Hugging Face's logo

C10X
/
tenny

Safetensors
qwen3
Model card Files
xet
 Community
C10X commited on
Commit
95ef5c8
·
verified ·
1 Parent(s): 2a99075

Upload 7 files

Browse files
Files changed (4) hide show
  1. config.json +5 -33
  2. generation_config.json +1 -1
  3. metadata.json +4 -4
  4. model.safetensors +2 -2
config.json CHANGED
@@ -7,50 +7,22 @@
7
  "bos_token_id": 0,
8
  "dtype": "float32",
9
  "eos_token_id": 4,
10
- "head_dim": 32,
11
  "hidden_act": "silu",
12
  "hidden_size": 64,
13
  "initializer_range": 0.02,
14
- "intermediate_size": 256,
15
  "layer_types": [
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
- "full_attention",
44
  "full_attention",
45
  "full_attention",
46
  "full_attention",
47
  "full_attention"
48
  ],
49
  "max_position_embeddings": 2048,
50
- "max_window_layers": 32,
51
  "model_type": "qwen3",
52
  "num_attention_heads": 4,
53
- "num_hidden_layers": 32,
54
  "num_key_value_heads": 2,
55
  "pad_token_id": 1,
56
  "rms_norm_eps": 1e-06,
@@ -59,7 +31,7 @@
59
  "sliding_window": null,
60
  "tie_word_embeddings": true,
61
  "transformers_version": "4.57.6",
62
- "use_cache": true,
63
  "use_sliding_window": false,
64
  "vocab_size": 2048
65
  }
 
7
  "bos_token_id": 0,
8
  "dtype": "float32",
9
  "eos_token_id": 4,
10
+ "head_dim": 16,
11
  "hidden_act": "silu",
12
  "hidden_size": 64,
13
  "initializer_range": 0.02,
14
+ "intermediate_size": 272,
15
  "layer_types": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  "full_attention",
17
  "full_attention",
18
  "full_attention",
19
  "full_attention"
20
  ],
21
  "max_position_embeddings": 2048,
22
+ "max_window_layers": 4,
23
  "model_type": "qwen3",
24
  "num_attention_heads": 4,
25
+ "num_hidden_layers": 4,
26
  "num_key_value_heads": 2,
27
  "pad_token_id": 1,
28
  "rms_norm_eps": 1e-06,
 
31
  "sliding_window": null,
32
  "tie_word_embeddings": true,
33
  "transformers_version": "4.57.6",
34
+ "use_cache": false,
35
  "use_sliding_window": false,
36
  "vocab_size": 2048
37
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 0,
4
  "eos_token_id": 4,
5
  "pad_token_id": 1,
6
- "use_cache": true
7
  }
 
3
  "bos_token_id": 0,
4
  "eos_token_id": 4,
5
  "pad_token_id": 1,
6
+ "use_cache": false
7
  }
metadata.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "preset": "qwen3-32layer-c10x",
3
  "family": "qwen3",
4
  "source": "inline-preset",
5
- "output_dir": "D:\\Qwen3-80m-tinystories-A\\workspace\\outputs\\qwen3-32layer-c10x",
6
- "parameters": 2496576,
7
  "vocab_size": 2048,
8
  "hidden_size": 64,
9
- "num_hidden_layers": 32,
10
  "num_attention_heads": 4,
11
  "num_key_value_heads": 2,
12
  "rope_theta": 10000.0
 
1
  {
2
+ "preset": "qwen3-16layer-c10x",
3
  "family": "qwen3",
4
  "source": "inline-preset",
5
+ "output_dir": "D:\\Qwen3-80m-tinystories-A\\workspace\\outputs\\qwen3-16layer-c10x",
6
+ "parameters": 389824,
7
  "vocab_size": 2048,
8
  "hidden_size": 64,
9
+ "num_hidden_layers": 4,
10
  "num_attention_heads": 4,
11
  "num_key_value_heads": 2,
12
  "rope_theta": 10000.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e223f0d607fdc649ddfa5bca27b1675e6ee75bdd65198b00450abe76cba4d283
3
- size 10023688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1398ccc0817400641f03154d30004d36b740ecc804e577f7db405f37565a45a6
3
+ size 1564088