Hugging Face's logo

knowledgator
/
retrico-lm-9b-sft-dev

Text Generation
PEFT
Safetensors
Transformers
qwen3_5
image-text-to-text
grpo
lora
trl
conversational
Model card Files
xet
 Community
alexandrlukashov commited on
Commit
a7ca348
·
verified ·
1 Parent(s): 6d03523

checkpoint step 10

Browse files
Files changed (11) hide show
  1. README.md +4 -2
  2. adapter_config.json +7 -7
  3. adapter_model.safetensors +2 -2
  4. chat_template.jinja +3 -3
  5. optimizer.pt +2 -2
  6. rng_state.pth +1 -1
  7. scheduler.pt +1 -1
  8. tokenizer.json +2 -2
  9. tokenizer_config.json +2 -2
  10. trainer_state.json +2 -2
  11. training_args.bin +2 -2
README.md CHANGED
@@ -1,11 +1,13 @@
1
  ---
2
- base_model: knowledgator/retrico-lm-9b-merged
3
  library_name: peft
4
  pipeline_tag: text-generation
5
  tags:
6
- - base_model:adapter:knowledgator/retrico-lm-9b-merged
 
7
  - lora
8
  - transformers
 
9
  ---
10
 
11
  # Model Card for Model ID
 
1
  ---
2
+ base_model: knowledgator/retrico-lm-4b
3
  library_name: peft
4
  pipeline_tag: text-generation
5
  tags:
6
+ - base_model:adapter:knowledgator/retrico-lm-4b
7
+ - grpo
8
  - lora
9
  - transformers
10
+ - trl
11
  ---
12
 
13
  # Model Card for Model ID
adapter_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "alpha_pattern": {},
4
  "arrow_config": null,
5
  "auto_mapping": null,
6
- "base_model_name_or_path": "knowledgator/retrico-lm-9b-merged",
7
  "bias": "none",
8
  "corda_config": null,
9
  "ensure_weight_tying": false,
@@ -16,7 +16,7 @@
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
- "lora_alpha": 128,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
@@ -26,17 +26,17 @@
26
  "peft_type": "LORA",
27
  "peft_version": "0.19.1",
28
  "qalora_group_size": 16,
29
- "r": 64,
30
  "rank_pattern": {},
31
  "revision": null,
32
  "target_modules": [
33
- "gate_proj",
34
  "q_proj",
35
- "down_proj",
36
  "v_proj",
37
- "o_proj",
38
  "k_proj",
39
- "up_proj"
 
 
 
40
  ],
41
  "target_parameters": null,
42
  "task_type": "CAUSAL_LM",
 
3
  "alpha_pattern": {},
4
  "arrow_config": null,
5
  "auto_mapping": null,
6
+ "base_model_name_or_path": "knowledgator/retrico-lm-4b",
7
  "bias": "none",
8
  "corda_config": null,
9
  "ensure_weight_tying": false,
 
16
  "layers_pattern": null,
17
  "layers_to_transform": null,
18
  "loftq_config": {},
19
+ "lora_alpha": 32,
20
  "lora_bias": false,
21
  "lora_dropout": 0.05,
22
  "lora_ga_config": null,
 
26
  "peft_type": "LORA",
27
  "peft_version": "0.19.1",
28
  "qalora_group_size": 16,
29
+ "r": 16,
30
  "rank_pattern": {},
31
  "revision": null,
32
  "target_modules": [
 
33
  "q_proj",
 
34
  "v_proj",
 
35
  "k_proj",
36
+ "o_proj",
37
+ "up_proj",
38
+ "down_proj",
39
+ "gate_proj"
40
  ],
41
  "target_parameters": null,
42
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2550592619631dbedfa7e49c4e70af87dae84ab91a61264a1c1d9fc64a7571b2
3
- size 465602056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65b4a8df99be1f7b3114fd32496b9523731ec44d90751d90ee20b8e1a4f4ea3d
3
+ size 84968408
chat_template.jinja CHANGED
@@ -146,9 +146,9 @@
146
  {%- endfor %}
147
  {%- if add_generation_prompt %}
148
  {{- '<|im_start|>assistant\n' }}
149
- {%- if enable_thinking is defined and enable_thinking is false %}
150
- {{- '<think>\n\n</think>\n\n' }}
151
- {%- else %}
152
  {{- '<think>\n' }}
 
 
153
  {%- endif %}
154
  {%- endif %}
 
146
  {%- endfor %}
147
  {%- if add_generation_prompt %}
148
  {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is true %}
 
 
150
  {{- '<think>\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n\n</think>\n\n' }}
153
  {%- endif %}
154
  {%- endif %}
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fa7b910fcc27c1f43e7cf5569db6ee16325c9ef7e052201d8aa5977b792e3ae
3
- size 931355339
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8109d5622156157f66b6a4b7813d875c0e0c243cf0d7b1b92ee9b6da41a5b213
3
+ size 170088587
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:336da8d7a76b4c4eaf8df0601ee2c874ef2a0132ab75c85b470003159489535a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a882ea3aecdaf3bc063734854e0dd50f45a53855818abcb7e6357f21ad6aa5f
3
  size 14645
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:623db7be34fc90f866356d6328be7b116e173bdd11eb466866533a57b15eb23c
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ee58a7d6ebf2b1a6995788ab8896acda606bcb6b483271329edfac9a998f41e
3
  size 1465
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
- size 19989325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
tokenizer_config.json CHANGED
@@ -9,7 +9,7 @@
9
  "eos_token": "<|im_end|>",
10
  "errors": "replace",
11
  "image_token": "<|image_pad|>",
12
- "is_local": true,
13
  "local_files_only": false,
14
  "model_max_length": 262144,
15
  "model_specific_special_tokens": {
@@ -24,7 +24,7 @@
24
  "pad_token": "<|endoftext|>",
25
  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
26
  "split_special_tokens": false,
27
- "tokenizer_class": "Qwen2Tokenizer",
28
  "unk_token": null,
29
  "video_token": "<|video_pad|>",
30
  "vision_bos_token": "<|vision_start|>",
 
9
  "eos_token": "<|im_end|>",
10
  "errors": "replace",
11
  "image_token": "<|image_pad|>",
12
+ "is_local": false,
13
  "local_files_only": false,
14
  "model_max_length": 262144,
15
  "model_specific_special_tokens": {
 
24
  "pad_token": "<|endoftext|>",
25
  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
26
  "split_special_tokens": false,
27
+ "tokenizer_class": "TokenizersBackend",
28
  "unk_token": null,
29
  "video_token": "<|video_pad|>",
30
  "vision_bos_token": "<|vision_start|>",
trainer_state.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41adbfc7f7cf2aa7de93ef893933aaa52aa1e177990a888469b0a9bd0cc9f681
3
- size 9622
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be73443c594248823d14b9997482ab713879147fc3e41f6ba15686b8e47592e0
3
+ size 11041
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bce5606f9baea607eeb3c667c1e28c7d753a628f85ee99cf3600d0eab4ac6735
3
- size 5137
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca3dc72e2c3a6ef3e9e5baf0882f615032e5094828e1aeb25df53a7e6c1c31f
3
+ size 7185