Hugging Face's logo

longlian
/
Qwen2-0.5B-GRPO-peft-demo

Transformers
Safetensors
Generated from Trainer
trl
grpo
Inference Endpoints
Model card Files Community
longlian commited on
Commit
5d99cbd
·
verified ·
1 Parent(s): 469a29f

Training in progress, step 10

Browse files
Files changed (3) hide show
  1. adapter_config.json +2 -2
  2. adapter_model.safetensors +1 -1
  3. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -23,8 +23,8 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "q_proj",
27
- "v_proj"
28
  ],
29
  "task_type": "CAUSAL_LM",
30
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
+ "v_proj",
27
+ "q_proj"
28
  ],
29
  "task_type": "CAUSAL_LM",
30
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099ef4e38bdee83c5cf98a5815372950a2ff60c65b70ba57e878bf53ed26afd
3
  size 2175168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eece4ba4e64ab341c818d1b9b7977c2642d11a215ceba49f95002cf4dafbed5
3
  size 2175168
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d18df471e8cfce4dcada967b02bff69e4e87a1e35d686eb5db38241fecf07bf8
3
  size 5752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f0cc875105161e33ce4c3eb0e0402fbf79c5d8015065cd6ab173e88ac25d46c
3
  size 5752