gitglubber commited on
Commit
d6da2ca
·
verified ·
1 Parent(s): fbb1017

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  model.onnx.data filter=lfs diff=lfs merge=lfs -text
37
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  model.onnx.data filter=lfs diff=lfs merge=lfs -text
37
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -1,38 +1,77 @@
1
- {
2
- "model_type": "qwen3",
3
- "architectures": ["Qwen3ForCausalLM"],
4
- "vocab_size": 151936,
5
- "hidden_size": 2560,
6
- "intermediate_size": 6912,
7
- "num_attention_heads": 32,
8
- "num_hidden_layers": 36,
9
- "num_key_value_heads": 8,
10
- "head_dim": 128,
11
- "max_position_embeddings": 262144,
12
- "rope_theta": 1000000.0,
13
- "rms_norm_eps": 1e-6,
14
- "use_cache": true,
15
- "pad_token_id": 151654,
16
- "bos_token_id": 151643,
17
- "eos_token_id": [151645, 151643],
18
- "tie_word_embeddings": false,
19
- "torch_dtype": "bfloat16",
20
- "use_sliding_window": false,
21
- "sliding_window": null,
22
- "max_window_layers": 36,
23
- "attention_dropout": 0.0,
24
- "hidden_dropout": 0.0,
25
- "initializer_range": 0.02,
26
- "use_qk_norm": false,
27
- "_name_or_path": "gitglubber/slider_onnx",
28
- "transformers_version": "4.40.0",
29
- "transformers.js_config": {
30
- "kv_cache_dtype": {
31
- "q4f16": "float16",
32
- "fp16": "float16"
33
- },
34
- "use_external_data_format": {
35
- "model.onnx": true
36
- }
37
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  }
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2560,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 9728,
14
+ "layer_types": [
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
+ "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
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 40960,
53
+ "max_window_layers": 36,
54
+ "model_type": "qwen3",
55
+ "num_attention_heads": 32,
56
+ "num_hidden_layers": 36,
57
+ "num_key_value_heads": 8,
58
+ "rms_norm_eps": 1e-06,
59
+ "rope_scaling": null,
60
+ "rope_theta": 1000000,
61
+ "sliding_window": null,
62
+ "tie_word_embeddings": true,
63
+ "torch_dtype": "bfloat16",
64
+ "transformers_version": "4.53.0.dev0",
65
+ "use_cache": true,
66
+ "use_sliding_window": false,
67
+ "vocab_size": 151936,
68
+ "transformers.js_config": {
69
+ "dtype": "q4f16",
70
+ "kv_cache_dtype": {
71
+ "q4f16": "float16"
72
+ },
73
+ "use_external_data_format": {
74
+ "model_q4f16.onnx": 1
75
+ }
76
+ }
77
  }
onnx/model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab1895aad365d30d5261b8ca6d8cbc50e59782f24ec03081b17c695e3d276f2
3
+ size 417816
onnx/model_q4f16.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e606bb2054b861ef7d46f0f9282aa8ed3fa7439b296144549ee9fabf8066395
3
+ size 4208328704