aacudad commited on
Commit
166474a
·
verified ·
1 Parent(s): cefca85

Release LLaVA-OneVision-7B AnomalyThink checkpoint: weights, processor, config with an explicit text_config.rope_theta for transformers 4.x, and model card

Browse files
.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 +1,212 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: llava-hf/llava-onevision-qwen2-7b-si-hf
4
+ datasets:
5
+ - aacudad/AnomalyThink
6
+ library_name: transformers
7
+ pipeline_tag: image-text-to-text
8
+ tags:
9
+ - anomaly-detection
10
+ - industrial-anomaly-detection
11
+ - vision-language-model
12
+ - reasoning
13
+ - llava_onevision
14
+ ---
15
+
16
+ # AnomalyThink-LLaVA-OneVision-7B-KCR
17
+
18
+ The strongest LLaVA-OneVision model in this family. Trained with SFT only, on a
19
+ self-distilled corpus that the model family generated itself.
20
+
21
+ A **LLaVA-OneVision-7B-SI** model fine-tuned for **explainable industrial anomaly
22
+ detection (IAD)**. Given one product image it writes a reasoning trace in `<think>`,
23
+ then a defect `<location>` and `<type>` when it sees a defect, and finally a binary
24
+ `<answer>`. Research artefact from the MSc thesis *Reasoning-Enhanced Vision-Language
25
+ Models for Explainable Industrial Anomaly Detection* (TU Delft, 2026).
26
+
27
+ This is the cross-architecture replication of the thesis pipeline. The backbone is the
28
+ same one IAD-R1 uses, so the comparison is on IAD-R1's own ground.
29
+
30
+ ## Results
31
+
32
+ Metric is **balanced accuracy**, `(TPR + TNR) / 2`, in percent.
33
+
34
+ | Benchmark | Balanced accuracy |
35
+ |---|---|
36
+ | MMAD DS-MVTec (1,670 images) | **88.45** |
37
+ | MMAD VisA (2,141 images) | **74.25** |
38
+
39
+ Reference rows measured on the exact same harness:
40
+
41
+ | Model | DS-MVTec | VisA |
42
+ |---|---|---|
43
+ | LLaVA-OneVision-7B-SI base | 75.66 | 53.80 |
44
+ | IAD-R1 released checkpoint | 81.92 | 71.34 |
45
+ | AnomalyThink LLaVA SFT (6K Gemini traces) | 85.91 | 68.26 |
46
+ | AnomalyThink LLaVA SFT then GRPO | 87.66 | 72.58 |
47
+ | **This model (KCR, SFT only)** | **88.45** | **74.25** |
48
+
49
+ **Evaluation protocol.** One shared harness for every row above. The DS-MVTec and VisA
50
+ subsets of MMAD, single image per prompt, the same instruction the model was trained on,
51
+ greedy decoding at temperature 0, at most 1024 new tokens, images capped at 262,144
52
+ pixels. Answers are parsed from the `<answer>` tag. Generation ran through vLLM 0.10.2,
53
+ which agreed with the plain transformers generate path on 99 percent of a probe set.
54
+ Nothing here is a re-scored or best-of-N number.
55
+
56
+ ## Contamination note, please read this before you compare DS-MVTec numbers
57
+
58
+ The public LLaVA-OneVision training mixture (`lmms-lab/LLaVA-OneVision-Data`, config
59
+ `vision_flan(filtered)`) contains 426 rows whose id matches `%MVTecAD%`. The base model
60
+ has therefore seen MVTec-AD material during its own instruction tuning. **Every DS-MVTec
61
+ number for any LLaVA-OneVision derived model carries that caveat, including the 88.45
62
+ above, and including the IAD-R1 row.** We do not know how much of the gap is real
63
+ capability and how much is recall.
64
+
65
+ VisA is not affected. The same query over the mixture returns 0 rows for VisA. So the
66
+ **74.25 on VisA is the clean number** and it is the one to trust for a cross-model
67
+ comparison.
68
+
69
+ ## Training
70
+
71
+ * **Base model**: [`llava-hf/llava-onevision-qwen2-7b-si-hf`](https://huggingface.co/llava-hf/llava-onevision-qwen2-7b-si-hf).
72
+ * **Corpus**: [`llava_kcr/sft_llava_C_train.json`](https://huggingface.co/datasets/aacudad/AnomalyThink/tree/main/llava_kcr),
73
+ 6,000 traces, balanced 50/50 over normal and anomalous parts, on Real-IAD images.
74
+ * **Recipe**: supervised fine-tuning only. No reinforcement learning stage. The SigLIP
75
+ vision tower is frozen, the multimodal projector and the language model are trained.
76
+ Learning rate 1e-5, cosine schedule, warmup ratio 0.03, weight decay 0.1, effective
77
+ batch size 32, context cutoff 8,192 tokens, bf16, 4 epochs.
78
+ * **Epoch**: this is **epoch 4 of 4** (step 748), the best of the four saved epochs.
79
+ The full epoch curve on DS-MVTec / VisA was 85.29 / 72.32, 85.60 / 70.10,
80
+ 86.45 / 73.56, and 88.45 / 74.25.
81
+
82
+ ## The KCR corpus here is LLaVA native, not borrowed from Qwen
83
+
84
+ This matters, so it is stated plainly. KCR stands for keep, correct, rewrite. The corpus
85
+ for this model was built from **LLaVA-OneVision's own rollouts**, not from the Qwen
86
+ rollouts used elsewhere in the thesis. The loop was:
87
+
88
+ 1. Sample 10,236 rollouts on Real-IAD training images from the sibling
89
+ [SFT then GRPO checkpoint](https://huggingface.co/aacudad/AnomalyThink-LLaVA-OneVision-7B-SFT-GRPO),
90
+ k = 8 per image at temperature 0.7.
91
+ 2. Bucket each trace by whether its verdict matched the label, into keep, needs
92
+ correction, or needs rewrite.
93
+ 3. Score every trace with a Gemini 2.5-Flash faithfulness judge, and demote traces that
94
+ were right for the wrong reason.
95
+ 4. Have Gemini 2.5-Flash correct or rewrite the traces that failed, then sample a
96
+ balanced 6,000.
97
+
98
+ The intermediate arms are published next to the final one:
99
+ [`llava_kcr/`](https://huggingface.co/datasets/aacudad/AnomalyThink/tree/main/llava_kcr)
100
+ holds `sft_llava_A_kept.json` (keep only), `sft_llava_B_kept_corrected.json` (keep plus
101
+ corrected), and `sft_llava_C_train.json` (the corpus this model was trained on).
102
+
103
+ Because the rollouts come from this backbone, the corpus is on-policy for
104
+ LLaVA-OneVision. Reusing the Qwen KCR corpus on this backbone gives a weaker model.
105
+
106
+ ## Tested transformers versions
107
+
108
+ The weights and configs in this repo were written by **transformers 4.51.3**. Loading,
109
+ the processor, and the full evaluation were verified under **transformers 4.57.1**, both
110
+ through the plain HF generate path and through **vLLM 0.10.2**.
111
+
112
+ One warning for anyone rebuilding this pipeline. Checkpoints saved by **transformers
113
+ 5.0** write the rope settings under `text_config.rope_parameters`. Transformers 4.x does
114
+ not read that key and silently falls back to `rope_theta = 10000`, which is 100 times
115
+ too small. The model then stays fluent but goes blind and answers "no" to nearly
116
+ everything, which looks like a collapsed run rather than a loading bug. This repo ships
117
+ a plain `text_config.rope_theta = 1000000.0` next to the 5.0 style block, so it loads
118
+ correctly on both major versions.
119
+
120
+ ## Usage
121
+
122
+ ```python
123
+ import torch
124
+ from PIL import Image
125
+ from transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration
126
+
127
+ repo = "aacudad/AnomalyThink-LLaVA-OneVision-7B-KCR"
128
+ model = LlavaOnevisionForConditionalGeneration.from_pretrained(
129
+ repo, torch_dtype=torch.bfloat16, device_map="auto")
130
+ processor = AutoProcessor.from_pretrained(repo)
131
+
132
+ image = Image.open("part.png").convert("RGB")
133
+ product = "tile" # the product category, it goes into the prompt
134
+
135
+ question = (
136
+ f"Analyze the provided image of the {product}. "
137
+ "Determine if there are any anomalies present. "
138
+ "If an anomaly is detected, specify its type and location, "
139
+ "and provide a detailed reasoning for your conclusion."
140
+ )
141
+ messages = [{"role": "user", "content": [
142
+ {"type": "image"},
143
+ {"type": "text", "text": question},
144
+ ]}]
145
+ prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
146
+ inputs = processor(images=image, text=prompt, return_tensors="pt").to(
147
+ model.device, torch.bfloat16)
148
+
149
+ out = model.generate(**inputs, max_new_tokens=1024, do_sample=False)
150
+ print(processor.decode(out[0][inputs["input_ids"].shape[1]:],
151
+ skip_special_tokens=True))
152
+ ```
153
+
154
+ Use this exact instruction. The model was trained on it and it degrades on a different
155
+ phrasing.
156
+
157
+ Expected output on a defective part:
158
+
159
+ ```
160
+ <think>
161
+ I am inspecting a tile with a speckled, grayish-white surface. ... In the center of the
162
+ tile, I detect a triangular, translucent plastic fragment. ...
163
+ </think>
164
+ <location>center</location>
165
+ <type>Contamination</type>
166
+ <answer>Yes</answer>
167
+ ```
168
+
169
+ On a normal part the model emits `<think>` and then `<answer>No</answer>`, with no
170
+ `<location>` or `<type>` tag.
171
+
172
+ ## Intended use and limitations
173
+
174
+ Research on explainable industrial anomaly detection. This is a thesis artefact, not a
175
+ production inspection system.
176
+
177
+ Known limitations:
178
+
179
+ * The DS-MVTec contamination caveat above.
180
+ * The model can write a confident and well argued trace for a defect that is not there.
181
+ * The `<type>` label is coarse and the model over-uses "missing parts" for any loss of
182
+ material, including chips and gouges.
183
+ * It was trained on Real-IAD style single-object images on plain backgrounds. Cluttered
184
+ scenes, multiple parts per image, and very different lighting are out of distribution.
185
+ * Reasoning traces were distilled from a teacher model. A fluent trace is not proof that
186
+ the model looked at the right pixels.
187
+
188
+ ## Citation
189
+
190
+ ```bibtex
191
+ @mastersthesis{acudad2026anomalythink,
192
+ title = {Reasoning-Enhanced Vision-Language Models for Explainable Industrial Anomaly Detection},
193
+ author = {Acudad, Adnane},
194
+ school = {Delft University of Technology},
195
+ year = {2026}
196
+ }
197
+ ```
198
+
199
+ The thesis is deposited in the TU Delft education repository. The training data is at
200
+ [aacudad/AnomalyThink](https://huggingface.co/datasets/aacudad/AnomalyThink).
201
+
202
+ ## Related models
203
+
204
+ * [AnomalyThink-LLaVA-OneVision-7B-SFT](https://huggingface.co/aacudad/AnomalyThink-LLaVA-OneVision-7B-SFT)
205
+ * [AnomalyThink-LLaVA-OneVision-7B-SFT-GRPO](https://huggingface.co/aacudad/AnomalyThink-LLaVA-OneVision-7B-SFT-GRPO)
206
+ * [AnomalyThink-Qwen2.5-VL-7B-KCR](https://huggingface.co/aacudad/AnomalyThink-Qwen2.5-VL-7B-KCR), the same pipeline on the Qwen2.5-VL backbone
207
+
208
+ ## License
209
+
210
+ Apache-2.0, inherited from the LLaVA-OneVision-7B-SI base. Trained on Real-IAD images,
211
+ which are not redistributed here, so cite Real-IAD separately. Reasoning traces were
212
+ distilled from Gemini 2.5-Flash.
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<image>": 151646,
3
+ "<video>": 151647,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644
7
+ }
chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + ' '}}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>' }}{% endfor %}{# Render all video then #}{% for content in message['content'] | selectattr('type', 'equalto', 'video') %}{{ '<video>' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ '
2
+ ' + content['text'] }}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ '
3
+ ' + content['text'] }}{% endgeneration %}{% endfor %}{% endif %}{{'<|im_end|>'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + ' '}}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>' }}{% endfor %}{# Render all video then #}{% for content in message['content'] | selectattr('type', 'equalto', 'video') %}{{ '<video>' }}{% endfor %}{# Render all text next #}{% if message['role'] != 'assistant' %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ '\n' + content['text'] }}{% endfor %}{% else %}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{% generation %}{{ '\n' + content['text'] }}{% endgeneration %}{% endfor %}{% endif %}{{'<|im_end|>'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaOnevisionForConditionalGeneration"
4
+ ],
5
+ "hidden_size": 3584,
6
+ "ignore_index": -100,
7
+ "image_grid_pinpoints": [
8
+ [
9
+ 384,
10
+ 384
11
+ ],
12
+ [
13
+ 384,
14
+ 768
15
+ ],
16
+ [
17
+ 384,
18
+ 1152
19
+ ],
20
+ [
21
+ 384,
22
+ 1536
23
+ ],
24
+ [
25
+ 384,
26
+ 1920
27
+ ],
28
+ [
29
+ 384,
30
+ 2304
31
+ ],
32
+ [
33
+ 768,
34
+ 384
35
+ ],
36
+ [
37
+ 768,
38
+ 768
39
+ ],
40
+ [
41
+ 768,
42
+ 1152
43
+ ],
44
+ [
45
+ 768,
46
+ 1536
47
+ ],
48
+ [
49
+ 768,
50
+ 1920
51
+ ],
52
+ [
53
+ 768,
54
+ 2304
55
+ ],
56
+ [
57
+ 1152,
58
+ 384
59
+ ],
60
+ [
61
+ 1152,
62
+ 768
63
+ ],
64
+ [
65
+ 1152,
66
+ 1152
67
+ ],
68
+ [
69
+ 1152,
70
+ 1536
71
+ ],
72
+ [
73
+ 1152,
74
+ 1920
75
+ ],
76
+ [
77
+ 1152,
78
+ 2304
79
+ ],
80
+ [
81
+ 1536,
82
+ 384
83
+ ],
84
+ [
85
+ 1536,
86
+ 768
87
+ ],
88
+ [
89
+ 1536,
90
+ 1152
91
+ ],
92
+ [
93
+ 1536,
94
+ 1536
95
+ ],
96
+ [
97
+ 1536,
98
+ 1920
99
+ ],
100
+ [
101
+ 1536,
102
+ 2304
103
+ ],
104
+ [
105
+ 1920,
106
+ 384
107
+ ],
108
+ [
109
+ 1920,
110
+ 768
111
+ ],
112
+ [
113
+ 1920,
114
+ 1152
115
+ ],
116
+ [
117
+ 1920,
118
+ 1536
119
+ ],
120
+ [
121
+ 1920,
122
+ 1920
123
+ ],
124
+ [
125
+ 1920,
126
+ 2304
127
+ ],
128
+ [
129
+ 2304,
130
+ 384
131
+ ],
132
+ [
133
+ 2304,
134
+ 768
135
+ ],
136
+ [
137
+ 2304,
138
+ 1152
139
+ ],
140
+ [
141
+ 2304,
142
+ 1536
143
+ ],
144
+ [
145
+ 2304,
146
+ 1920
147
+ ],
148
+ [
149
+ 2304,
150
+ 2304
151
+ ]
152
+ ],
153
+ "image_token_index": 151646,
154
+ "model_type": "llava_onevision",
155
+ "multimodal_projector_bias": true,
156
+ "projector_hidden_act": "gelu",
157
+ "text_config": {
158
+ "_name_or_path": "Qwen/Qwen2-7B-Instruct",
159
+ "architectures": [
160
+ "Qwen2ForCausalLM"
161
+ ],
162
+ "attention_dropout": 0.0,
163
+ "bos_token_id": 151643,
164
+ "eos_token_id": 151645,
165
+ "hidden_act": "silu",
166
+ "hidden_size": 3584,
167
+ "initializer_range": 0.02,
168
+ "intermediate_size": 18944,
169
+ "max_position_embeddings": 32768,
170
+ "max_window_layers": 28,
171
+ "model_type": "qwen2",
172
+ "num_attention_heads": 28,
173
+ "num_hidden_layers": 28,
174
+ "num_key_value_heads": 4,
175
+ "rms_norm_eps": 1e-06,
176
+ "rope_scaling": null,
177
+ "rope_theta": 1000000.0,
178
+ "sliding_window": 4096,
179
+ "torch_dtype": "float32",
180
+ "use_cache": true,
181
+ "use_sliding_window": false,
182
+ "vocab_size": 152128
183
+ },
184
+ "tie_word_embeddings": false,
185
+ "torch_dtype": "bfloat16",
186
+ "transformers_version": "4.51.3",
187
+ "use_cache": false,
188
+ "use_image_newline_parameter": true,
189
+ "video_token_index": 151647,
190
+ "vision_aspect_ratio": "anyres_max_9",
191
+ "vision_config": {
192
+ "attention_dropout": 0.0,
193
+ "hidden_act": "gelu_pytorch_tanh",
194
+ "hidden_size": 1152,
195
+ "image_size": 384,
196
+ "intermediate_size": 4304,
197
+ "layer_norm_eps": 1e-06,
198
+ "model_type": "siglip_vision_model",
199
+ "num_attention_heads": 16,
200
+ "num_channels": 3,
201
+ "num_hidden_layers": 26,
202
+ "patch_size": 14,
203
+ "torch_dtype": "float32",
204
+ "vision_use_head": false
205
+ },
206
+ "vision_feature_layer": -1,
207
+ "vision_feature_select_strategy": "full"
208
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.51.3"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1713a49d8273da3a5f8a2b0bd161908fe49a6c78f01010feef2caa32e7b96535
3
+ size 4911200872
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a11c89685165e2c1a34baf3c24619d94eaf5c04e42ee62378cca5006be1847b4
3
+ size 4991497792
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660a3af1c64fbe5c332cab8f2b01543420fc50d59b33e9b8cb6de1b01c219323
3
+ size 4932752872
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e22e8c840c0a8ba7a33d780bcc247fecec5f7ac608f5fa6c50daa7123356975
3
+ size 1226266248
model.safetensors.index.json ADDED
@@ -0,0 +1,772 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16061615168
4
+ },
5
+ "weight_map": {
6
+ "image_newline": "model-00001-of-00004.safetensors",
7
+ "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
21
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
27
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
28
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
29
+ "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
30
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
31
+ "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
32
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
33
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "language_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
+ "language_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
90
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
91
+ "language_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
92
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
93
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
95
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
96
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
97
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
98
+ "language_model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
99
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
100
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
101
+ "language_model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
102
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
103
+ "language_model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
104
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
106
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
107
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
108
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
109
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
110
+ "language_model.model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
111
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
112
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
113
+ "language_model.model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
114
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "language_model.model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
116
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
118
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
119
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
120
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
121
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
122
+ "language_model.model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
123
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
124
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
125
+ "language_model.model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
126
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
127
+ "language_model.model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
128
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
129
+ "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
131
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
132
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
133
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
134
+ "language_model.model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
135
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
140
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
141
+ "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
147
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
148
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
149
+ "language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
150
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
154
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
155
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
156
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
157
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
158
+ "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
159
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
160
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
161
+ "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
162
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
163
+ "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
164
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
165
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
168
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
169
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
170
+ "language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
171
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
172
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
173
+ "language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
174
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
183
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
184
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
185
+ "language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
186
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
188
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
195
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
+ "language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
198
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
199
+ "language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
200
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
201
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
203
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
204
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
205
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "language_model.model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
207
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
208
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
209
+ "language_model.model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
210
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
211
+ "language_model.model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
212
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
+ "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "language_model.model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
219
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
220
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
221
+ "language_model.model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
222
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
223
+ "language_model.model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
224
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
225
+ "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "language_model.model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
231
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
+ "language_model.model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
234
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
235
+ "language_model.model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
236
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
237
+ "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
238
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
239
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
240
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
241
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
242
+ "language_model.model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
243
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
244
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
245
+ "language_model.model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
246
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
247
+ "language_model.model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
248
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
250
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
251
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
252
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
253
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
254
+ "language_model.model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
255
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
256
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
257
+ "language_model.model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
258
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
259
+ "language_model.model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
260
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
261
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
267
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
270
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
271
+ "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
272
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
273
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
275
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
276
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
277
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
278
+ "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
279
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
280
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
281
+ "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
282
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
283
+ "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
284
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
286
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
287
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
289
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
290
+ "language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
291
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
292
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
293
+ "language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
294
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
295
+ "language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
296
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
297
+ "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
298
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
299
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
300
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
301
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
302
+ "language_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
303
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
304
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
305
+ "language_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
306
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
307
+ "language_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
308
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
309
+ "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
310
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
311
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
312
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
313
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
314
+ "language_model.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
315
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
316
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
317
+ "language_model.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
318
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
319
+ "language_model.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
320
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
321
+ "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
+ "language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
327
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
328
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
329
+ "language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
330
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
331
+ "language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
332
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
333
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
334
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
335
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
336
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
337
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
338
+ "language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
339
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
340
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
341
+ "language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
342
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
343
+ "language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
344
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
345
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
346
+ "multi_modal_projector.linear_1.bias": "model-00001-of-00004.safetensors",
347
+ "multi_modal_projector.linear_1.weight": "model-00001-of-00004.safetensors",
348
+ "multi_modal_projector.linear_2.bias": "model-00001-of-00004.safetensors",
349
+ "multi_modal_projector.linear_2.weight": "model-00001-of-00004.safetensors",
350
+ "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
351
+ "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
352
+ "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
353
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
354
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
355
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
356
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
357
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
358
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
359
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
360
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
361
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
362
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
363
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
364
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
365
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
366
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
367
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
368
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
369
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
370
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
371
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
372
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
373
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
374
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
375
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
376
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
377
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
378
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
379
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
380
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
381
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
382
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
383
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
384
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
385
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
386
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
387
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
388
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
389
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
390
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
391
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
392
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
393
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
394
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
395
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
396
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
397
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
398
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
399
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
400
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
401
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
402
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
403
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
404
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
405
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
406
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
407
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
408
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
409
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
410
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
411
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
412
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
413
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
414
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
415
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
416
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
417
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
418
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
419
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
420
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
421
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
422
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
423
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
424
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
425
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
426
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
427
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
428
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
429
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
430
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
431
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
432
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
433
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
434
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
435
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
436
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
437
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
438
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
439
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
440
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
441
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
442
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
443
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
444
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
445
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
446
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
447
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
448
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
449
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
450
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
451
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
452
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
453
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
454
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
455
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
456
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
457
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
458
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
459
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
460
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
461
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
462
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
463
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
464
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
465
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
466
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
467
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
468
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
469
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
470
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
471
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
472
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
473
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
474
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
475
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
476
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
477
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
478
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
479
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
480
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
481
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
482
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
483
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
484
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
485
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
486
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
487
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
488
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
489
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
490
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
491
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
492
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
493
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
494
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
495
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
496
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
497
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
498
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
499
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
500
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
501
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
502
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
503
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
504
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
505
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
506
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
507
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
508
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
509
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
510
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
511
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
512
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
513
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
514
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
515
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
516
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
517
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
518
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
519
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
520
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
521
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
522
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
523
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
524
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
525
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
526
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
527
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
528
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
529
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
530
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
531
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
532
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
533
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
534
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
535
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
536
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
537
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
538
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
539
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
540
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
541
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
542
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
543
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
544
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
545
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
546
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
547
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
548
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
549
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
550
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
551
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
552
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
553
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
554
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
555
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
556
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
557
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
558
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
559
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
560
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
561
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
562
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
563
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
564
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
565
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
566
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
567
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
568
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
569
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
570
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
571
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
572
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
573
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
574
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
575
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
576
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
577
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
578
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
579
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
580
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
581
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
582
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
583
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
584
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
585
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
586
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
587
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
588
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
589
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
590
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
591
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
592
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
593
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
594
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
595
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
596
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
597
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
598
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
599
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
600
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
601
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
602
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
603
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
604
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
605
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
606
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
607
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
608
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
609
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
610
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
611
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
612
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
613
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
614
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
615
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
616
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
617
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
618
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
619
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
620
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
621
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
622
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
623
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
624
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
625
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00004.safetensors",
626
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00004.safetensors",
627
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00004.safetensors",
628
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00004.safetensors",
629
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
630
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
631
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
632
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
633
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
634
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
635
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
636
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
637
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
638
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
639
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
640
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
641
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00004.safetensors",
642
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00004.safetensors",
643
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00004.safetensors",
644
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00004.safetensors",
645
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
646
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
647
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
648
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
649
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
650
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
651
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
652
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
653
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
654
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
655
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
656
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
657
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
658
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
659
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
660
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
661
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
662
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
663
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
664
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
665
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
666
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
667
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
668
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
669
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
670
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
671
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
672
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
673
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
674
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
675
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
676
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
677
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
678
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
679
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
680
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
681
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
682
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
683
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
684
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
685
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
686
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
687
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
688
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
689
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
690
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
691
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
692
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
693
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
694
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
695
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
696
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
697
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
698
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
699
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
700
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
701
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
702
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
703
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
704
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
705
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
706
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
707
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
708
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
709
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
710
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
711
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
712
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
713
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
714
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
715
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
716
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
717
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
718
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
719
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
720
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
721
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
722
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
723
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
724
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
725
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
726
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
727
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
728
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
729
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
730
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
731
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
732
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
733
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
734
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
735
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
736
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
737
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
738
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
739
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
740
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
741
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
742
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
743
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
744
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
745
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
746
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
747
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
748
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
749
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
750
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
751
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
752
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
753
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
754
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
755
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
756
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
757
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
758
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
759
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
760
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
761
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
762
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
763
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
764
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
765
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
766
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
767
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
768
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
769
+ "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
770
+ "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors"
771
+ }
772
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_grid_pinpoints": [
8
+ [
9
+ 384,
10
+ 384
11
+ ],
12
+ [
13
+ 384,
14
+ 768
15
+ ],
16
+ [
17
+ 384,
18
+ 1152
19
+ ],
20
+ [
21
+ 384,
22
+ 1536
23
+ ],
24
+ [
25
+ 384,
26
+ 1920
27
+ ],
28
+ [
29
+ 384,
30
+ 2304
31
+ ],
32
+ [
33
+ 768,
34
+ 384
35
+ ],
36
+ [
37
+ 768,
38
+ 768
39
+ ],
40
+ [
41
+ 768,
42
+ 1152
43
+ ],
44
+ [
45
+ 768,
46
+ 1536
47
+ ],
48
+ [
49
+ 768,
50
+ 1920
51
+ ],
52
+ [
53
+ 768,
54
+ 2304
55
+ ],
56
+ [
57
+ 1152,
58
+ 384
59
+ ],
60
+ [
61
+ 1152,
62
+ 768
63
+ ],
64
+ [
65
+ 1152,
66
+ 1152
67
+ ],
68
+ [
69
+ 1152,
70
+ 1536
71
+ ],
72
+ [
73
+ 1152,
74
+ 1920
75
+ ],
76
+ [
77
+ 1152,
78
+ 2304
79
+ ],
80
+ [
81
+ 1536,
82
+ 384
83
+ ],
84
+ [
85
+ 1536,
86
+ 768
87
+ ],
88
+ [
89
+ 1536,
90
+ 1152
91
+ ],
92
+ [
93
+ 1536,
94
+ 1536
95
+ ],
96
+ [
97
+ 1536,
98
+ 1920
99
+ ],
100
+ [
101
+ 1536,
102
+ 2304
103
+ ],
104
+ [
105
+ 1920,
106
+ 384
107
+ ],
108
+ [
109
+ 1920,
110
+ 768
111
+ ],
112
+ [
113
+ 1920,
114
+ 1152
115
+ ],
116
+ [
117
+ 1920,
118
+ 1536
119
+ ],
120
+ [
121
+ 1920,
122
+ 1920
123
+ ],
124
+ [
125
+ 1920,
126
+ 2304
127
+ ],
128
+ [
129
+ 2304,
130
+ 384
131
+ ],
132
+ [
133
+ 2304,
134
+ 768
135
+ ],
136
+ [
137
+ 2304,
138
+ 1152
139
+ ],
140
+ [
141
+ 2304,
142
+ 1536
143
+ ],
144
+ [
145
+ 2304,
146
+ 1920
147
+ ],
148
+ [
149
+ 2304,
150
+ 2304
151
+ ]
152
+ ],
153
+ "image_mean": [
154
+ 0.5,
155
+ 0.5,
156
+ 0.5
157
+ ],
158
+ "image_processor_type": "LlavaOnevisionImageProcessor",
159
+ "image_std": [
160
+ 0.5,
161
+ 0.5,
162
+ 0.5
163
+ ],
164
+ "processor_class": "LlavaOnevisionProcessor",
165
+ "resample": 3,
166
+ "rescale_factor": 0.00392156862745098,
167
+ "size": {
168
+ "height": 384,
169
+ "width": 384
170
+ }
171
+ }
processor_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_token": "<image>",
3
+ "num_image_tokens": 729,
4
+ "processor_class": "LlavaOnevisionProcessor",
5
+ "video_token": "<video>",
6
+ "vision_feature_select_strategy": "full"
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09f1889210ae8f16539761f6a6d645641eb8e583d22c6f36c92d253e247887f
3
+ size 11418634
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<image>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<video>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "additional_special_tokens": [
46
+ "<|im_start|>",
47
+ "<|im_end|>"
48
+ ],
49
+ "bos_token": null,
50
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
51
+ "clean_up_tokenization_spaces": false,
52
+ "eos_token": "<|im_end|>",
53
+ "errors": "replace",
54
+ "extra_special_tokens": {},
55
+ "max_length": null,
56
+ "model_max_length": 8192,
57
+ "pad_to_multiple_of": null,
58
+ "pad_token": "<|endoftext|>",
59
+ "pad_token_type_id": 0,
60
+ "padding_side": "right",
61
+ "processor_class": "LlavaOnevisionProcessor",
62
+ "split_special_tokens": false,
63
+ "tokenizer_class": "Qwen2Tokenizer",
64
+ "unk_token": null
65
+ }
video_processor/preprocessor_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_pad": 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": "LlavaOnevisionVideoProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "processor_class": "LlavaOnevisionProcessor",
19
+ "resample": 3,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 384,
23
+ "width": 384
24
+ }
25
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff