Hugging Face's logo

fc91
/
CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_7.2

Transformers
Safetensors
Generated from Trainer
trl
unsloth
grpo
Model card Files
xet
 Community
fc91 commited on
Commit
ca3534d
·
verified ·
1 Parent(s): 478b85c

Training in progress, step 430

Browse files
Files changed (4) hide show
  1. README.md +1 -1
  2. adapter_config.json +5 -5
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -4,9 +4,9 @@ library_name: transformers
4
  model_name: CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_7.2
5
  tags:
6
  - generated_from_trainer
7
- - grpo
8
  - trl
9
  - unsloth
 
10
  licence: license
11
  ---
12
 
 
4
  model_name: CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_7.2
5
  tags:
6
  - generated_from_trainer
 
7
  - trl
8
  - unsloth
9
+ - grpo
10
  licence: license
11
  ---
12
 
adapter_config.json CHANGED
@@ -29,13 +29,13 @@
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
32
- "o_proj",
33
- "v_proj",
34
  "down_proj",
35
- "up_proj",
 
36
  "k_proj",
37
- "gate_proj",
38
- "q_proj"
39
  ],
40
  "task_type": "CAUSAL_LM",
41
  "trainable_token_indices": null,
 
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
32
+ "gate_proj",
 
33
  "down_proj",
34
+ "v_proj",
35
+ "q_proj",
36
  "k_proj",
37
+ "up_proj",
38
+ "o_proj"
39
  ],
40
  "task_type": "CAUSAL_LM",
41
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50b7c0d6787dc8a7681ed1554a55cd43152432d7fa500102a2166a4eed1a5253
3
  size 194563400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3818ab5ce40279a67e457f3858a3128742951deae83bb945475d0bdcb6bfb5f2
3
  size 194563400
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47bd84f18ee38770ddeaf274bd989f5207ac3438b2a261ef86ed74af22e1ef30
3
  size 7121
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c7d900446237d1e2d3da3da30c75b8ea971aae913fa39be4480629862dc5a75
3
  size 7121