Hugging Face's logo

DeepBrainz
/
DeepBrainz-R1-0.6B-Exp

Text Generation
Safetensors
English
qwen3
reasoning
math
coding
distillation
small-model
conversational
Model card Files
xet
Community
3
ArunkumarVR commited on
Commit
5ab9014
·
verified ·
1 Parent(s): 55ced14

Update with OPD step_100 checkpoint (10.0% accuracy, 16K context, fixed head_dim)

Browse files
Files changed (2) hide show
  1. config.json +16 -47
  2. model.safetensors +2 -2
config.json CHANGED
@@ -2,59 +2,28 @@
2
  "architectures": [
3
  "Qwen3ForCausalLM"
4
  ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
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
- "layer_types": [
15
- "full_attention",
16
- "full_attention",
17
- "full_attention",
18
- "full_attention",
19
- "full_attention",
20
- "full_attention",
21
- "full_attention",
22
- "full_attention",
23
- "full_attention",
24
- "full_attention",
25
- "full_attention",
26
- "full_attention",
27
- "full_attention",
28
- "full_attention",
29
- "full_attention",
30
- "full_attention",
31
- "full_attention",
32
- "full_attention",
33
- "full_attention",
34
- "full_attention",
35
- "full_attention",
36
- "full_attention",
37
- "full_attention",
38
- "full_attention",
39
- "full_attention",
40
- "full_attention",
41
- "full_attention",
42
- "full_attention"
43
- ],
44
- "max_position_embeddings": 40960,
45
- "max_window_layers": 28,
46
- "model_type": "qwen3",
47
- "num_attention_heads": 16,
48
  "num_hidden_layers": 28,
 
49
  "num_key_value_heads": 8,
 
 
50
  "rms_norm_eps": 1e-06,
 
51
  "rope_scaling": null,
52
- "rope_theta": 1000000,
53
- "sliding_window": null,
54
- "tie_word_embeddings": true,
 
 
55
  "torch_dtype": "bfloat16",
56
- "transformers_version": "4.55.4",
57
  "use_cache": true,
58
  "use_sliding_window": false,
59
- "vocab_size": 151936
60
- }
 
 
 
 
2
  "architectures": [
3
  "Qwen3ForCausalLM"
4
  ],
5
+ "model_type": "qwen3",
 
 
 
 
 
6
  "hidden_size": 1024,
 
7
  "intermediate_size": 3072,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "num_hidden_layers": 28,
9
+ "num_attention_heads": 16,
10
  "num_key_value_heads": 8,
11
+ "head_dim": 128,
12
+ "max_position_embeddings": 16384,
13
  "rms_norm_eps": 1e-06,
14
+ "rope_theta": 1000000.0,
15
  "rope_scaling": null,
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "hidden_act": "silu",
19
+ "initializer_range": 0.02,
20
+ "tie_word_embeddings": false,
21
  "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.45.0",
23
  "use_cache": true,
24
  "use_sliding_window": false,
25
+ "vocab_size": 151936,
26
+ "bos_token_id": 151643,
27
+ "eos_token_id": 151645,
28
+ "pad_token_id": 151643
29
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a80d1186cbd76cb222ea7a8ed63a5b218103534599e09a1b2090794af31e5dc
3
- size 2384234944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9920f3b4a9a3280f669b8a51343c16b82fecd48d3c90bb6fda297d50d9602bab
3
+ size 3006565024