Hugging Face's logo

fangwu97
/
Qwen2.5-7B-Instruct-GRPO-test

Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
grpo
Model card Files
xet
Metrics Community
1
fangwu97 commited on
Commit
b2035dd
·
verified ·
1 Parent(s): 4b7917d

Model save

Browse files
Files changed (5) hide show
  1. README.md +2 -3
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. tokenizer.json +2 -2
  5. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,5 @@
1
  ---
2
  base_model: Qwen/Qwen2.5-7B-Instruct
3
- datasets: AI-MO/NuminaMath-TIR
4
  library_name: transformers
5
  model_name: Qwen2.5-7B-Instruct-GRPO-test
6
  tags:
@@ -12,7 +11,7 @@ licence: license
12
 
13
  # Model Card for Qwen2.5-7B-Instruct-GRPO-test
14
 
15
- This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the [AI-MO/NuminaMath-TIR](https://huggingface.co/datasets/AI-MO/NuminaMath-TIR) dataset.
16
  It has been trained using [TRL](https://github.com/huggingface/trl).
17
 
18
  ## Quick start
@@ -28,7 +27,7 @@ print(output["generated_text"])
28
 
29
  ## Training procedure
30
 
31
-
32
 
33
 
34
  This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
 
1
  ---
2
  base_model: Qwen/Qwen2.5-7B-Instruct
 
3
  library_name: transformers
4
  model_name: Qwen2.5-7B-Instruct-GRPO-test
5
  tags:
 
11
 
12
  # Model Card for Qwen2.5-7B-Instruct-GRPO-test
13
 
14
+ This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
15
  It has been trained using [TRL](https://github.com/huggingface/trl).
16
 
17
  ## Quick start
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/fangwu/grpo_train/runs/vph9apcv)
31
 
32
 
33
  This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
adapter_config.json CHANGED
@@ -23,8 +23,8 @@
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,
 
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,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf811cc48e6d52048421f81a79f0add59ac8403ae7401036a7329c630027c74b
3
  size 10107280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea4f85050e3f72aa61b67d20cd87af744f04a84c2ced064a91d8babadbcb92b
3
  size 10107280
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
3
- size 11422063
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1acd4d0d9a9860c92759c0f9eca833daf894cfbd2b9e7e1246407b7140307fa
3
  size 5816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ee04ac1d241fb7b3941a777a3cf78a6726e39287672af6709cb8fe8ddd228bc
3
  size 5816