Hugging Face's logo

kishizaki-sci
/
Llama-4-Scout-17B-16E-Instruct-AWQ

Safetensors
English
llama4
4-bit precision
awq
Model card Files Community
kishizaki-sci commited on
Commit
e96143b
·
verified ·
1 Parent(s): e167b9d

Upload Llama4ForConditionalGeneration

Browse files
Files changed (16) hide show
  1. config.json +197 -0
  2. generation_config.json +13 -0
  3. model-00001-of-00013.safetensors +3 -0
  4. model-00002-of-00013.safetensors +3 -0
  5. model-00003-of-00013.safetensors +3 -0
  6. model-00004-of-00013.safetensors +3 -0
  7. model-00005-of-00013.safetensors +3 -0
  8. model-00006-of-00013.safetensors +3 -0
  9. model-00007-of-00013.safetensors +3 -0
  10. model-00008-of-00013.safetensors +3 -0
  11. model-00009-of-00013.safetensors +3 -0
  12. model-00010-of-00013.safetensors +3 -0
  13. model-00011-of-00013.safetensors +3 -0
  14. model-00012-of-00013.safetensors +3 -0
  15. model-00013-of-00013.safetensors +3 -0
  16. model.safetensors.index.json +0 -0
config.json ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Llama4ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 200080,
6
+ "eoi_token_index": 200081,
7
+ "image_token_index": 200092,
8
+ "max_seq_len": 2048,
9
+ "model_type": "llama4",
10
+ "quantization_config": {
11
+ "bits": 4,
12
+ "group_size": 128,
13
+ "modules_to_not_convert": [
14
+ "self_attn.o_proj",
15
+ "feed_forward.router"
16
+ ],
17
+ "quant_method": "awq",
18
+ "version": "gemm",
19
+ "zero_point": true
20
+ },
21
+ "text_config": {
22
+ "_attn_implementation_autoset": true,
23
+ "attention_bias": false,
24
+ "attention_chunk_size": 8192,
25
+ "attention_dropout": 0.0,
26
+ "attn_scale": 0.1,
27
+ "attn_temperature_tuning": 4,
28
+ "bos_token_id": 200000,
29
+ "cache_implementation": "hybrid",
30
+ "eos_token_id": [
31
+ 200001,
32
+ 200007,
33
+ 200008
34
+ ],
35
+ "floor_scale": 8192,
36
+ "for_llm_compressor": false,
37
+ "head_dim": 128,
38
+ "hidden_act": "silu",
39
+ "hidden_size": 5120,
40
+ "initializer_range": 0.02,
41
+ "interleave_moe_layer_step": 1,
42
+ "intermediate_size": 8192,
43
+ "intermediate_size_mlp": 16384,
44
+ "max_position_embeddings": 10485760,
45
+ "model_type": "llama4_text",
46
+ "moe_layers": [
47
+ 0,
48
+ 1,
49
+ 2,
50
+ 3,
51
+ 4,
52
+ 5,
53
+ 6,
54
+ 7,
55
+ 8,
56
+ 9,
57
+ 10,
58
+ 11,
59
+ 12,
60
+ 13,
61
+ 14,
62
+ 15,
63
+ 16,
64
+ 17,
65
+ 18,
66
+ 19,
67
+ 20,
68
+ 21,
69
+ 22,
70
+ 23,
71
+ 24,
72
+ 25,
73
+ 26,
74
+ 27,
75
+ 28,
76
+ 29,
77
+ 30,
78
+ 31,
79
+ 32,
80
+ 33,
81
+ 34,
82
+ 35,
83
+ 36,
84
+ 37,
85
+ 38,
86
+ 39,
87
+ 40,
88
+ 41,
89
+ 42,
90
+ 43,
91
+ 44,
92
+ 45,
93
+ 46,
94
+ 47
95
+ ],
96
+ "no_rope_layers": [
97
+ 1,
98
+ 1,
99
+ 1,
100
+ 0,
101
+ 1,
102
+ 1,
103
+ 1,
104
+ 0,
105
+ 1,
106
+ 1,
107
+ 1,
108
+ 0,
109
+ 1,
110
+ 1,
111
+ 1,
112
+ 0,
113
+ 1,
114
+ 1,
115
+ 1,
116
+ 0,
117
+ 1,
118
+ 1,
119
+ 1,
120
+ 0,
121
+ 1,
122
+ 1,
123
+ 1,
124
+ 0,
125
+ 1,
126
+ 1,
127
+ 1,
128
+ 0,
129
+ 1,
130
+ 1,
131
+ 1,
132
+ 0,
133
+ 1,
134
+ 1,
135
+ 1,
136
+ 0,
137
+ 1,
138
+ 1,
139
+ 1,
140
+ 0,
141
+ 1,
142
+ 1,
143
+ 1,
144
+ 0
145
+ ],
146
+ "num_attention_heads": 40,
147
+ "num_experts_per_tok": 1,
148
+ "num_hidden_layers": 48,
149
+ "num_key_value_heads": 8,
150
+ "num_local_experts": 16,
151
+ "output_router_logits": false,
152
+ "pad_token_id": 200018,
153
+ "rms_norm_eps": 1e-05,
154
+ "rope_scaling": {
155
+ "factor": 16.0,
156
+ "high_freq_factor": 1.0,
157
+ "low_freq_factor": 1.0,
158
+ "original_max_position_embeddings": 8192,
159
+ "rope_type": "llama3"
160
+ },
161
+ "rope_theta": 500000.0,
162
+ "router_aux_loss_coef": 0.001,
163
+ "router_jitter_noise": 0.0,
164
+ "torch_dtype": "float16",
165
+ "use_cache": false,
166
+ "use_qk_norm": true,
167
+ "vocab_size": 202048
168
+ },
169
+ "tie_word_embeddings": false,
170
+ "torch_dtype": "float16",
171
+ "transformers_version": "4.51.3",
172
+ "vision_config": {
173
+ "_attn_implementation_autoset": true,
174
+ "attention_dropout": 0.0,
175
+ "hidden_act": "gelu",
176
+ "hidden_size": 1408,
177
+ "image_size": 336,
178
+ "initializer_range": 0.02,
179
+ "intermediate_size": 5632,
180
+ "model_type": "llama4_vision_model",
181
+ "multi_modal_projector_bias": false,
182
+ "norm_eps": 1e-05,
183
+ "num_attention_heads": 16,
184
+ "num_channels": 3,
185
+ "num_hidden_layers": 34,
186
+ "patch_size": 14,
187
+ "pixel_shuffle_ratio": 0.5,
188
+ "projector_dropout": 0.0,
189
+ "projector_input_dim": 4096,
190
+ "projector_output_dim": 4096,
191
+ "rope_theta": 10000,
192
+ "torch_dtype": "float16",
193
+ "vision_feature_layer": -1,
194
+ "vision_feature_select_strategy": "default",
195
+ "vision_output_dim": 4096
196
+ }
197
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 200000,
4
+ "cache_implementation": "hybrid",
5
+ "eos_token_id": [
6
+ 200001,
7
+ 200007,
8
+ 200008
9
+ ],
10
+ "pad_token_id": 200018,
11
+ "transformers_version": "4.51.3",
12
+ "use_cache": false
13
+ }
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c39962a22bde96469e2f00846de64ebde9e0acfffc2c90b2323f1106ee069a63
3
+ size 4996382800
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0384e3ecca798c0384aaff35e2092694a60b036684dbd4d1aec21bd57137e21
3
+ size 4979791152
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c32b34c71a869d1d336772bb01b84c0964eb9a3f71d921b33786e15e4ce34969
3
+ size 4995512616
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29d92fe189e9cc5999cb00eaaf83da5903398e746e89b1d0b69e228ef0d7fe05
3
+ size 4995513344
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94ab4cac08a52312564686b19e66f8ea9e3cf6b6f7ac9c4ee25433fabec7b363
3
+ size 4995513504
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaf670acaa577db32f234cdfbb22f3266b20112f42a7264971145e4050a471d7
3
+ size 4979993288
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c91388e9bcaadf05f47d82689cd96c5d391fa23b5dfcc7626d3a578418ba29f6
3
+ size 4995513456
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2018aa956d8f71edf9d285dff776ef9b8cb6270f6f18fa62ea37c7273c38d6d1
3
+ size 4995513456
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2dbc60e17a7b5807371f82c39cb34f31bd2f5e14b758578ef142bfb8d796f6a
3
+ size 4995513480
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bd0cdb9b0bc191e3ba0a35e081655016fd562ab819ab375472027a547372e42
3
+ size 4995677488
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b422549a29af3b6b82daf0c3ccdae0a3d4c2ea3ea25067b25ddaebd052e81c8
3
+ size 4979829280
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d88a8ea67828c095cc7425fb9f45c46bc569d0e6c681257e3e40b1c8dd53defe
3
+ size 4995513456
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52f09586e3a98ba32f571bec639e9f7d593bfaa894b84c4a0a96ca8a6e1826f4
3
+ size 2788560568
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff