Hugging Face's logo

Blancy
/
Qwen3-0.6B-Open-R1-GRPO

Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Model card Files
xet
Community
Blancy commited on
Commit
4da7567
·
verified ·
1 Parent(s): 085332c

Training in progress, step 36

Browse files
Files changed (3) hide show
  1. config.json +2 -2
  2. model.safetensors +2 -2
  3. training_args.bin +1 -1
config.json CHANGED
@@ -8,9 +8,9 @@
8
  "eos_token_id": 151645,
9
  "head_dim": 128,
10
  "hidden_act": "silu",
11
- "hidden_size": 1024,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
  "max_position_embeddings": 40960,
15
  "max_window_layers": 28,
16
  "model_type": "qwen3",
 
8
  "eos_token_id": 151645,
9
  "head_dim": 128,
10
  "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 6144,
14
  "max_position_embeddings": 40960,
15
  "max_window_layers": 28,
16
  "model_type": "qwen3",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4c91f251eb6610040500fa1ac8e1c341ce765270170524832770f5ee67f1808
3
- size 1503300328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:858a411e08107bbbfc16b446e94872aefe0a8c51473fb2a210db29b01879e3a9
3
+ size 4063515640
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:344398021d8f8ac2bed4f1583d831d72c7d5ee8fe335f66ee0d52341f9bd28a4
3
  size 7992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d391a40b062be36390fa0926081d5d6c7d4411558f21de2f306816fa487ba20d
3
  size 7992