Hugging Face's logo

threex
/
3x-0.5B-Chat

Safetensors
threex2
Model card Files
xet
 Community
tomzhou10010 commited on
Commit
4ba003e
·
verified ·
1 Parent(s): d68371f

Release 3x-0.5B-Chat (standard HF interface, no trust_remote_code needed)

Browse files
Files changed (1) hide show
  1. config.json +57 -57
config.json CHANGED
@@ -1,57 +1,57 @@
1
- {
2
- "architectures": [
3
- "Qwen2ForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
- "dtype": "float32",
8
- "eos_token_id": 151645,
9
- "hidden_act": "silu",
10
- "hidden_size": 1024,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 2816,
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
- "full_attention",
33
- "full_attention",
34
- "full_attention",
35
- "full_attention",
36
- "full_attention",
37
- "full_attention"
38
- ],
39
- "max_position_embeddings": 32768,
40
- "model_type": "qwen2",
41
- "num_attention_heads": 16,
42
- "num_hidden_layers": 24,
43
- "num_key_value_heads": 16,
44
- "pad_token_id": 151645,
45
- "rms_norm_eps": 1e-06,
46
- "rope_parameters": {
47
- "rope_theta": 10000.0,
48
- "rope_type": "default"
49
- },
50
- "rope_theta": 10000.0,
51
- "sliding_window": null,
52
- "tie_word_embeddings": false,
53
- "transformers_version": "5.2.0",
54
- "use_cache": true,
55
- "use_sliding_window": false,
56
- "vocab_size": 151936
57
- }
 
1
+ {
2
+ "architectures": [
3
+ "ThreexForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "float32",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 2816,
13
+ "layer_types": [
14
+ "attention",
15
+ "attention",
16
+ "attention",
17
+ "attention",
18
+ "attention",
19
+ "attention",
20
+ "attention",
21
+ "attention",
22
+ "attention",
23
+ "attention",
24
+ "attention",
25
+ "attention",
26
+ "attention",
27
+ "attention",
28
+ "attention",
29
+ "attention",
30
+ "attention",
31
+ "attention",
32
+ "attention",
33
+ "attention",
34
+ "attention",
35
+ "attention",
36
+ "attention",
37
+ "attention"
38
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "model_type": "threex2",
41
+ "num_attention_heads": 16,
42
+ "num_hidden_layers": 24,
43
+ "num_key_value_heads": 16,
44
+ "pad_token_id": 151645,
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_parameters": {
47
+ "rope_theta": 10000.0,
48
+ "rope_type": "default"
49
+ },
50
+ "rope_theta": 10000.0,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": false,
53
+ "transformers_version": "5.2.0",
54
+ "use_cache": true,
55
+ "use_sliding_window": false,
56
+ "vocab_size": 151936
57
+ }