Hugging Face's logo

fc91
/
CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_7.7

Transformers
Safetensors
Generated from Trainer
unsloth
trl
grpo
Model card Files
xet
 Community
fc91 commited on
Commit
78c496e
·
verified ·
1 Parent(s): c0bab1c

Training in progress, step 360

Browse files
Files changed (4) hide show
  1. README.md +2 -2
  2. adapter_config.json +4 -4
  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_7.7
5
  tags:
6
  - generated_from_trainer
7
- - unsloth
8
- - trl
9
  - grpo
 
 
10
  licence: license
11
  ---
12
 
 
4
  model_name: CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_7.7
5
  tags:
6
  - generated_from_trainer
 
 
7
  - grpo
8
+ - trl
9
+ - unsloth
10
  licence: license
11
  ---
12
 
adapter_config.json CHANGED
@@ -34,12 +34,12 @@
34
  "revision": null,
35
  "target_modules": [
36
  "q_proj",
37
- "v_proj",
38
- "o_proj",
39
- "k_proj",
40
  "gate_proj",
41
  "up_proj",
42
- "down_proj"
 
 
 
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
34
  "revision": null,
35
  "target_modules": [
36
  "q_proj",
 
 
 
37
  "gate_proj",
38
  "up_proj",
39
+ "o_proj",
40
+ "down_proj",
41
+ "v_proj",
42
+ "k_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4486f35279323679530cf73f57d30330d896d78adba3db63862bf00fd96a3426
3
  size 194563400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3519e1d5e16bc79c17588af870220cc743a5f42931482fcac320dd01536a25b
3
  size 194563400
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d74d97682b3ca368fa0bde4ba1402d648e13cfc5ff1db4d0557cbc83e9f88e6
3
  size 7185
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d254135edc9d765d2c392cd8d5fbc109924996685adeb53eb52066ef9facb86
3
  size 7185