Zoont commited on
Commit
bbf124b
·
verified ·
1 Parent(s): 3ac7fff

Upload Qwen3ForCausalLM

Browse files
Files changed (2) hide show
  1. config.json +48 -48
  2. model.safetensors +2 -2
config.json CHANGED
@@ -1,48 +1,48 @@
1
- {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "dtype": "bfloat16",
8
- "head_dim": 128,
9
- "hidden_act": "silu",
10
- "hidden_size": 640,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 1920,
13
- "layer_types": [
14
- "full_attention",
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
- ],
33
- "max_position_embeddings": 2048,
34
- "max_window_layers": 18,
35
- "model_type": "qwen3",
36
- "num_attention_heads": 8,
37
- "num_hidden_layers": 18,
38
- "num_key_value_heads": 4,
39
- "rms_norm_eps": 1e-06,
40
- "rope_scaling": null,
41
- "rope_theta": 10000.0,
42
- "sliding_window": null,
43
- "tie_word_embeddings": true,
44
- "transformers_version": "4.57.3",
45
- "use_cache": true,
46
- "use_sliding_window": false,
47
- "vocab_size": 32010
48
- }
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 640,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 1920,
13
+ "layer_types": [
14
+ "full_attention",
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
+ ],
33
+ "max_position_embeddings": 2048,
34
+ "max_window_layers": 18,
35
+ "model_type": "qwen3",
36
+ "num_attention_heads": 8,
37
+ "num_hidden_layers": 18,
38
+ "num_key_value_heads": 4,
39
+ "rms_norm_eps": 1e-06,
40
+ "rope_scaling": null,
41
+ "rope_theta": 10000.0,
42
+ "sliding_window": null,
43
+ "tie_word_embeddings": true,
44
+ "transformers_version": "4.57.3",
45
+ "use_cache": true,
46
+ "use_sliding_window": false,
47
+ "vocab_size": 32064
48
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:058e9fb56be84137903640fd9b17a06a23bcdbcdda09f5a57ec695c1cd0add63
3
- size 244542240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbe24dfb5a605b150298c5a4cf4e1ac1af7f279d4ad8cf5a7c11ee5d7526c74a
3
+ size 244610080