Dans commited on
Commit
1ecaaab
·
verified ·
1 Parent(s): 1bf75d1

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 3,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 3,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 512,
13
+ "initializer_range": 0.041666666666666664,
14
+ "intermediate_size": 2304,
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
+ ],
34
+ "max_position_embeddings": 512,
35
+ "max_window_layers": 17,
36
+ "model_type": "qwen3",
37
+ "num_attention_heads": 4,
38
+ "num_hidden_layers": 17,
39
+ "num_key_value_heads": 1,
40
+ "rms_norm_eps": 1e-06,
41
+ "rope_scaling": null,
42
+ "rope_theta": 10000,
43
+ "sliding_window": null,
44
+ "tie_word_embeddings": false,
45
+ "transformers_version": "4.56.1",
46
+ "use_cache": true,
47
+ "use_sliding_window": false,
48
+ "vocab_size": 8192
49
+ }
decoder.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e6e90997806f5f476911242c4f74c8b020d6929d5cd7697637ff6d887a30a8
3
+ size 57890568
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 3,
4
+ "eos_token_id": 3,
5
+ "transformers_version": "4.56.1"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:249b22edf3b165e9fb0a2f7612e0ff876abe4cdde68b27abc206ad33ada10465
3
+ size 318875656
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "[STOP]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ }
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff