gangel commited on
Commit
87f0296
·
verified ·
1 Parent(s): 351312b

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. config.json +53 -0
  2. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DFlashDraftModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "block_size": 16,
8
+ "dflash_config": {
9
+ "mask_token_id": 32127,
10
+ "target_layer_ids": [
11
+ 1,
12
+ 12,
13
+ 23,
14
+ 34,
15
+ 45
16
+ ]
17
+ },
18
+ "dtype": "bfloat16",
19
+ "head_dim": 128,
20
+ "hidden_act": "silu",
21
+ "hidden_size": 4096,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 14336,
24
+ "layer_types": [
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention"
30
+ ],
31
+ "max_position_embeddings": 32768,
32
+ "max_window_layers": 28,
33
+ "mlp_bias": false,
34
+ "model_type": "qwen3",
35
+ "num_attention_heads": 32,
36
+ "num_hidden_layers": 5,
37
+ "num_key_value_heads": 8,
38
+ "num_target_layers": 50,
39
+ "rms_norm_eps": 1e-05,
40
+ "rope_scaling": null,
41
+ "rope_theta": 1000000,
42
+ "sliding_window": null,
43
+ "tie_word_embeddings": false,
44
+ "transformers_version": "4.57.5",
45
+ "use_cache": true,
46
+ "use_sliding_window": false,
47
+ "vocab_size": 32128,
48
+ "quantization": {
49
+ "group_size": 32,
50
+ "bits": 8,
51
+ "mode": "affine"
52
+ }
53
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a4bbc69b4ae614a2afc0440c1077c7e0247a9b83cfede6518ba5129fb0dd1f
3
+ size 1321320396