danielhanchen commited on
Commit
5020118
·
verified ·
1 Parent(s): 7ae7ee3

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,21 @@ 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
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00006-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
37
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00017-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
38
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00014-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
39
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00003-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
40
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00013-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
41
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00015-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
42
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00011-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
43
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00010-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
44
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00002-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
45
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00008-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
46
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00007-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
47
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00004-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
48
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00009-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
49
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00001-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
50
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00012-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
51
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00018-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
52
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00016-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
53
+ BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00005-of-00018.gguf filter=lfs diff=lfs merge=lfs -text
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00001-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:747d3c4885e0086966ce02d12ee26a4d53f17ddb8d5ce63a753a9e0ab1c656ce
3
+ size 46166870080
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00002-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3110010fb2ec2739dd1de27183e64f60f4f252275122b0e6aaeca7b088f54fa
3
+ size 42949673376
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00003-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc3fcb851cb191133c357030aaa58b91c4dcbdeee53c6d2d957b7524367c1df9
3
+ size 42949673376
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00004-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77bc9634f9e547b763a1dcae424163edf9f197cb4a0c424064ee3b5b131acba3
3
+ size 42949673376
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00005-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7960a0f43ac664ac8e2e2ca67a91190c8edf60032f617e38a6b19e855ea03f62
3
+ size 47943931840
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00006-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13b1e40154895979a30c2ca28f44a40a946667fb30f31a4d88fdbb4f2e98d5a0
3
+ size 42949673376
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00007-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d27f62dfcc2af38c430aaab8b8dbfc27d13de9f02c91ac4694a5a07d2b9b53e9
3
+ size 42949673376
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00008-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05e168b65bd75dac39941349bb7aded581a926e9904bbfc60fd5bef2684649f9
3
+ size 42949673376
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00009-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a51a6db7957cd9e5ffebfe8c579296ec8a6e83b517f6b64a1a0a9e33bf3b97a
3
+ size 47922960288
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00010-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c77a1a6a4a8fab46fc1ce16b86e6dfd4feb16843a313bd3c24220d5b90b9863
3
+ size 42949673376
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00011-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e5cca151d8dbeca92a90410a460d9c063d86c9e358661faee0e7346bab3fd5e
3
+ size 42949673376
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00012-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78875927ab39090918819661c3b72af419701ad444e61e4418ba57948039e96e
3
+ size 47912433568
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00013-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d801bd313446694487aa9abdcda925e7341111ddbcdcf628ea3c2bc644fb0442
3
+ size 42949673376
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00014-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d283438bfe01cce20db677b9227d85e1e41f79a6113ecf65da8cdf9ed4b05b2c
3
+ size 42949673376
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00015-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e57e52ac7b348ef13369760836ba570a42acb4e86052f9232089e4dbc1e35c0
3
+ size 42949673376
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00016-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bc41417430249d157028345d016d2386d1e761aad6885128c70f9bbecf58506
3
+ size 47912474624
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00017-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9d16895bcbc96ee4551f06a74f052a35db2032ed66ee438a5721314e00f5280
3
+ size 42949673376
BF16/Llama-4-Maverick-17B-128E-Instruct-BF16-00018-of-00018.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02f26173164408cbaab89ad05be2f5609e8c384200ebf973255207ecc960b09
3
+ size 48214491296
config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2,
26
+ "intermediate_size": 8192,
27
+ "intermediate_size_mlp": 16384,
28
+ "max_position_embeddings": 1048576,
29
+ "model_type": "llama4_text",
30
+ "num_attention_heads": 40,
31
+ "num_experts_per_tok": 1,
32
+ "num_hidden_layers": 48,
33
+ "num_key_value_heads": 8,
34
+ "num_local_experts": 128,
35
+ "output_router_logits": false,
36
+ "pad_token_id": 200018,
37
+ "rms_norm_eps": 1e-05,
38
+ "rope_scaling": null,
39
+ "rope_theta": 500000.0,
40
+ "router_aux_loss_coef": 0.001,
41
+ "router_jitter_noise": 0.0,
42
+ "torch_dtype": "bfloat16",
43
+ "use_cache": true,
44
+ "use_qk_norm": false,
45
+ "vocab_size": 202048
46
+ },
47
+ "torch_dtype": "bfloat16",
48
+ "transformers_version": "4.51.0.dev0",
49
+ "vision_config": {
50
+ "_attn_implementation_autoset": true,
51
+ "attention_dropout": 0.0,
52
+ "hidden_act": "gelu",
53
+ "hidden_size": 1408,
54
+ "image_size": 336,
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 5632,
57
+ "model_type": "llama4_vision_model",
58
+ "multi_modal_projector_bias": false,
59
+ "norm_eps": 1e-05,
60
+ "num_attention_heads": 16,
61
+ "num_channels": 3,
62
+ "num_hidden_layers": 34,
63
+ "patch_size": 14,
64
+ "pixel_shuffle_ratio": 0.5,
65
+ "projector_dropout": 0.0,
66
+ "projector_input_dim": 4096,
67
+ "projector_output_dim": 4096,
68
+ "rope_theta": 10000,
69
+ "vision_feature_layer": -1,
70
+ "vision_feature_select_strategy": "default",
71
+ "vision_output_dim": 4096
72
+ }
73
+ }