Hugging Face's logo

Kadins
/
Qwen-2.5-7B-Math-RL

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Model card Files Community
Kadins commited on
Commit
efc65d4
·
verified ·
1 Parent(s): 759a8e5

Training in progress, step 10

Browse files
Files changed (6) hide show
  1. config.json +2 -2
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00003-of-00004.safetensors +1 -1
  5. model-00004-of-00004.safetensors +1 -1
  6. training_args.bin +2 -2
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/home/jovyan/LLM/yanjz/finetuned/qwen2_5-7b-math-r1/v2-20250305-101739/checkpoint-7",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
@@ -24,7 +24,7 @@
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.49.0",
27
- "use_cache": true,
28
  "use_mrope": false,
29
  "use_sliding_window": false,
30
  "vocab_size": 152064
 
1
  {
2
+ "_name_or_path": "/home/jovyan/LLM/yanjz/finetuned/qwen2_5-7b-math-r1/v3-20250305-153627/checkpoint-15",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
 
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.49.0",
27
+ "use_cache": false,
28
  "use_mrope": false,
29
  "use_sliding_window": false,
30
  "vocab_size": 152064
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b597d7c884bdc69e0d33e88934bfcc63dff3490f0747cad4f2bba14fadbbc8dc
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a9a393b2b3fd564dc757d9fae67d6d563637fc37f65997409201778b332407
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b12b97afec858d0b7437905dedbed33a3882eeb98043c7879e2ab06f39f60f1
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99d113ebe26217a9f9cb328899fb97a96e3e77079b0b0239efc8b3fb52565a96
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b041fc5a53bbc7dea514776a4f5f4308db0fd399ad8476d0b15b07642b4ebfc
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7054963f98d38414978d3d761c86ed750b3501382d97223f8e1b0d6b0a2fb05
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92751d55da45c0947a097c88a48976029c7585b3ea853d69f4bbe7823308ceff
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd02e16364c0fdacd4a03f2fc60e8fcf8e1ed12ac2e19351d3d4fc5e599295f1
3
  size 1089994880
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd402b52184580aa5baad01b75817bc94a3207a4ff3b3ba6caa0330c095e468a
3
- size 7928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0101728fd6a86d7198a4afd2d7fa65126a8e34a0c55a9a922b6ceb3cd908444a
3
+ size 7992