MikeRoz commited on
Commit
aba7baf
1 Parent(s): a7c4657

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ ---
4
+ # Join our Discord! https://discord.gg/Nbv9pQ88Xb
5
+ ## 2500+ members strong 💪 Now with more channels! A hub for users and makers alike!
6
+ ---
7
+
8
+ # Lazarus 2407 100B 🌖
9
+
10
+ > To the brave men and women who gave their lives so we could begin again.
11
+
12
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/99LemcIuW0c2qWac-qDg8.png)
13
+
14
+ # Links
15
+
16
+ - Original: https://huggingface.co/TheDrummer/Lazarus-2407-100B
17
+ - GGUF: https://huggingface.co/TheDrummer/Lazarus-2407-100B-GGUF
18
+ - iMatrix (Recommended): https://huggingface.co/bartowski/Lazarus-2407-100B
19
+
20
+ ## A pruned version of Mistral Large 2407 123B
21
+
22
+ - Theory: https://arxiv.org/abs/2403.17887
23
+ - Practice: https://github.com/arcee-ai/PruneMe
24
+
25
+ ```yaml
26
+ slices:
27
+ - sources:
28
+ - model: ./largestral
29
+ layer_range: [0, 54]
30
+ - sources:
31
+ - model: ./largestral
32
+ layer_range: [70,88]
33
+ merge_method: passthrough
34
+ dtype: bfloat16
35
+ ```
36
+
37
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/gNsvay6NpaVKazg-nYSoL.png)
38
+
39
+ ```
40
+ block_start,block_end,average_distance
41
+ 1,17,0.42018115234375
42
+ 2,18,0.40477392578125
43
+ 3,19,0.3955498046875
44
+ 4,20,0.39202392578125
45
+ 5,21,0.38614453125
46
+ 6,22,0.380365234375
47
+ 7,23,0.37550830078125
48
+ 8,24,0.36995361328125
49
+ 9,25,0.36802099609375
50
+ 10,26,0.36337158203125
51
+ 11,27,0.3570400390625
52
+ 12,28,0.35895654296875
53
+ 13,29,0.360716796875
54
+ 14,30,0.36415234375
55
+ 15,31,0.3656328125
56
+ 16,32,0.3657451171875
57
+ 17,33,0.36321337890625
58
+ 18,34,0.36210791015625
59
+ 19,35,0.3613828125
60
+ 20,36,0.36101806640625
61
+ 21,37,0.36395361328125
62
+ 22,38,0.36294921875
63
+ 23,39,0.36490673828125
64
+ 24,40,0.36392578125
65
+ 25,41,0.3616650390625
66
+ 26,42,0.360994140625
67
+ 27,43,0.357458984375
68
+ 28,44,0.35728759765625
69
+ 29,45,0.35514013671875
70
+ 30,46,0.35244140625
71
+ 31,47,0.34866162109375
72
+ 32,48,0.3489375
73
+ 33,49,0.3480888671875
74
+ 34,50,0.34322607421875
75
+ 35,51,0.3366806640625
76
+ 36,52,0.331208984375
77
+ 37,53,0.31834423828125
78
+ 38,54,0.30483203125
79
+ 39,55,0.29027587890625
80
+ 40,56,0.2789296875
81
+ 41,57,0.263868408203125
82
+ 42,58,0.25043017578125
83
+ 43,59,0.23816162109375
84
+ 44,60,0.223565185546875
85
+ 45,61,0.216619140625
86
+ 46,62,0.212794189453125
87
+ 47,63,0.205733642578125
88
+ 48,64,0.200558837890625
89
+ 49,65,0.196917236328125
90
+ 50,66,0.1951201171875
91
+ 51,67,0.192659423828125
92
+ 52,68,0.191610595703125
93
+ 53,69,0.1910341796875
94
+ 54,70,0.190966064453125
95
+ 55,71,0.1920712890625
96
+ 56,72,0.1935439453125
97
+ 57,73,0.1973837890625
98
+ 58,74,0.200970703125
99
+ 59,75,0.205339111328125
100
+ 60,76,0.216475341796875
101
+ 61,77,0.218605224609375
102
+ 62,78,0.22363916015625
103
+ 63,79,0.229986083984375
104
+ 64,80,0.23776171875
105
+ 65,81,0.24455322265625
106
+ 66,82,0.2542783203125
107
+ 67,83,0.2635498046875
108
+ 68,84,0.27629443359375
109
+ 69,85,0.29324267578125
110
+ 70,86,0.32201220703125
111
+ 71,87,0.36908154296875
112
+ 72,88,0.4007587890625
113
+ ```
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./largestral",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 12288,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 131072,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 96,
17
+ "num_hidden_layers": 72,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.46.3",
25
+ "use_cache": true,
26
+ "vocab_size": 32768,
27
+ "quantization_config": {
28
+ "quant_method": "exl2",
29
+ "version": "0.2.3",
30
+ "bits": 2.25,
31
+ "head_bits": 6,
32
+ "calibration": {
33
+ "rows": 115,
34
+ "length": 2048,
35
+ "dataset": "(default)"
36
+ }
37
+ }
38
+ }
huggingface-metadata.txt ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ url: https://huggingface.co/TheDrummer/Lazarus-2407-100B
2
+ branch: main
3
+ download date: 2024-12-06 03:07:18
4
+ sha256sum:
5
+ 1fd03ff284e4324bd3a31511d1bbaab644cc30dff53db64c37acbcac7f91769c model-00001-of-00042.safetensors
6
+ 5b95ba9950ba6d154a2d4d8379a7b0a487770b4d1b0809f1fd76f554a58fec90 model-00002-of-00042.safetensors
7
+ f723328d474667d0128c4dae515e96bc354978ec5e5e0a131e0e2144a7205cdd model-00003-of-00042.safetensors
8
+ 5df0b636a686027a11922d0a5265982869dd1a6d99dd216e926e719e778046d0 model-00004-of-00042.safetensors
9
+ 26079a878ffb3be350f2f3be6dcc2b3c8b94a809fbc1055878d6bb16ea5e38cd model-00005-of-00042.safetensors
10
+ e6ac509de863f43d57058123802c886b765d1de504a5704a71150016d470b6c1 model-00006-of-00042.safetensors
11
+ f1445451312364a818b8d00f22e0983d4a4a708f7e64d1651f43f2770c8ad281 model-00007-of-00042.safetensors
12
+ 6e6f38d4d0512e7e044d86216d455cefaf4024183ef0cc8268ab2ed07c69ec2c model-00008-of-00042.safetensors
13
+ 7084ebd6036043235dd8a4a4f61e85f00919fa343cd44abc4f2ded7ed1937bf6 model-00009-of-00042.safetensors
14
+ 37402d9de86f9774b1f6e8c94ba931a33af1e9d34a0d4d9e65d6ce7badabf06f model-00010-of-00042.safetensors
15
+ a292a527dd49a1191477ca9878ec626be03acd8ffcdc961ef416d461588b5532 model-00011-of-00042.safetensors
16
+ 3f78ca4dfbf798d916ece12866a4a692fa8be0808bd4e5baba864d375273a536 model-00012-of-00042.safetensors
17
+ 617a866352025f1056601bf416c9011318f19bcd8395131f5258f239b978f881 model-00013-of-00042.safetensors
18
+ 8f3b45ee06ddb1fcf6efe798413b2be4387dd18355c7470b9010d0626a027e66 model-00014-of-00042.safetensors
19
+ fee053dfe5e767594eaaa306257c81413091b81a9d16f65f148bdeff214fd3f8 model-00015-of-00042.safetensors
20
+ f01feebcd156a59cd271ceb70db8c2e278b04d40931520842822a5f039b3d4e0 model-00016-of-00042.safetensors
21
+ 59bcbf4ff95cbc81bb37c89bbaff63dc9a38aa8d9bb6129f6322a77e86b094af model-00017-of-00042.safetensors
22
+ 147aa39b3c962b8c3b1b73f2128e36940d99c01e763afc3d757f7fa0b8fc6315 model-00018-of-00042.safetensors
23
+ eb07a3afb493bf99c13a6fa57faebacb441eb9f0360e499cb68f42a8b389a92c model-00019-of-00042.safetensors
24
+ 470c827d90faaba2494a66097a188b4301a96a69a18a4ef0ecfdb6d9c264fa5d model-00020-of-00042.safetensors
25
+ 1c7743d28ff7a220e9bfaea6391933f54f7df74b5fd1af228f8706fd6c010a2f model-00021-of-00042.safetensors
26
+ b6f89b01006b9ec7d89e4ff8c3e7b3d28dbdba56c1aeb920d6896dbfabe867ff model-00022-of-00042.safetensors
27
+ 7ccb7a480ffb48d1b98944c6b8e8acf3a639b6a900970c66127e9f683505c455 model-00023-of-00042.safetensors
28
+ 34ba6f2e8e813e11b61a8e23eb509acb01c9fc58865afff33ce51f2f21e7a298 model-00024-of-00042.safetensors
29
+ d2e44a26af05c606e72af0bd8ec64e805de1af850a047cd4d5e449870ec31df4 model-00025-of-00042.safetensors
30
+ 357a8c44ed120b7818e232833ee03c5ed2246d7d15c26eaa3689b205255cdf59 model-00026-of-00042.safetensors
31
+ f7fb3e1e017c583ffb055694d47d4667ebbb83e504fe9eef236d2e07778f0225 model-00027-of-00042.safetensors
32
+ c2d1d588d58e6df0372b37731f2af1d99018690dad65250f0eadb0ce990e3647 model-00028-of-00042.safetensors
33
+ f266d30470d820efca4001cab2f79291f0368347c200eb68e8750fb5bad93b5f model-00029-of-00042.safetensors
34
+ 4d6b7a53e4350c55fb11cb82ffacd7f988c363040f23235da3b1b6e6b7c93c6e model-00030-of-00042.safetensors
35
+ 120a01b8ba2a250f158ce543fcc00d79ebe6e967c2b196b8067f9156e3065b60 model-00031-of-00042.safetensors
36
+ a951a4eb571e45279ce61fe2d385a7ab27d83ffe2ae5c42bd3bf81fd5939c926 model-00032-of-00042.safetensors
37
+ bf96bfe477ada0c1eb8e0e520a759ce9444ff8f7fc52d4da3eb7ab25b2339b39 model-00033-of-00042.safetensors
38
+ ac09d38c846528d0595b568da4fd00e6326487df01097ad1e2f6340a58f86894 model-00034-of-00042.safetensors
39
+ c09bc65f20cf5625454cf36d4bc840cbbf126e7d55576d1da3132b5fb8f4b8ae model-00035-of-00042.safetensors
40
+ 8a96da07c5f47875d37214173db9cdf6039239b35d4f7e27ef4a7b15e1713720 model-00036-of-00042.safetensors
41
+ f473e9d44ba0602bcf99f2e6f8aeed3704bed162e179e0cc7fc5c07be94b53cd model-00037-of-00042.safetensors
42
+ 97df327fe66e618ede014bfa59571e74538c8e952e0c9fdf53e95f3b6ef2a869 model-00038-of-00042.safetensors
43
+ f6d4be47ed0d718953e227f65b358383f8faff8e927487c36c1cf646308d4c7a model-00039-of-00042.safetensors
44
+ 26f5950fa2eb49fd8ca3af4b28e2b86d783242377cb782e493dcd7dff75b58a7 model-00040-of-00042.safetensors
45
+ 10058b8f5aad558fa467b156c2133a8404d3738ee5362041269f99f61831a0b5 model-00041-of-00042.safetensors
46
+ 11ef423990873bd8cc3dfd6bd56d5ae1a689bf6af9351bf9253d7a450f747e8a model-00042-of-00042.safetensors
47
+ 59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06 tokenizer.model
measurement.json ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.5.2", "total_size": 200927502336}, "weight_map": {"lm_head.weight": "model-00001-of-00042.safetensors", "model.embed_tokens.weight": "model-00001-of-00042.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00042.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00042.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00042.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00042.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00042.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00042.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00042.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00042.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00042.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00042.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00042.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00042.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00042.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00042.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00042.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00042.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00042.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00042.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00042.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00042.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00042.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00042.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00042.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00042.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00042.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00042.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00042.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00042.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00042.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00042.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00042.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00042.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00042.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00042.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00042.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00042.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00042.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00042.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00042.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00042.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00042.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00042.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00042.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00042.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00042.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00042.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00042.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00042.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00042.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00042.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00042.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00042.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00042.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00042.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00042.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00042.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00042.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00042.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00042.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00042.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00042.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00042.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00042.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00042.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00042.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00042.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00042.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00042.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00042.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00042.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00042.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00042.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00042.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00042.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00042.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00042.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00042.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00042.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00042.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00042.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00042.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00042.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00042.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00042.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00042.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00042.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00042.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00042.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00042.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00042.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00042.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00042.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00042.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00042.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00042.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00042.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00042.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00042.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00042.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00042.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00042.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00042.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00042.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00042.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00042.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00042.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00042.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00042.safetensors", "model.layers.2.input_layernorm.weight": "model-00008-of-00042.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00008-of-00042.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00008-of-00042.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00008-of-00042.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00008-of-00042.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00008-of-00042.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00008-of-00042.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00008-of-00042.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00008-of-00042.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00042.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00042.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00042.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00042.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00042.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00042.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00042.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00042.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00042.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00042.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00009-of-00042.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00042.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00009-of-00042.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00042.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00042.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00042.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00042.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00042.safetensors", "model.layers.22.input_layernorm.weight": "model-00009-of-00042.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00010-of-00042.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00042.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00010-of-00042.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00042.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00042.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00042.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00042.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00042.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00042.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00010-of-00042.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00042.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00010-of-00042.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00042.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00042.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00042.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00042.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00042.safetensors", "model.layers.24.input_layernorm.weight": "model-00011-of-00042.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00011-of-00042.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00042.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00011-of-00042.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00042.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00042.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00042.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00042.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00042.safetensors", "model.layers.25.input_layernorm.weight": "model-00011-of-00042.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00011-of-00042.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00042.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00012-of-00042.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00042.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00042.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00042.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00042.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00042.safetensors", "model.layers.26.input_layernorm.weight": "model-00012-of-00042.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00012-of-00042.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00042.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00012-of-00042.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00042.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00042.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00042.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00042.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00042.safetensors", "model.layers.27.input_layernorm.weight": "model-00012-of-00042.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00012-of-00042.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00042.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00013-of-00042.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00042.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00042.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00042.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00042.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00042.safetensors", "model.layers.28.input_layernorm.weight": "model-00013-of-00042.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00013-of-00042.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00042.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00013-of-00042.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00042.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00042.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00042.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00042.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00042.safetensors", "model.layers.29.input_layernorm.weight": "model-00013-of-00042.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00014-of-00042.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00042.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00014-of-00042.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00042.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00042.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00042.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00042.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00042.safetensors", "model.layers.3.input_layernorm.weight": "model-00014-of-00042.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00014-of-00042.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00014-of-00042.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00014-of-00042.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00014-of-00042.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00014-of-00042.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00015-of-00042.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00015-of-00042.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00015-of-00042.safetensors", "model.layers.30.input_layernorm.weight": "model-00015-of-00042.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00015-of-00042.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00015-of-00042.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00015-of-00042.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00042.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00042.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00042.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00042.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00042.safetensors", "model.layers.31.input_layernorm.weight": "model-00015-of-00042.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00015-of-00042.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00042.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00016-of-00042.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00016-of-00042.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00016-of-00042.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00016-of-00042.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00016-of-00042.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00042.safetensors", "model.layers.32.input_layernorm.weight": "model-00016-of-00042.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00016-of-00042.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00016-of-00042.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00016-of-00042.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00016-of-00042.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00016-of-00042.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00016-of-00042.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00016-of-00042.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00016-of-00042.safetensors", "model.layers.33.input_layernorm.weight": "model-00016-of-00042.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00016-of-00042.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00017-of-00042.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00017-of-00042.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00017-of-00042.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00017-of-00042.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00017-of-00042.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00017-of-00042.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00017-of-00042.safetensors", "model.layers.34.input_layernorm.weight": "model-00017-of-00042.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00017-of-00042.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00017-of-00042.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00017-of-00042.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00017-of-00042.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00017-of-00042.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00017-of-00042.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00017-of-00042.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00017-of-00042.safetensors", "model.layers.35.input_layernorm.weight": "model-00017-of-00042.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00018-of-00042.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00018-of-00042.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00018-of-00042.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00018-of-00042.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00018-of-00042.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00018-of-00042.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00042.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00018-of-00042.safetensors", "model.layers.36.input_layernorm.weight": "model-00018-of-00042.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00018-of-00042.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00018-of-00042.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00018-of-00042.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00042.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00018-of-00042.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00042.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00019-of-00042.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00042.safetensors", "model.layers.37.input_layernorm.weight": "model-00019-of-00042.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00019-of-00042.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00019-of-00042.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00019-of-00042.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00019-of-00042.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00042.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00019-of-00042.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00019-of-00042.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00042.safetensors", "model.layers.38.input_layernorm.weight": "model-00019-of-00042.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00019-of-00042.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00019-of-00042.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00020-of-00042.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00020-of-00042.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00020-of-00042.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00042.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00042.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00042.safetensors", "model.layers.39.input_layernorm.weight": "model-00020-of-00042.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00020-of-00042.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00020-of-00042.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00020-of-00042.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00020-of-00042.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00020-of-00042.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00042.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00020-of-00042.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00020-of-00042.safetensors", "model.layers.4.input_layernorm.weight": "model-00020-of-00042.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00020-of-00042.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00021-of-00042.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00021-of-00042.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00021-of-00042.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00021-of-00042.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00021-of-00042.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00021-of-00042.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00021-of-00042.safetensors", "model.layers.40.input_layernorm.weight": "model-00021-of-00042.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00021-of-00042.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00021-of-00042.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00021-of-00042.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00021-of-00042.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00021-of-00042.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00021-of-00042.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00021-of-00042.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00021-of-00042.safetensors", "model.layers.41.input_layernorm.weight": "model-00021-of-00042.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00022-of-00042.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00022-of-00042.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00022-of-00042.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00022-of-00042.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00022-of-00042.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00022-of-00042.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00022-of-00042.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00022-of-00042.safetensors", "model.layers.42.input_layernorm.weight": "model-00022-of-00042.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00022-of-00042.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00022-of-00042.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00022-of-00042.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00022-of-00042.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00022-of-00042.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00023-of-00042.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00023-of-00042.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00023-of-00042.safetensors", "model.layers.43.input_layernorm.weight": "model-00023-of-00042.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00023-of-00042.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00023-of-00042.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00023-of-00042.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00023-of-00042.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00023-of-00042.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00023-of-00042.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00023-of-00042.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00023-of-00042.safetensors", "model.layers.44.input_layernorm.weight": "model-00023-of-00042.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00023-of-00042.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00023-of-00042.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00024-of-00042.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00024-of-00042.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00024-of-00042.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00024-of-00042.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00024-of-00042.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00024-of-00042.safetensors", "model.layers.45.input_layernorm.weight": "model-00024-of-00042.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00024-of-00042.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00024-of-00042.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00024-of-00042.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00024-of-00042.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00024-of-00042.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00024-of-00042.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00024-of-00042.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00024-of-00042.safetensors", "model.layers.46.input_layernorm.weight": "model-00024-of-00042.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00024-of-00042.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00025-of-00042.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00025-of-00042.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00025-of-00042.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00025-of-00042.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00025-of-00042.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00025-of-00042.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00025-of-00042.safetensors", "model.layers.47.input_layernorm.weight": "model-00025-of-00042.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00025-of-00042.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00025-of-00042.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00025-of-00042.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00025-of-00042.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00025-of-00042.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00025-of-00042.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00025-of-00042.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00025-of-00042.safetensors", "model.layers.48.input_layernorm.weight": "model-00025-of-00042.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00026-of-00042.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00026-of-00042.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00026-of-00042.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00026-of-00042.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00026-of-00042.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00026-of-00042.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00026-of-00042.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00026-of-00042.safetensors", "model.layers.49.input_layernorm.weight": "model-00026-of-00042.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00026-of-00042.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00026-of-00042.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00026-of-00042.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00026-of-00042.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00026-of-00042.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00027-of-00042.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00027-of-00042.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00027-of-00042.safetensors", "model.layers.5.input_layernorm.weight": "model-00027-of-00042.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00027-of-00042.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00027-of-00042.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00027-of-00042.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00027-of-00042.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00027-of-00042.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00027-of-00042.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00027-of-00042.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00027-of-00042.safetensors", "model.layers.50.input_layernorm.weight": "model-00027-of-00042.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00027-of-00042.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00027-of-00042.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00028-of-00042.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00028-of-00042.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00028-of-00042.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00028-of-00042.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00028-of-00042.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00028-of-00042.safetensors", "model.layers.51.input_layernorm.weight": "model-00028-of-00042.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00028-of-00042.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00028-of-00042.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00028-of-00042.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00028-of-00042.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00028-of-00042.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00028-of-00042.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00028-of-00042.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00028-of-00042.safetensors", "model.layers.52.input_layernorm.weight": "model-00028-of-00042.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00028-of-00042.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00029-of-00042.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00029-of-00042.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00029-of-00042.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00029-of-00042.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00029-of-00042.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00029-of-00042.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00029-of-00042.safetensors", "model.layers.53.input_layernorm.weight": "model-00029-of-00042.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00029-of-00042.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00029-of-00042.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00029-of-00042.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00029-of-00042.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00029-of-00042.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00029-of-00042.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00029-of-00042.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00029-of-00042.safetensors", "model.layers.6.input_layernorm.weight": "model-00029-of-00042.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00030-of-00042.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00030-of-00042.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00030-of-00042.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00030-of-00042.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00030-of-00042.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00030-of-00042.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00030-of-00042.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00030-of-00042.safetensors", "model.layers.7.input_layernorm.weight": "model-00030-of-00042.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00030-of-00042.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00030-of-00042.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00030-of-00042.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00030-of-00042.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00030-of-00042.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00031-of-00042.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00031-of-00042.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00031-of-00042.safetensors", "model.layers.54.input_layernorm.weight": "model-00031-of-00042.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00031-of-00042.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00031-of-00042.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00031-of-00042.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00031-of-00042.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00031-of-00042.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00031-of-00042.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00031-of-00042.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00031-of-00042.safetensors", "model.layers.55.input_layernorm.weight": "model-00031-of-00042.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00031-of-00042.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00031-of-00042.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00032-of-00042.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00032-of-00042.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00032-of-00042.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00032-of-00042.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00032-of-00042.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00032-of-00042.safetensors", "model.layers.56.input_layernorm.weight": "model-00032-of-00042.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00032-of-00042.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00032-of-00042.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00032-of-00042.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00032-of-00042.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00032-of-00042.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00032-of-00042.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00032-of-00042.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00032-of-00042.safetensors", "model.layers.57.input_layernorm.weight": "model-00032-of-00042.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00032-of-00042.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00033-of-00042.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00033-of-00042.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00033-of-00042.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00033-of-00042.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00033-of-00042.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00033-of-00042.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00033-of-00042.safetensors", "model.layers.58.input_layernorm.weight": "model-00033-of-00042.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00033-of-00042.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00033-of-00042.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00033-of-00042.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00033-of-00042.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00033-of-00042.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00033-of-00042.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00033-of-00042.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00033-of-00042.safetensors", "model.layers.59.input_layernorm.weight": "model-00033-of-00042.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00034-of-00042.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00034-of-00042.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00034-of-00042.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00034-of-00042.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00034-of-00042.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00034-of-00042.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00034-of-00042.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00034-of-00042.safetensors", "model.layers.60.input_layernorm.weight": "model-00034-of-00042.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00034-of-00042.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00034-of-00042.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00034-of-00042.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00034-of-00042.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00034-of-00042.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00035-of-00042.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00035-of-00042.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00035-of-00042.safetensors", "model.layers.61.input_layernorm.weight": "model-00035-of-00042.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00035-of-00042.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00035-of-00042.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00035-of-00042.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00035-of-00042.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00035-of-00042.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00035-of-00042.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00035-of-00042.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00035-of-00042.safetensors", "model.layers.62.input_layernorm.weight": "model-00035-of-00042.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00035-of-00042.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00035-of-00042.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00036-of-00042.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00036-of-00042.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00036-of-00042.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00036-of-00042.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00036-of-00042.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00036-of-00042.safetensors", "model.layers.63.input_layernorm.weight": "model-00036-of-00042.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00036-of-00042.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00036-of-00042.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00036-of-00042.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00036-of-00042.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00036-of-00042.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00036-of-00042.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00036-of-00042.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00036-of-00042.safetensors", "model.layers.8.input_layernorm.weight": "model-00036-of-00042.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00036-of-00042.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00037-of-00042.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00037-of-00042.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00037-of-00042.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00037-of-00042.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00037-of-00042.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00037-of-00042.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00037-of-00042.safetensors", "model.layers.64.input_layernorm.weight": "model-00037-of-00042.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00037-of-00042.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00037-of-00042.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00037-of-00042.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00037-of-00042.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00037-of-00042.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00037-of-00042.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00037-of-00042.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00037-of-00042.safetensors", "model.layers.65.input_layernorm.weight": "model-00037-of-00042.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00038-of-00042.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00038-of-00042.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00038-of-00042.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00038-of-00042.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00038-of-00042.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00038-of-00042.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00038-of-00042.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00038-of-00042.safetensors", "model.layers.66.input_layernorm.weight": "model-00038-of-00042.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00038-of-00042.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00038-of-00042.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00038-of-00042.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00038-of-00042.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00038-of-00042.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00039-of-00042.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00039-of-00042.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00039-of-00042.safetensors", "model.layers.67.input_layernorm.weight": "model-00039-of-00042.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00039-of-00042.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00039-of-00042.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00039-of-00042.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00039-of-00042.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00039-of-00042.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00039-of-00042.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00039-of-00042.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00039-of-00042.safetensors", "model.layers.68.input_layernorm.weight": "model-00039-of-00042.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00039-of-00042.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00039-of-00042.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00040-of-00042.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00040-of-00042.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00040-of-00042.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00040-of-00042.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00040-of-00042.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00040-of-00042.safetensors", "model.layers.69.input_layernorm.weight": "model-00040-of-00042.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00040-of-00042.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00040-of-00042.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00040-of-00042.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00040-of-00042.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00040-of-00042.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00040-of-00042.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00040-of-00042.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00040-of-00042.safetensors", "model.layers.70.input_layernorm.weight": "model-00040-of-00042.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00040-of-00042.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00041-of-00042.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00041-of-00042.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00041-of-00042.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00041-of-00042.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00041-of-00042.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00041-of-00042.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00041-of-00042.safetensors", "model.layers.71.input_layernorm.weight": "model-00041-of-00042.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00041-of-00042.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00041-of-00042.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00041-of-00042.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00041-of-00042.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00041-of-00042.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00041-of-00042.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00041-of-00042.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00041-of-00042.safetensors", "model.layers.9.input_layernorm.weight": "model-00041-of-00042.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00042-of-00042.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00042-of-00042.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00042-of-00042.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00042-of-00042.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00042-of-00042.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00042-of-00042.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00042-of-00042.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00042-of-00042.safetensors", "model.norm.weight": "model-00042-of-00042.safetensors"}}
output-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0da6fb0560223fd4fa8d5c5deef5deefccd6f3ed1b6ae95a12aa367a7d12ef69
3
+ size 8578319608
output-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c3ed57f64d7710daff8d749934d86161612eb0a672f1630bf30bd96e192b312
3
+ size 8520821374
output-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a5b76456900e31dfae251e8efab2f0886138e65a4bb09f4f825d5b82d2490d7
3
+ size 8573093508
output-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0734790f350260d65392b689ea2e614ff33a72ad92d85c62cf3f2da3fbc6684
3
+ size 3483774110
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
3
+ size 587583
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff