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
Model card Files Community
Blancy commited on
Commit
4e03fa7
·
verified ·
1 Parent(s): c560b73

Training in progress, step 10

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:a17da41212c9ee66cec8710b96f987bdbbcf3b376ecaca5ff5046de7ec0eb8a1
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6dbdb24a538a16d157cce66170544681a295a1c511afe6c1495a67d17b9e39a
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:d8dab92b2f363053fd3e2161bb9b1f14a7e4e858a4385a15fe106701d40267f3
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c5a245c828a82740398ec31a104b0c52bb9ca3d5251e8247a2f051ba7c2a560
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cb2ee72c694ffa9510e28f17ce67ba65aa8c5edb494a3254d212b407e110ade
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194c99b83c7e632f14842c148883eb9ec37ee1460c11327ae90b8ab013590338
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6749b5126bda1106063c71746718a4b3a9e9ef74d9786ffa3408ff8e3d944290
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6c7de1a03b76816e269c0496fefd3988d1386ff51c1533ea71e2769d6dc204e
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:ee8c4426e4be3182b2f3d77955a205ea5a15b64f2ef762f99db187505e1b3b38
3
  size 7864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73830b4ac8b473afac88e24583ec4562a904a39b25326cae2cb5ef486b33fc62
3
  size 7864