gihong99 commited on
Commit
e39679f
·
verified ·
1 Parent(s): e659b5a

Upload config.json with huggingface_hub

Browse files
Files changed (2) hide show
  1. .gitattributes +1 -0
  2. config.json +3 -60
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
38
+ config.json filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -1,60 +1,3 @@
1
- {
2
- "architectures": [
3
- "Qwen3Model"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "eos_token_id": 151643,
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": 32768,
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": "float32",
56
- "transformers_version": "4.54.1",
57
- "use_cache": true,
58
- "use_sliding_window": false,
59
- "vocab_size": 219698
60
- }
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:413318e08dc21deeb36c3d37e6c44b8664dec6a0a185102f3d06cbac58687332
3
+ size 1330909880