Hugging Face's logo

unsloth
/
Llama-4-Scout-17B-16E-Instruct-GGUF

Image-Text-to-Text
Transformers
GGUF
PyTorch
llama4
facebook
unsloth
meta
llama
llama-4
imatrix
conversational
Model card Files
xet
Community
10
danielhanchen commited on
Commit
7dc5ea1
·
verified ·
1 Parent(s): 1d4034a

Add files using upload-large-folder tool

Browse files
Files changed (29) hide show
  1. .gitattributes +27 -0
  2. BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00001-of-00005.gguf +3 -0
  3. BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00002-of-00005.gguf +3 -0
  4. BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00003-of-00005.gguf +3 -0
  5. BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00004-of-00005.gguf +3 -0
  6. BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00005-of-00005.gguf +3 -0
  7. Llama-4-Scout-17B-16E-Instruct-Q2_K.gguf +3 -0
  8. Llama-4-Scout-17B-16E-Instruct-Q2_K_L.gguf +3 -0
  9. Llama-4-Scout-17B-16E-Instruct-UD-IQ1_M.gguf +3 -0
  10. Llama-4-Scout-17B-16E-Instruct-UD-IQ1_S.gguf +3 -0
  11. Llama-4-Scout-17B-16E-Instruct-UD-IQ2_XXS.gguf +3 -0
  12. Llama-4-Scout-17B-16E-Instruct-UD-Q2_K_XL.gguf +3 -0
  13. Q3_K_M/Llama-4-Scout-17B-16E-Instruct-Q3_K_M-00001-of-00002.gguf +3 -0
  14. Q3_K_M/Llama-4-Scout-17B-16E-Instruct-Q3_K_M-00002-of-00002.gguf +3 -0
  15. Q4_K_M/Llama-4-Scout-17B-16E-Instruct-Q4_K_M-00001-of-00002.gguf +3 -0
  16. Q4_K_M/Llama-4-Scout-17B-16E-Instruct-Q4_K_M-00002-of-00002.gguf +3 -0
  17. Q5_K_M/Llama-4-Scout-17B-16E-Instruct-Q5_K_M-00001-of-00002.gguf +3 -0
  18. Q5_K_M/Llama-4-Scout-17B-16E-Instruct-Q5_K_M-00002-of-00002.gguf +3 -0
  19. Q6_K/Llama-4-Scout-17B-16E-Instruct-Q6_K-00001-of-00002.gguf +3 -0
  20. Q6_K/Llama-4-Scout-17B-16E-Instruct-Q6_K-00002-of-00002.gguf +3 -0
  21. Q8_0/Llama-4-Scout-17B-16E-Instruct-Q8_0-00001-of-00003.gguf +3 -0
  22. Q8_0/Llama-4-Scout-17B-16E-Instruct-Q8_0-00002-of-00003.gguf +3 -0
  23. Q8_0/Llama-4-Scout-17B-16E-Instruct-Q8_0-00003-of-00003.gguf +3 -0
  24. UD-Q3_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q3_K_XL.gguf-00001-of-00002.gguf +3 -0
  25. UD-Q3_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q3_K_XL.gguf-00002-of-00002.gguf +3 -0
  26. UD-Q4_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL.gguf-00001-of-00002.gguf +3 -0
  27. UD-Q4_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL.gguf-00002-of-00002.gguf +3 -0
  28. config.json +80 -0
  29. imatrix.dat +3 -0
.gitattributes CHANGED
@@ -33,3 +33,30 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ imatrix.dat filter=lfs diff=lfs merge=lfs -text
37
+ Llama-4-Scout-17B-16E-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Llama-4-Scout-17B-16E-Instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Llama-4-Scout-17B-16E-Instruct-UD-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Llama-4-Scout-17B-16E-Instruct-UD-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Llama-4-Scout-17B-16E-Instruct-UD-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Llama-4-Scout-17B-16E-Instruct-UD-Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
43
+ BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
44
+ BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
45
+ BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
46
+ BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
47
+ BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Q8_0/Llama-4-Scout-17B-16E-Instruct-Q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Q8_0/Llama-4-Scout-17B-16E-Instruct-Q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Q8_0/Llama-4-Scout-17B-16E-Instruct-Q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
51
+ Q6_K/Llama-4-Scout-17B-16E-Instruct-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
52
+ Q6_K/Llama-4-Scout-17B-16E-Instruct-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
53
+ Q5_K_M/Llama-4-Scout-17B-16E-Instruct-Q5_K_M-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
54
+ Q5_K_M/Llama-4-Scout-17B-16E-Instruct-Q5_K_M-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
55
+ Q4_K_M/Llama-4-Scout-17B-16E-Instruct-Q4_K_M-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
56
+ Q4_K_M/Llama-4-Scout-17B-16E-Instruct-Q4_K_M-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
57
+ Q3_K_M/Llama-4-Scout-17B-16E-Instruct-Q3_K_M-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
58
+ Q3_K_M/Llama-4-Scout-17B-16E-Instruct-Q3_K_M-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
59
+ UD-Q4_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL.gguf-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
60
+ UD-Q4_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL.gguf-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
61
+ UD-Q3_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q3_K_XL.gguf-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
62
+ UD-Q3_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q3_K_XL.gguf-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00001-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e9d5edd4290d75417742ffe20df3b895a32d84d3bc98bfb82e1906f804c42d
3
+ size 48936101088
BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00002-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09c6b6ca68dab43f7e0afabfa45bc0f383b7abb9c05642f614bcfe72b2070203
3
+ size 49958553056
BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00003-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b2944d204d72d7137f529374ba93e0032e9b7beafc52bc3010d04d5d62ec8d6
3
+ size 48658032224
BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00004-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5842028df069d72012974b737de27c9e7de29bd48da9bdc8fe2a115f6969c5dc
3
+ size 49790453024
BF16/Llama-4-Scout-17B-16E-Instruct-BF16-00005-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:499a20fff79de7dbbf811a224500c8c2f1f199411a9198a3fec6cbc595bce0f6
3
+ size 18218540256
Llama-4-Scout-17B-16E-Instruct-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb08c8ff3fe3ab79ec66bc5f7fc149017307626322a1aac6e0d019b87cbc9f80
3
+ size 39563315200
Llama-4-Scout-17B-16E-Instruct-Q2_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26eb5e3ebaa5c09e05d112881919de4edc4c23fcdb780b549d3d769041f3d904
3
+ size 39805772800
Llama-4-Scout-17B-16E-Instruct-UD-IQ1_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f3a48e392c73e2659e956d5424ac5abfa4f7cfff990eda03daa71b5a79285a
3
+ size 35356533760
Llama-4-Scout-17B-16E-Instruct-UD-IQ1_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0289d7a0d627023b5debd07dbb225f13c1837f8a5012746f78169cae41b51edf
3
+ size 33846584320
Llama-4-Scout-17B-16E-Instruct-UD-IQ2_XXS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e819f509a655a69e2bbca978d7326e8fe14d8e01473a1125911b59d80fee60eb
3
+ size 38565176320
Llama-4-Scout-17B-16E-Instruct-UD-Q2_K_XL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:641cedafd9205b1c8f20dcea8114b0e3ef68bbcc46522bf2a0374813d2a5e7ea
3
+ size 42237813760
Q3_K_M/Llama-4-Scout-17B-16E-Instruct-Q3_K_M-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f79b152c0e83dc8d43fcedb16dedf36c29d6b7cca52cf7f4db4bc8ca7886cb6
3
+ size 29832535584
Q3_K_M/Llama-4-Scout-17B-16E-Instruct-Q3_K_M-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa4a9c2ed429319cb9efcb37a8a76d4de32b6b79df9cabb857c6d5e8e094a232
3
+ size 21922649248
Q4_K_M/Llama-4-Scout-17B-16E-Instruct-Q4_K_M-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea072cba84db0f6c3eb837d21e0a5fea5f5123ba2cd11d6412ebc086787fd03a
3
+ size 49848377216
Q4_K_M/Llama-4-Scout-17B-16E-Instruct-Q4_K_M-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae472f8c0d6dd5ab42cfe7d39319b1fb1a53ba1a4cd8f34b965b0b2eac644601
3
+ size 15511520608
Q5_K_M/Llama-4-Scout-17B-16E-Instruct-Q5_K_M-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4669db1e16bfb9ae6e990556320c04fd37901dec7321625a39b8219bbd0bff2
3
+ size 49893490016
Q5_K_M/Llama-4-Scout-17B-16E-Instruct-Q5_K_M-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddae123772423750d09f3a977456418cec992b3f8223fcbc2248c34a3215ef7e
3
+ size 26652952416
Q6_K/Llama-4-Scout-17B-16E-Instruct-Q6_K-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07e0f6d38c654721f4548eb4bfe8a2390b1ce9a641bdbea7dfc8afaaa6dd5bfa
3
+ size 49906421888
Q6_K/Llama-4-Scout-17B-16E-Instruct-Q6_K-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee36ed90ee2fecb326bbeecd555c095f617e30e600f6ae19276d0ddcbd77c30
3
+ size 38525724256
Q8_0/Llama-4-Scout-17B-16E-Instruct-Q8_0-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8056ca4defdba26bb905ed1788a0bbd31dea5c152bbe718b42a3e3eed21f00a5
3
+ size 49835919264
Q8_0/Llama-4-Scout-17B-16E-Instruct-Q8_0-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206dcaf225895fa0430d3a8c963f02183f4ef5ceb97e8f4c5af3f47607fe16f0
3
+ size 49898043104
Q8_0/Llama-4-Scout-17B-16E-Instruct-Q8_0-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84d1c69c73fc93acfbf388d58c1bc46f5a61d6a6076a0e87046d9c7aab8ebfb
3
+ size 14797624544
UD-Q3_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q3_K_XL.gguf-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df95155280eb57fff951ed3fd3daad9399261437fbe627bbfab59180788436b4
3
+ size 29891489120
UD-Q3_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q3_K_XL.gguf-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2738062a45d25ec5b2f7722a331cce967bdc3211ed144f4bb442fa8d1cc1e8b
3
+ size 23039178592
UD-Q4_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL.gguf-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:019f25b4ca25f14bc142707711b84423ac854108878d5da73627559ddb2e3611
3
+ size 39991695040
UD-Q4_K_XL/Llama-4-Scout-17B-16E-Instruct-UD-Q4_K_XL.gguf-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4643674cce752f61875b5d164ff8d6ff34f361dded6cedfe93308607642b3a65
3
+ size 25627725312
config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Llama4ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 200080,
6
+ "eoi_token_index": 200081,
7
+ "image_token_index": 200092,
8
+ "model_type": "llama4",
9
+ "text_config": {
10
+ "_attn_implementation_autoset": true,
11
+ "attention_bias": false,
12
+ "attention_chunk_size": 8192,
13
+ "attention_dropout": 0.0,
14
+ "bos_token_id": 200000,
15
+ "eos_token_id": [
16
+ 200001,
17
+ 200007,
18
+ 200008
19
+ ],
20
+ "for_llm_compressor": false,
21
+ "head_dim": 128,
22
+ "hidden_act": "silu",
23
+ "hidden_size": 5120,
24
+ "initializer_range": 0.02,
25
+ "interleave_moe_layer_step": 1,
26
+ "intermediate_size": 8192,
27
+ "intermediate_size_mlp": 16384,
28
+ "max_position_embeddings": 10485760,
29
+ "model_type": "llama4_text",
30
+ "no_rope_layers": [],
31
+ "num_attention_heads": 40,
32
+ "num_experts_per_tok": 1,
33
+ "num_hidden_layers": 48,
34
+ "num_key_value_heads": 8,
35
+ "num_local_experts": 16,
36
+ "output_router_logits": false,
37
+ "pad_token_id": 200018,
38
+ "rms_norm_eps": 1e-05,
39
+ "rope_scaling": {
40
+ "factor": 8.0,
41
+ "high_freq_factor": 4.0,
42
+ "low_freq_factor": 1.0,
43
+ "original_max_position_embeddings": 8192,
44
+ "rope_type": "llama3"
45
+ },
46
+ "rope_theta": 500000.0,
47
+ "router_aux_loss_coef": 0.001,
48
+ "router_jitter_noise": 0.0,
49
+ "torch_dtype": "bfloat16",
50
+ "use_cache": true,
51
+ "use_qk_norm": true,
52
+ "vocab_size": 202048
53
+ },
54
+ "torch_dtype": "bfloat16",
55
+ "transformers_version": "4.51.0.dev0",
56
+ "vision_config": {
57
+ "_attn_implementation_autoset": true,
58
+ "attention_dropout": 0.0,
59
+ "hidden_act": "gelu",
60
+ "hidden_size": 1408,
61
+ "image_size": 336,
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 5632,
64
+ "model_type": "llama4_vision_model",
65
+ "multi_modal_projector_bias": false,
66
+ "norm_eps": 1e-05,
67
+ "num_attention_heads": 16,
68
+ "num_channels": 3,
69
+ "num_hidden_layers": 34,
70
+ "patch_size": 14,
71
+ "pixel_shuffle_ratio": 0.5,
72
+ "projector_dropout": 0.0,
73
+ "projector_input_dim": 4096,
74
+ "projector_output_dim": 4096,
75
+ "rope_theta": 10000,
76
+ "vision_feature_layer": -1,
77
+ "vision_feature_select_strategy": "default",
78
+ "vision_output_dim": 4096
79
+ }
80
+ }
imatrix.dat ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9577125fe0fcba6c67984a2aaa8359d61d490f3f7ad5439a932b27813f353aef
3
+ size 65096578