Hugging Face's logo

jonathanhe123
/
iapo

Reinforcement Learning
Safetensors
Model card Files
xet
 Community
1
jonathanhe123 commited on
Commit
181ec8b
·
verified ·
1 Parent(s): f90c313

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. .gitattributes +1 -0
  2. Qwen2.5-0.5B-Instruct_DAPO-Math-17k/config.json +1 -1
  3. Qwen2.5-0.5B-Instruct_DAPO-Math-17k/generation_config.json +14 -0
  4. Qwen2.5-0.5B-Instruct_DAPO-Math-17k/merges.txt +0 -0
  5. Qwen2.5-0.5B-Instruct_DAPO-Math-17k/model.safetensors +1 -1
  6. Qwen2.5-0.5B-Instruct_DAPO-Math-17k/tokenizer.json +0 -0
.gitattributes CHANGED
@@ -1,3 +1,4 @@
1
  Qwen2.5-0.5B-Instruct_DAPO-Math-17k/model.safetensors filter=lfs diff=lfs merge=lfs -text
2
  Qwen2.5-0.5B-Instruct_GSM8K/model.safetensors filter=lfs diff=lfs merge=lfs -text
3
  Qwen2.5-0.5B-Instruct_GSM8K/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
1
  Qwen2.5-0.5B-Instruct_DAPO-Math-17k/model.safetensors filter=lfs diff=lfs merge=lfs -text
2
  Qwen2.5-0.5B-Instruct_GSM8K/model.safetensors filter=lfs diff=lfs merge=lfs -text
3
  Qwen2.5-0.5B-Instruct_GSM8K/tokenizer.json filter=lfs diff=lfs merge=lfs -text
4
+ Qwen2.5-0.5B-Instruct_DAPO-Math-17k/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Qwen2.5-0.5B-Instruct_DAPO-Math-17k/config.json CHANGED
@@ -47,7 +47,7 @@
47
  "rope_theta": 1000000.0,
48
  "sliding_window": null,
49
  "tie_word_embeddings": true,
50
- "transformers_version": "4.57.3",
51
  "use_cache": false,
52
  "use_sliding_window": false,
53
  "vocab_size": 151936
 
47
  "rope_theta": 1000000.0,
48
  "sliding_window": null,
49
  "tie_word_embeddings": true,
50
+ "transformers_version": "4.57.6",
51
  "use_cache": false,
52
  "use_sliding_window": false,
53
  "vocab_size": 151936
Qwen2.5-0.5B-Instruct_DAPO-Math-17k/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "repetition_penalty": 1.1,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.6",
13
+ "use_cache": false
14
+ }
Qwen2.5-0.5B-Instruct_DAPO-Math-17k/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
Qwen2.5-0.5B-Instruct_DAPO-Math-17k/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6eee78a66b2cbeba919fa61a03c90044406b2f77fa4f03ecd3b2e88d83cc997c
3
  size 1260367448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:855ef73596006d8cbf2cb598e04b7d72129a7a3af65fdfc75f93acadb32ef7f9
3
  size 1260367448
Qwen2.5-0.5B-Instruct_DAPO-Math-17k/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff