Hugging Face's logo

Blancy
/
Qwen-2.5-7B-Simple-RL

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Blancy commited on
Commit
ca4401d
·
verified ·
1 Parent(s): 868431e

Training in progress, step 7

Browse files
Files changed (7) hide show
  1. config.json +1 -1
  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. tokenizer.json +2 -2
  7. training_args.bin +1 -1
config.json CHANGED
@@ -23,7 +23,7 @@
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.49.0",
26
- "use_cache": true,
27
  "use_mrope": false,
28
  "use_sliding_window": false,
29
  "vocab_size": 152064
 
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.49.0",
26
+ "use_cache": false,
27
  "use_mrope": false,
28
  "use_sliding_window": false,
29
  "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:bfe2e73ec4ecfb32690fcb1ae6c32fcf54cf697c9061f80135369a86ea581ac7
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3efd0ef3b2eee2381a769c22f7b3ee4084f409ffd684bf4b6b5a92160380d8fa
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:880f3539e8840151fa69908dff09c363d9d909d74ba1c7e9e75990db04339bbe
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31a4f5a54637e6e5398d1d0e3ae8067922cf251e157767d3fbd1621b269f4655
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cd53fffb43925af37d32ea2c3b3f41a47304b8aee2da332f7cbafa2cf6be02c
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b014ab890790623fee1925408ccc575abe1d6660603df21892f7c4097207d1
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47579f89df5ab2ba520f30677200499074233f4ae6eacdc9c0e3e3eb41782d6d
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f9374297568099555f2a9a70e826f8354c329eb2f1fcfe0bff76345b86c2ea
3
  size 1089994880
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
- size 11421896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
3
+ size 11422063
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e65ee56a5701b8445dc0c9d735738ae75ac41d7a7d5eb9efff23e9f669ca3eb
3
  size 7864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:143482d016b9c9172d1b9f90b054230ffea7c33be7fe32151ba6b76ac522eb35
3
  size 7864