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
xet
Community
Blancy commited on
Commit
4dd0cd4
·
verified ·
1 Parent(s): eb0f52c

Training in progress, step 31

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 sha256:64e6c561434f0100e74400079267d5967288934f16cd7f2ab03cffbc55ccbc07
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af8fa3d5b13f0c233de220a67e5d61915b963954f90b94d0d86c39c3634ef8f1
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85854e1823fae0f4536868c28b9740575588b3e6fe4f002a7057af1a78f7ae10
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ca3217f4d998124486292212390a9bd077166f054f8974060c44748c04c3f8a
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:d9bce30fb3c0ece0125dd5b14aa4afe8dedeaa011dd0af96710f87cdc0d59976
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:058d31e31cf96656cbe5eeaa07a435588395dcaf2ecb303d6f4c942aab8d8532
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:ec92e1736b3cc64f23577e73a5c884b077c9f362f00faf75ee86252288d65870
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bb0d9ebf5a0bccced264d5e4bd0d8b1480407b614af438ff3935c712022f4b0
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 sha256:074e26b83712b26854ce02dacd15685ba2e0b2eb493e4fe65bee5612f1bbe1ea
3
  size 7864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fc5d8b502130f494c30d2149285adf201cd66e3a02eacfcdfa33bade1c50216
3
  size 7864