shared_expert.gate_proj.weight": "model-00007-of-00026.safetensors",
677
+ "model.language_model.layers.8.mlp.shared_expert.up_proj.weight": "model-00007-of-00026.safetensors",
678
+ "model.language_model.layers.8.mlp.shared_expert_gate.weight": "model-00007-of-00026.safetensors",
679
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00007-of-00026.safetensors",
680
+ "model.language_model.layers.9.input_layernorm.weight": "model-00007-of-00026.safetensors",
681
+ "model.language_model.layers.9.linear_attn.A_log": "model-00007-of-00026.safetensors",
682
+ "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00007-of-00026.safetensors",
683
+ "model.language_model.layers.9.linear_attn.dt_bias": "model-00007-of-00026.safetensors",
684
+ "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00007-of-00026.safetensors",
685
+ "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00007-of-00026.safetensors",
686
+ "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00006-of-00026.safetensors",
687
+ "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00006-of-00026.safetensors",
688
+ "model.language_model.layers.9.linear_attn.norm.weight": "model-00007-of-00026.safetensors",
689
+ "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00006-of-00026.safetensors",
690
+ "model.language_model.layers.9.mlp.experts.down_proj": "model-00006-of-00026.safetensors",
691
+ "model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00006-of-00026.safetensors",
692
+ "model.language_model.layers.9.mlp.gate.weight": "model-00007-of-00026.safetensors",
693
+ "model.language_model.layers.9.mlp.shared_expert.down_proj.weight": "model-00007-of-00026.safetensors",
694
+ "model.language_model.layers.9.mlp.shared_expert.gate_proj.weight": "model-00007-of-00026.safetensors",
695
+ "model.language_model.layers.9.mlp.shared_expert.up_proj.weight": "model-00007-of-00026.safetensors",
696
+ "model.language_model.layers.9.mlp.shared_expert_gate.weight": "model-00007-of-00026.safetensors",
697
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00007-of-00026.safetensors",
698
+ "model.language_model.norm.weight": "model-00026-of-00026.safetensors",
699
+ "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00026.safetensors",
700
+ "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00026.safetensors",
701
+ "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00026.safetensors",
702
+ "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00026.safetensors",
703
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
704
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
705
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
706
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
707
+ "model.visual.blocks.0.norm1.bias": "model-00002-of-00026.safetensors",
708
+ "model.visual.blocks.0.norm1.weight": "model-00002-of-00026.safetensors",
709
+ "model.visual.blocks.0.norm2.bias": "model-00002-of-00026.safetensors",
710
+ "model.visual.blocks.0.norm2.weight": "model-00002-of-00026.safetensors",
711
+ "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00026.safetensors",
712
+ "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00026.safetensors",
713
+ "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00026.safetensors",
714
+ "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00026.safetensors",
715
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
716
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
717
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
718
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
719
+ "model.visual.blocks.1.norm1.bias": "model-00002-of-00026.safetensors",
720
+ "model.visual.blocks.1.norm1.weight": "model-00002-of-00026.safetensors",
721
+ "model.visual.blocks.1.norm2.bias": "model-00002-of-00026.safetensors",
722
+ "model.visual.blocks.1.norm2.weight": "model-00002-of-00026.safetensors",
723
+ "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00026.safetensors",
724
+ "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00026.safetensors",
725
+ "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00026.safetensors",
726
+ "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00026.safetensors",
727
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
728
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
729
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
730
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
731
+ "model.visual.blocks.10.norm1.bias": "model-00002-of-00026.safetensors",
732
+ "model.visual.blocks.10.norm1.weight": "model-00002-of-00026.safetensors",
733
+ "model.visual.blocks.10.norm2.bias": "model-00002-of-00026.safetensors",
734
+ "model.visual.blocks.10.norm2.weight": "model-00002-of-00026.safetensors",
735
+ "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00026.safetensors",
736
+ "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00026.safetensors",
737
+ "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00026.safetensors",
738
+ "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00026.safetensors",
739
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
740
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
741
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
742
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
743
+ "model.visual.blocks.11.norm1.bias": "model-00002-of-00026.safetensors",
744
+ "model.visual.blocks.11.norm1.weight": "model-00002-of-00026.safetensors",
745
+ "model.visual.blocks.11.norm2.bias": "model-00002-of-00026.safetensors",
746
+ "model.visual.blocks.11.norm2.weight": "model-00002-of-00026.safetensors",
747
+ "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00026.safetensors",
748
+ "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00026.safetensors",
749
+ "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00026.safetensors",
750
+ "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00026.safetensors",
751
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
752
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00026.safetensors",
753
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
754
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00026.safetensors",
755
+ "model.visual.blocks.12.norm1.bias": "model-00002-of-00026.safetensors",
756
+ "model.visual.blocks.12.norm1.weight": "model-00002-of-00026.safetensors",
757
+ "model.visual.blocks.12.norm2.bias": "model-00002-of-00026.safetensors",
758
+ "model.visual.blocks.12.norm2.weight": "model-00002-of-00026.safetensors",
759
+ "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00026.safetensors",
760
+ "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00026.safetensors",
761
+ "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00026.safetensors",
762
+ "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00026.safetensors",
763
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
764
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
765
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
766
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
767
+ "model.visual.blocks.13.norm1.bias": "model-00002-of-00026.safetensors",
768
+ "model.visual.blocks.13.norm1.weight": "model-00002-of-00026.safetensors",
769
+ "model.visual.blocks.13.norm2.bias": "model-00002-of-00026.safetensors",
770
+ "model.visual.blocks.13.norm2.weight": "model-00002-of-00026.safetensors",
771
+ "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00026.safetensors",
772
+ "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00026.safetensors",
773
+ "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00026.safetensors",
774
+ "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00026.safetensors",
775
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
776
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
777
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
778
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
779
+ "model.visual.blocks.14.norm1.bias": "model-00002-of-00026.safetensors",
780
+ "model.visual.blocks.14.norm1.weight": "model-00002-of-00026.safetensors",
781
+ "model.visual.blocks.14.norm2.bias": "model-00002-of-00026.safetensors",
782
+ "model.visual.blocks.14.norm2.weight": "model-00002-of-00026.safetensors",
783
+ "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00026.safetensors",
784
+ "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00026.safetensors",
785
+ "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00026.safetensors",
786
+ "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00026.safetensors",
787
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
788
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
789
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
790
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
791
+ "model.visual.blocks.15.norm1.bias": "model-00002-of-00026.safetensors",
792
+ "model.visual.blocks.15.norm1.weight": "model-00002-of-00026.safetensors",
793
+ "model.visual.blocks.15.norm2.bias": "model-00002-of-00026.safetensors",
794
+ "model.visual.blocks.15.norm2.weight": "model-00002-of-00026.safetensors",
795
+ "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00026.safetensors",
796
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00026.safetensors",
797
+ "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00026.safetensors",
798
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00026.safetensors",
799
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
800
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
801
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
802
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
803
+ "model.visual.blocks.16.norm1.bias": "model-00002-of-00026.safetensors",
804
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00026.safetensors",
805
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00026.safetensors",
806
+ "model.visual.blocks.16.norm2.weight": "model-00002-of-00026.safetensors",
807
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00026.safetensors",
808
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00026.safetensors",
809
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00026.safetensors",
810
+ "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00026.safetensors",
811
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
812
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
813
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
814
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
815
+ "model.visual.blocks.17.norm1.bias": "model-00002-of-00026.safetensors",
816
+ "model.visual.blocks.17.norm1.weight": "model-00002-of-00026.safetensors",
817
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00026.safetensors",
818
+ "model.visual.blocks.17.norm2.weight": "model-00002-of-00026.safetensors",
819
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00026.safetensors",
820
+ "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00026.safetensors",
821
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00026.safetensors",
822
+ "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00026.safetensors",
823
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
824
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
825
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
826
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
827
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00026.safetensors",
828
+ "model.visual.blocks.18.norm1.weight": "model-00002-of-00026.safetensors",
829
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00026.safetensors",
830
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00026.safetensors",
831
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00026.safetensors",
832
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00026.safetensors",
833
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00026.safetensors",
834
+ "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00026.safetensors",
835
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
836
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
837
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
838
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
839
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00026.safetensors",
840
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00026.safetensors",
841
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00026.safetensors",
842
+ "model.visual.blocks.19.norm2.weight": "model-00002-of-00026.safetensors",
843
+ "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00026.safetensors",
844
+ "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00026.safetensors",
845
+ "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00026.safetensors",
846
+ "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00026.safetensors",
847
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
848
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
849
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
850
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
851
+ "model.visual.blocks.2.norm1.bias": "model-00002-of-00026.safetensors",
852
+ "model.visual.blocks.2.norm1.weight": "model-00002-of-00026.safetensors",
853
+ "model.visual.blocks.2.norm2.bias": "model-00002-of-00026.safetensors",
854
+ "model.visual.blocks.2.norm2.weight": "model-00002-of-00026.safetensors",
855
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00026.safetensors",
856
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00026.safetensors",
857
+ "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00026.safetensors",
858
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00026.safetensors",
859
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
860
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
861
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
862
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
863
+ "model.visual.blocks.20.norm1.bias": "model-00002-of-00026.safetensors",
864
+ "model.visual.blocks.20.norm1.weight": "model-00002-of-00026.safetensors",
865
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00026.safetensors",
866
+ "model.visual.blocks.20.norm2.weight": "model-00002-of-00026.safetensors",
867
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00026.safetensors",
868
+ "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00026.safetensors",
869
+ "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00026.safetensors",
870
+ "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00026.safetensors",
871
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
872
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
873
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
874
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
875
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00026.safetensors",
876
+ "model.visual.blocks.21.norm1.weight": "model-00002-of-00026.safetensors",
877
+ "model.visual.blocks.21.norm2.bias": "model-00002-of-00026.safetensors",
878
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00026.safetensors",
879
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00026.safetensors",
880
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00026.safetensors",
881
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00026.safetensors",
882
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00026.safetensors",
883
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
884
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
885
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
886
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
887
+ "model.visual.blocks.22.norm1.bias": "model-00002-of-00026.safetensors",
888
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00026.safetensors",
889
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00026.safetensors",
890
+ "model.visual.blocks.22.norm2.weight": "model-00002-of-00026.safetensors",
891
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00026.safetensors",
892
+ "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00026.safetensors",
893
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00026.safetensors",
894
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00026.safetensors",
895
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
896
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
897
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
898
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
899
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00026.safetensors",
900
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00026.safetensors",
901
+ "model.visual.blocks.23.norm2.bias": "model-00002-of-00026.safetensors",
902
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00026.safetensors",
903
+ "model.visual.blocks.24.attn.proj.bias": "model-00002-of-00026.safetensors",
904
+ "model.visual.blocks.24.attn.proj.weight": "model-00002-of-00026.safetensors",
905
+ "model.visual.blocks.24.attn.qkv.bias": "model-00002-of-00026.safetensors",
906
+ "model.visual.blocks.24.attn.qkv.weight": "model-00002-of-00026.safetensors",
907
+ "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
908
+ "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
909
+ "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
910
+ "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
911
+ "model.visual.blocks.24.norm1.bias": "model-00002-of-00026.safetensors",
912
+ "model.visual.blocks.24.norm1.weight": "model-00002-of-00026.safetensors",
913
+ "model.visual.blocks.24.norm2.bias": "model-00002-of-00026.safetensors",
914
+ "model.visual.blocks.24.norm2.weight": "model-00002-of-00026.safetensors",
915
+ "model.visual.blocks.25.attn.proj.bias": "model-00002-of-00026.safetensors",
916
+ "model.visual.blocks.25.attn.proj.weight": "model-00002-of-00026.safetensors",
917
+ "model.visual.blocks.25.attn.qkv.bias": "model-00002-of-00026.safetensors",
918
+ "model.visual.blocks.25.attn.qkv.weight": "model-00002-of-00026.safetensors",
919
+ "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
920
+ "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
921
+ "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
922
+ "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
923
+ "model.visual.blocks.25.norm1.bias": "model-00002-of-00026.safetensors",
924
+ "model.visual.blocks.25.norm1.weight": "model-00002-of-00026.safetensors",
925
+ "model.visual.blocks.25.norm2.bias": "model-00002-of-00026.safetensors",
926
+ "model.visual.blocks.25.norm2.weight": "model-00002-of-00026.safetensors",
927
+ "model.visual.blocks.26.attn.proj.bias": "model-00002-of-00026.safetensors",
928
+ "model.visual.blocks.26.attn.proj.weight": "model-00002-of-00026.safetensors",
929
+ "model.visual.blocks.26.attn.qkv.bias": "model-00002-of-00026.safetensors",
930
+ "model.visual.blocks.26.attn.qkv.weight": "model-00002-of-00026.safetensors",
931
+ "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
932
+ "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
933
+ "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
934
+ "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
935
+ "model.visual.blocks.26.norm1.bias": "model-00002-of-00026.safetensors",
936
+ "model.visual.blocks.26.norm1.weight": "model-00002-of-00026.safetensors",
937
+ "model.visual.blocks.26.norm2.bias": "model-00002-of-00026.safetensors",
938
+ "model.visual.blocks.26.norm2.weight": "model-00002-of-00026.safetensors",
939
+ "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00026.safetensors",
940
+ "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00026.safetensors",
941
+ "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00026.safetensors",
942
+ "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00026.safetensors",
943
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
944
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
945
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
946
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
947
+ "model.visual.blocks.3.norm1.bias": "model-00002-of-00026.safetensors",
948
+ "model.visual.blocks.3.norm1.weight": "model-00002-of-00026.safetensors",
949
+ "model.visual.blocks.3.norm2.bias": "model-00002-of-00026.safetensors",
950
+ "model.visual.blocks.3.norm2.weight": "model-00002-of-00026.safetensors",
951
+ "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00026.safetensors",
952
+ "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00026.safetensors",
953
+ "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00026.safetensors",
954
+ "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00026.safetensors",
955
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
956
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
957
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
958
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
959
+ "model.visual.blocks.4.norm1.bias": "model-00002-of-00026.safetensors",
960
+ "model.visual.blocks.4.norm1.weight": "model-00002-of-00026.safetensors",
961
+ "model.visual.blocks.4.norm2.bias": "model-00002-of-00026.safetensors",
962
+ "model.visual.blocks.4.norm2.weight": "model-00002-of-00026.safetensors",
963
+ "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00026.safetensors",
964
+ "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00026.safetensors",
965
+ "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00026.safetensors",
966
+ "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00026.safetensors",
967
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
968
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
969
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
970
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
971
+ "model.visual.blocks.5.norm1.bias": "model-00002-of-00026.safetensors",
972
+ "model.visual.blocks.5.norm1.weight": "model-00002-of-00026.safetensors",
973
+ "model.visual.blocks.5.norm2.bias": "model-00002-of-00026.safetensors",
974
+ "model.visual.blocks.5.norm2.weight": "model-00002-of-00026.safetensors",
975
+ "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00026.safetensors",
976
+ "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00026.safetensors",
977
+ "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00026.safetensors",
978
+ "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00026.safetensors",
979
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
980
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
981
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
982
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
983
+ "model.visual.blocks.6.norm1.bias": "model-00002-of-00026.safetensors",
984
+ "model.visual.blocks.6.norm1.weight": "model-00002-of-00026.safetensors",
985
+ "model.visual.blocks.6.norm2.bias": "model-00002-of-00026.safetensors",
986
+ "model.visual.blocks.6.norm2.weight": "model-00002-of-00026.safetensors",
987
+ "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00026.safetensors",
988
+ "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00026.safetensors",
989
+ "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00026.safetensors",
990
+ "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00026.safetensors",
991
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
992
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
993
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
994
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
995
+ "model.visual.blocks.7.norm1.bias": "model-00002-of-00026.safetensors",
996
+ "model.visual.blocks.7.norm1.weight": "model-00002-of-00026.safetensors",
997
+ "model.visual.blocks.7.norm2.bias": "model-00002-of-00026.safetensors",
998
+ "model.visual.blocks.7.norm2.weight": "model-00002-of-00026.safetensors",
999
+ "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00026.safetensors",
1000
+ "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00026.safetensors",
1001
+ "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00026.safetensors",
1002
+ "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00026.safetensors",
1003
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
1004
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
1005
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
1006
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
1007
+ "model.visual.blocks.8.norm1.bias": "model-00002-of-00026.safetensors",
1008
+ "model.visual.blocks.8.norm1.weight": "model-00002-of-00026.safetensors",
1009
+ "model.visual.blocks.8.norm2.bias": "model-00002-of-00026.safetensors",
1010
+ "model.visual.blocks.8.norm2.weight": "model-00002-of-00026.safetensors",
1011
+ "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00026.safetensors",
1012
+ "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00026.safetensors",
1013
+ "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00026.safetensors",
1014
+ "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00026.safetensors",
1015
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00026.safetensors",
1016
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00026.safetensors",
1017
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00026.safetensors",
1018
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00026.safetensors",
1019
+ "model.visual.blocks.9.norm1.bias": "model-00002-of-00026.safetensors",
1020
+ "model.visual.blocks.9.norm1.weight": "model-00002-of-00026.safetensors",
1021
+ "model.visual.blocks.9.norm2.bias": "model-00002-of-00026.safetensors",
1022
+ "model.visual.blocks.9.norm2.weight": "model-00002-of-00026.safetensors",
1023
+ "model.visual.merger.linear_fc1.bias": "model-00002-of-00026.safetensors",
1024
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00026.safetensors",
1025
+ "model.visual.merger.linear_fc2.bias": "model-00002-of-00026.safetensors",
1026
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00026.safetensors",
1027
+ "model.visual.merger.norm.bias": "model-00002-of-00026.safetensors",
1028
+ "model.visual.merger.norm.weight": "model-00002-of-00026.safetensors",
1029
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00026.safetensors",
1030
+ "model.visual.patch_embed.proj.weight": "model-00002-of-00026.safetensors",
1031
+ "model.visual.pos_embed.weight": "model-00002-of-00026.safetensors",
1032
+ "mtp.fc.weight": "model-00026-of-00026.safetensors",
1033
+ "mtp.layers.0.input_layernorm.weight": "model-00026-of-00026.safetensors",
1034
+ "mtp.layers.0.mlp.experts.down_proj": "model-00026-of-00026.safetensors",
1035
+ "mtp.layers.0.mlp.experts.gate_up_proj": "model-00025-of-00026.safetensors",
1036
+ "mtp.layers.0.mlp.gate.weight": "model-00026-of-00026.safetensors",
1037
+ "mtp.layers.0.mlp.shared_expert.down_proj.weight": "model-00026-of-00026.safetensors",
1038
+ "mtp.layers.0.mlp.shared_expert.gate_proj.weight": "model-00026-of-00026.safetensors",
1039
+ "mtp.layers.0.mlp.shared_expert.up_proj.weight": "model-00026-of-00026.safetensors",
1040
+ "mtp.layers.0.mlp.shared_expert_gate.weight": "model-00026-of-00026.safetensors",
1041
+ "mtp.layers.0.post_attention_layernorm.weight": "model-00026-of-00026.safetensors",
1042
+ "mtp.layers.0.self_attn.k_norm.weight": "model-00026-of-00026.safetensors",
1043
+ "mtp.layers.0.self_attn.k_proj.weight": "model-00026-of-00026.safetensors",
1044
+ "mtp.layers.0.self_attn.o_proj.weight": "model-00026-of-00026.safetensors",
1045
+ "mtp.layers.0.self_attn.q_norm.weight": "model-00026-of-00026.safetensors",
1046
+ "mtp.layers.0.self_attn.q_proj.weight": "model-00026-of-00026.safetensors",
1047
+ "mtp.layers.0.self_attn.v_proj.weight": "model-00026-of-00026.safetensors",
1048
+ "mtp.norm.weight": "model-00026-of-00026.safetensors",
1049
+ "mtp.pre_fc_norm_embedding.weight": "model-00026-of-00026.safetensors",
1050
+ "mtp.pre_fc_norm_hidden.weight": "model-00026-of-00026.safetensors"
1051
+ }
1052
+ }
processor_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "do_convert_rgb": true,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "merge_size": 2,
19
+ "patch_size": 16,
20
+ "resample": 3,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 16777216,
24
+ "shortest_edge": 65536
25
+ },
26
+ "temporal_patch_size": 2
27
+ },
28
+ "processor_class": "Qwen3VLProcessor",
29
+ "video_processor": {
30
+ "do_convert_rgb": true,
31
+ "do_normalize": true,
32
+ "do_rescale": true,
33
+ "do_resize": true,
34
+ "do_sample_frames": true,
35
+ "fps": 2,
36
+ "image_mean": [
37
+ 0.5,
38
+ 0.5,
39
+ 0.5
40
+ ],
41
+ "image_std": [
42
+ 0.5,
43
+ 0.5,
44
+ 0.5
45
+ ],
46
+ "max_frames": 768,
47
+ "merge_size": 2,
48
+ "min_frames": 4,
49
+ "patch_size": 16,
50
+ "resample": 3,
51
+ "rescale_factor": 0.00392156862745098,
52
+ "return_metadata": false,
53
+ "size": {
54
+ "longest_edge": 25165824,
55
+ "shortest_edge": 4096
56
+ },
57
+ "temporal_patch_size": 2,
58
+ "video_processor_type": "Qwen3VLVideoProcessor"
59
+ }
60
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
tokenizer_config.json ADDED
@@ -0,0 +1,300 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "padding_side": "right",
25
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
26
+ "processor_class": "Qwen3VLProcessor",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "TokenizersBackend",
29
+ "unk_token": null,
30
+ "video_token": "<|video_pad|>",
31
+ "vision_bos_token": "<|vision_start|>",
32
+ "vision_eos_token": "<|vision_end|>",
33
+ "added_tokens_decoder": {
34
+ "248044": {
35
+ "content": "<|endoftext|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ "248045": {
43
+ "content": "<|im_start|>",
44
+ "single_word": false,
45
+ "lstrip": false,
46
+ "rstrip": false,
47
+ "normalized": false,
48
+ "special": true
49
+ },
50
+ "248046": {
51
+ "content": "<|im_end|>",
52
+ "single_word": false,
53
+ "lstrip": false,
54
+ "rstrip": false,
55
+ "normalized": false,
56
+ "special": true
57
+ },
58
+ "248047": {
59
+ "content": "<|object_ref_start|>",
60
+ "single_word": false,
61
+ "lstrip": false,
62
+ "rstrip": false,
63
+ "normalized": false,
64
+ "special": true
65
+ },
66
+ "248048": {
67
+ "content": "<|object_ref_end|>",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": false,
72
+ "special": true
73
+ },
74
+ "248049": {
75
+ "content": "<|box_start|>",
76
+ "single_word": false,
77
+ "lstrip": false,
78
+ "rstrip": false,
79
+ "normalized": false,
80
+ "special": true
81
+ },
82
+ "248050": {
83
+ "content": "<|box_end|>",
84
+ "single_word": false,
85
+ "lstrip": false,
86
+ "rstrip": false,
87
+ "normalized": false,
88
+ "special": true
89
+ },
90
+ "248051": {
91
+ "content": "<|quad_start|>",
92
+ "single_word": false,
93
+ "lstrip": false,
94
+ "rstrip": false,
95
+ "normalized": false,
96
+ "special": true
97
+ },
98
+ "248052": {
99
+ "content": "<|quad_end|>",
100
+ "single_word": false,
101
+ "lstrip": false,
102
+ "rstrip": false,
103
+ "normalized": false,
104
+ "special": true
105
+ },
106
+ "248053": {
107
+ "content": "<|vision_start|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ "248054": {
115
+ "content": "<|vision_end|>",
116
+ "single_word": false,
117
+ "lstrip": false,
118
+ "rstrip": false,
119
+ "normalized": false,
120
+ "special": true
121
+ },
122
+ "248055": {
123
+ "content": "<|vision_pad|>",
124
+ "single_word": false,
125
+ "lstrip": false,
126
+ "rstrip": false,
127
+ "normalized": false,
128
+ "special": true
129
+ },
130
+ "248056": {
131
+ "content": "<|image_pad|>",
132
+ "single_word": false,
133
+ "lstrip": false,
134
+ "rstrip": false,
135
+ "normalized": false,
136
+ "special": true
137
+ },
138
+ "248057": {
139
+ "content": "<|video_pad|>",
140
+ "single_word": false,
141
+ "lstrip": false,
142
+ "rstrip": false,
143
+ "normalized": false,
144
+ "special": true
145
+ },
146
+ "248058": {
147
+ "content": "<tool_call>",
148
+ "single_word": false,
149
+ "lstrip": false,
150
+ "rstrip": false,
151
+ "normalized": false,
152
+ "special": false
153
+ },
154
+ "248059": {
155
+ "content": "</tool_call>",
156
+ "single_word": false,
157
+ "lstrip": false,
158
+ "rstrip": false,
159
+ "normalized": false,
160
+ "special": false
161
+ },
162
+ "248060": {
163
+ "content": "<|fim_prefix|>",
164
+ "single_word": false,
165
+ "lstrip": false,
166
+ "rstrip": false,
167
+ "normalized": false,
168
+ "special": false
169
+ },
170
+ "248061": {
171
+ "content": "<|fim_middle|>",
172
+ "single_word": false,
173
+ "lstrip": false,
174
+ "rstrip": false,
175
+ "normalized": false,
176
+ "special": false
177
+ },
178
+ "248062": {
179
+ "content": "<|fim_suffix|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": false
185
+ },
186
+ "248063": {
187
+ "content": "<|fim_pad|>",
188
+ "single_word": false,
189
+ "lstrip": false,
190
+ "rstrip": false,
191
+ "normalized": false,
192
+ "special": false
193
+ },
194
+ "248064": {
195
+ "content": "<|repo_name|>",
196
+ "single_word": false,
197
+ "lstrip": false,
198
+ "rstrip": false,
199
+ "normalized": false,
200
+ "special": false
201
+ },
202
+ "248065": {
203
+ "content": "<|file_sep|>",
204
+ "single_word": false,
205
+ "lstrip": false,
206
+ "rstrip": false,
207
+ "normalized": false,
208
+ "special": false
209
+ },
210
+ "248066": {
211
+ "content": "<tool_response>",
212
+ "single_word": false,
213
+ "lstrip": false,
214
+ "rstrip": false,
215
+ "normalized": false,
216
+ "special": false
217
+ },
218
+ "248067": {
219
+ "content": "</tool_response>",
220
+ "single_word": false,
221
+ "lstrip": false,
222
+ "rstrip": false,
223
+ "normalized": false,
224
+ "special": false
225
+ },
226
+ "248068": {
227
+ "content": "<think>",
228
+ "single_word": false,
229
+ "lstrip": false,
230
+ "rstrip": false,
231
+ "normalized": false,
232
+ "special": false
233
+ },
234
+ "248069": {
235
+ "content": "</think>",
236
+ "single_word": false,
237
+ "lstrip": false,
238
+ "rstrip": false,
239
+ "normalized": false,
240
+ "special": false
241
+ },
242
+ "248070": {
243
+ "content": "<|audio_start|>",
244
+ "single_word": false,
245
+ "lstrip": false,
246
+ "rstrip": false,
247
+ "normalized": false,
248
+ "special": true
249
+ },
250
+ "248071": {
251
+ "content": "<|audio_end|>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ "248072": {
259
+ "content": "<tts_pad>",
260
+ "single_word": false,
261
+ "lstrip": false,
262
+ "rstrip": false,
263
+ "normalized": false,
264
+ "special": true
265
+ },
266
+ "248073": {
267
+ "content": "<tts_text_bos>",
268
+ "single_word": false,
269
+ "lstrip": false,
270
+ "rstrip": false,
271
+ "normalized": false,
272
+ "special": true
273
+ },
274
+ "248074": {
275
+ "content": "<tts_text_eod>",
276
+ "single_word": false,
277
+ "lstrip": false,
278
+ "rstrip": false,
279
+ "normalized": false,
280
+ "special": true
281
+ },
282
+ "248075": {
283
+ "content": "<tts_text_bos_single>",
284
+ "single_word": false,
285
+ "lstrip": false,
286
+ "rstrip": false,
287
+ "normalized": false,
288
+ "special": true
289
+ },
290
+ "248076": {
291
+ "content": "<|audio_pad|>",
292
+ "single_word": false,
293
+ "lstrip": false,
294
+ "rstrip": false,
295
+ "normalized": false,
296
+ "special": true
297
+ }
298
+ },
299
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %} {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
300
+ }