Clocksmith commited on
Commit
a887e84
·
verified ·
1 Parent(s): e3940a5

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
manifest.json ADDED
@@ -0,0 +1,3200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "modelId": "dcc83ea841ab6100d6b47a070329e1ba4cf78752",
4
+ "modelType": "transformer",
5
+ "architecture": "Gemma3ForCausalLM",
6
+ "quantization": "Q4_K_M",
7
+ "hashAlgorithm": "sha256",
8
+ "config": {
9
+ "architectures": [
10
+ "Gemma3ForCausalLM"
11
+ ],
12
+ "attention_bias": false,
13
+ "attention_dropout": 0,
14
+ "attn_logit_softcapping": null,
15
+ "bos_token_id": 2,
16
+ "cache_implementation": "hybrid",
17
+ "eos_token_id": [
18
+ 1,
19
+ 106
20
+ ],
21
+ "final_logit_softcapping": null,
22
+ "head_dim": 256,
23
+ "hidden_activation": "gelu_pytorch_tanh",
24
+ "hidden_size": 1152,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 6912,
27
+ "max_position_embeddings": 32768,
28
+ "model_type": "gemma3_text",
29
+ "num_attention_heads": 4,
30
+ "num_hidden_layers": 26,
31
+ "num_key_value_heads": 1,
32
+ "pad_token_id": 0,
33
+ "query_pre_attn_scalar": 256,
34
+ "rms_norm_eps": 0.000001,
35
+ "rope_local_base_freq": 10000,
36
+ "rope_scaling": null,
37
+ "rope_theta": 1000000,
38
+ "sliding_window": 512,
39
+ "sliding_window_pattern": 6,
40
+ "torch_dtype": "bfloat16",
41
+ "transformers_version": "4.50.0.dev0",
42
+ "use_cache": true,
43
+ "vocab_size": 262144
44
+ },
45
+ "tokenizer": {
46
+ "type": "huggingface",
47
+ "file": "tokenizer.json",
48
+ "vocabSize": 262144,
49
+ "tokenizerType": "bpe"
50
+ },
51
+ "shards": [
52
+ {
53
+ "index": 0,
54
+ "fileName": "shard_00000.bin",
55
+ "size": 67108864,
56
+ "hash": "ce0aa445c0342d8d331dcf0ea12420ec4d958f2aa0f9d03b0d11549afd51c51f",
57
+ "hashAlgorithm": "sha256"
58
+ },
59
+ {
60
+ "index": 1,
61
+ "fileName": "shard_00001.bin",
62
+ "size": 67108864,
63
+ "hash": "139db6c33ea369fa5089fbbdbece91639d7be9abdb4330d4b6f6bbb69bd8eba8",
64
+ "hashAlgorithm": "sha256"
65
+ },
66
+ {
67
+ "index": 2,
68
+ "fileName": "shard_00002.bin",
69
+ "size": 67108864,
70
+ "hash": "23bc7a67086efe16a19f78880349ed9a5c317765455e70a1e58a00876ab2e0e0",
71
+ "hashAlgorithm": "sha256"
72
+ },
73
+ {
74
+ "index": 3,
75
+ "fileName": "shard_00003.bin",
76
+ "size": 67108864,
77
+ "hash": "a88c622d0c6e726c6c0c3e37397295073027ff0c330c1cc5d44da39c71c8cbf4",
78
+ "hashAlgorithm": "sha256"
79
+ },
80
+ {
81
+ "index": 4,
82
+ "fileName": "shard_00004.bin",
83
+ "size": 67108864,
84
+ "hash": "98c6a4d591d7f5877a8d973e7680ff4969edeb8e5f9cbebbf944ddd7476b1ac4",
85
+ "hashAlgorithm": "sha256"
86
+ },
87
+ {
88
+ "index": 5,
89
+ "fileName": "shard_00005.bin",
90
+ "size": 67108864,
91
+ "hash": "faf353ffab307ec5129f24adaa86869002557318356141c3bc9d71506f29ec98",
92
+ "hashAlgorithm": "sha256"
93
+ },
94
+ {
95
+ "index": 6,
96
+ "fileName": "shard_00006.bin",
97
+ "size": 67108864,
98
+ "hash": "e97594ce663739291e96563d5ae421382ade6a4a2f242acbbb0199c9e79b3a19",
99
+ "hashAlgorithm": "sha256"
100
+ },
101
+ {
102
+ "index": 7,
103
+ "fileName": "shard_00007.bin",
104
+ "size": 67108864,
105
+ "hash": "3b41e5abe58bdcb2016a89da6a38f25e2cb64f13fb626e4c10513b39c215a589",
106
+ "hashAlgorithm": "sha256"
107
+ },
108
+ {
109
+ "index": 8,
110
+ "fileName": "shard_00008.bin",
111
+ "size": 67108864,
112
+ "hash": "68e2a3bc7312c7a7044a7676c41281059dcfa30df985fbf78acaaa2ce1c08e41",
113
+ "hashAlgorithm": "sha256"
114
+ },
115
+ {
116
+ "index": 9,
117
+ "fileName": "shard_00009.bin",
118
+ "size": 64989184,
119
+ "hash": "06e71a558b15e6036b42040a8940269a7d1ac333d24dfa8dee5e62dc2237cbe8",
120
+ "hashAlgorithm": "sha256"
121
+ },
122
+ {
123
+ "index": 10,
124
+ "fileName": "shard_00010.bin",
125
+ "size": 60504064,
126
+ "hash": "440fba3e14be8879f97d9c3212403327033eb92a1d90d8e7befcd1017819310b",
127
+ "hashAlgorithm": "sha256"
128
+ },
129
+ {
130
+ "index": 11,
131
+ "fileName": "shard_00011.bin",
132
+ "size": 60504064,
133
+ "hash": "eacd2fdc1199087368713516f5e508a547b22188f7d895959190be791f408a2a",
134
+ "hashAlgorithm": "sha256"
135
+ },
136
+ {
137
+ "index": 12,
138
+ "fileName": "shard_00012.bin",
139
+ "size": 60504064,
140
+ "hash": "3d913fbef5025c977adcd4c762cd45319e5ac22175da82e30aed6df8eb77551e",
141
+ "hashAlgorithm": "sha256"
142
+ },
143
+ {
144
+ "index": 13,
145
+ "fileName": "shard_00013.bin",
146
+ "size": 60504064,
147
+ "hash": "972b4d936485b275a6067cd1e8a338315550d8e1943090b63ed79cc23e40a4f1",
148
+ "hashAlgorithm": "sha256"
149
+ },
150
+ {
151
+ "index": 14,
152
+ "fileName": "shard_00014.bin",
153
+ "size": 60504064,
154
+ "hash": "d09003383bbd78f0d407ccd72a1531dc6feeea3eb9dab7fadfd125d825befc48",
155
+ "hashAlgorithm": "sha256"
156
+ },
157
+ {
158
+ "index": 15,
159
+ "fileName": "shard_00015.bin",
160
+ "size": 25770240,
161
+ "hash": "68c92552170ce6c12f7e8b6a8d44683d6e527955d533fff685bce22cde11d13b",
162
+ "hashAlgorithm": "sha256"
163
+ }
164
+ ],
165
+ "tensors": {
166
+ "model.embed_tokens.weight": {
167
+ "shardIndex": 0,
168
+ "offset": 0,
169
+ "size": 603979776,
170
+ "shape": [
171
+ 262144,
172
+ 1152
173
+ ],
174
+ "dtype": "BF16",
175
+ "spans": [
176
+ {
177
+ "shardIndex": 0,
178
+ "offset": 0,
179
+ "size": 67108864
180
+ },
181
+ {
182
+ "shardIndex": 1,
183
+ "offset": 0,
184
+ "size": 67108864
185
+ },
186
+ {
187
+ "shardIndex": 2,
188
+ "offset": 0,
189
+ "size": 67108864
190
+ },
191
+ {
192
+ "shardIndex": 3,
193
+ "offset": 0,
194
+ "size": 67108864
195
+ },
196
+ {
197
+ "shardIndex": 4,
198
+ "offset": 0,
199
+ "size": 67108864
200
+ },
201
+ {
202
+ "shardIndex": 5,
203
+ "offset": 0,
204
+ "size": 67108864
205
+ },
206
+ {
207
+ "shardIndex": 6,
208
+ "offset": 0,
209
+ "size": 67108864
210
+ },
211
+ {
212
+ "shardIndex": 7,
213
+ "offset": 0,
214
+ "size": 67108864
215
+ },
216
+ {
217
+ "shardIndex": 8,
218
+ "offset": 0,
219
+ "size": 67108864
220
+ }
221
+ ]
222
+ },
223
+ "model.layers.0.input_layernorm.weight": {
224
+ "shardIndex": 9,
225
+ "offset": 0,
226
+ "size": 2304,
227
+ "shape": [
228
+ 1152
229
+ ],
230
+ "dtype": "BF16"
231
+ },
232
+ "model.layers.0.mlp.down_proj.weight": {
233
+ "shardIndex": 9,
234
+ "offset": 4096,
235
+ "size": 4478976,
236
+ "shape": [
237
+ 1152,
238
+ 6912
239
+ ],
240
+ "dtype": "Q4_K_M"
241
+ },
242
+ "model.layers.0.mlp.gate_up_proj.weight": {
243
+ "shardIndex": 9,
244
+ "offset": 4485120,
245
+ "size": 8957952,
246
+ "shape": [
247
+ 13824,
248
+ 1152
249
+ ],
250
+ "dtype": "Q4_K_M"
251
+ },
252
+ "model.layers.0.post_attention_layernorm.weight": {
253
+ "shardIndex": 9,
254
+ "offset": 13443072,
255
+ "size": 2304,
256
+ "shape": [
257
+ 1152
258
+ ],
259
+ "dtype": "BF16"
260
+ },
261
+ "model.layers.0.post_feedforward_layernorm.weight": {
262
+ "shardIndex": 9,
263
+ "offset": 13447168,
264
+ "size": 2304,
265
+ "shape": [
266
+ 1152
267
+ ],
268
+ "dtype": "BF16"
269
+ },
270
+ "model.layers.0.pre_feedforward_layernorm.weight": {
271
+ "shardIndex": 9,
272
+ "offset": 13451264,
273
+ "size": 2304,
274
+ "shape": [
275
+ 1152
276
+ ],
277
+ "dtype": "BF16"
278
+ },
279
+ "model.layers.0.self_attn.k_norm.weight": {
280
+ "shardIndex": 9,
281
+ "offset": 13455360,
282
+ "size": 512,
283
+ "shape": [
284
+ 256
285
+ ],
286
+ "dtype": "BF16"
287
+ },
288
+ "model.layers.0.self_attn.k_proj.weight": {
289
+ "shardIndex": 9,
290
+ "offset": 13459456,
291
+ "size": 165888,
292
+ "shape": [
293
+ 256,
294
+ 1152
295
+ ],
296
+ "dtype": "Q4_K_M"
297
+ },
298
+ "model.layers.0.self_attn.o_proj.weight": {
299
+ "shardIndex": 9,
300
+ "offset": 13627392,
301
+ "size": 663552,
302
+ "shape": [
303
+ 1152,
304
+ 1024
305
+ ],
306
+ "dtype": "Q4_K_M"
307
+ },
308
+ "model.layers.0.self_attn.q_norm.weight": {
309
+ "shardIndex": 9,
310
+ "offset": 14290944,
311
+ "size": 512,
312
+ "shape": [
313
+ 256
314
+ ],
315
+ "dtype": "BF16"
316
+ },
317
+ "model.layers.0.self_attn.q_proj.weight": {
318
+ "shardIndex": 9,
319
+ "offset": 14295040,
320
+ "size": 663552,
321
+ "shape": [
322
+ 1024,
323
+ 1152
324
+ ],
325
+ "dtype": "Q4_K_M"
326
+ },
327
+ "model.layers.0.self_attn.v_proj.weight": {
328
+ "shardIndex": 9,
329
+ "offset": 14958592,
330
+ "size": 165888,
331
+ "shape": [
332
+ 256,
333
+ 1152
334
+ ],
335
+ "dtype": "Q4_K_M"
336
+ },
337
+ "model.layers.1.input_layernorm.weight": {
338
+ "shardIndex": 9,
339
+ "offset": 15126528,
340
+ "size": 2304,
341
+ "shape": [
342
+ 1152
343
+ ],
344
+ "dtype": "BF16"
345
+ },
346
+ "model.layers.1.mlp.down_proj.weight": {
347
+ "shardIndex": 9,
348
+ "offset": 15130624,
349
+ "size": 4478976,
350
+ "shape": [
351
+ 1152,
352
+ 6912
353
+ ],
354
+ "dtype": "Q4_K_M"
355
+ },
356
+ "model.layers.1.mlp.gate_up_proj.weight": {
357
+ "shardIndex": 9,
358
+ "offset": 19611648,
359
+ "size": 8957952,
360
+ "shape": [
361
+ 13824,
362
+ 1152
363
+ ],
364
+ "dtype": "Q4_K_M"
365
+ },
366
+ "model.layers.1.post_attention_layernorm.weight": {
367
+ "shardIndex": 9,
368
+ "offset": 28569600,
369
+ "size": 2304,
370
+ "shape": [
371
+ 1152
372
+ ],
373
+ "dtype": "BF16"
374
+ },
375
+ "model.layers.1.post_feedforward_layernorm.weight": {
376
+ "shardIndex": 9,
377
+ "offset": 28573696,
378
+ "size": 2304,
379
+ "shape": [
380
+ 1152
381
+ ],
382
+ "dtype": "BF16"
383
+ },
384
+ "model.layers.1.pre_feedforward_layernorm.weight": {
385
+ "shardIndex": 9,
386
+ "offset": 28577792,
387
+ "size": 2304,
388
+ "shape": [
389
+ 1152
390
+ ],
391
+ "dtype": "BF16"
392
+ },
393
+ "model.layers.1.self_attn.k_norm.weight": {
394
+ "shardIndex": 9,
395
+ "offset": 28581888,
396
+ "size": 512,
397
+ "shape": [
398
+ 256
399
+ ],
400
+ "dtype": "BF16"
401
+ },
402
+ "model.layers.1.self_attn.k_proj.weight": {
403
+ "shardIndex": 9,
404
+ "offset": 28585984,
405
+ "size": 165888,
406
+ "shape": [
407
+ 256,
408
+ 1152
409
+ ],
410
+ "dtype": "Q4_K_M"
411
+ },
412
+ "model.layers.1.self_attn.o_proj.weight": {
413
+ "shardIndex": 9,
414
+ "offset": 28753920,
415
+ "size": 663552,
416
+ "shape": [
417
+ 1152,
418
+ 1024
419
+ ],
420
+ "dtype": "Q4_K_M"
421
+ },
422
+ "model.layers.1.self_attn.q_norm.weight": {
423
+ "shardIndex": 9,
424
+ "offset": 29417472,
425
+ "size": 512,
426
+ "shape": [
427
+ 256
428
+ ],
429
+ "dtype": "BF16"
430
+ },
431
+ "model.layers.1.self_attn.q_proj.weight": {
432
+ "shardIndex": 9,
433
+ "offset": 29421568,
434
+ "size": 663552,
435
+ "shape": [
436
+ 1024,
437
+ 1152
438
+ ],
439
+ "dtype": "Q4_K_M"
440
+ },
441
+ "model.layers.1.self_attn.v_proj.weight": {
442
+ "shardIndex": 9,
443
+ "offset": 30085120,
444
+ "size": 165888,
445
+ "shape": [
446
+ 256,
447
+ 1152
448
+ ],
449
+ "dtype": "Q4_K_M"
450
+ },
451
+ "model.layers.10.input_layernorm.weight": {
452
+ "shardIndex": 9,
453
+ "offset": 30253056,
454
+ "size": 2304,
455
+ "shape": [
456
+ 1152
457
+ ],
458
+ "dtype": "BF16"
459
+ },
460
+ "model.layers.10.mlp.down_proj.weight": {
461
+ "shardIndex": 9,
462
+ "offset": 30257152,
463
+ "size": 4478976,
464
+ "shape": [
465
+ 1152,
466
+ 6912
467
+ ],
468
+ "dtype": "Q4_K_M"
469
+ },
470
+ "model.layers.10.mlp.gate_up_proj.weight": {
471
+ "shardIndex": 9,
472
+ "offset": 34738176,
473
+ "size": 8957952,
474
+ "shape": [
475
+ 13824,
476
+ 1152
477
+ ],
478
+ "dtype": "Q4_K_M"
479
+ },
480
+ "model.layers.10.post_attention_layernorm.weight": {
481
+ "shardIndex": 9,
482
+ "offset": 43696128,
483
+ "size": 2304,
484
+ "shape": [
485
+ 1152
486
+ ],
487
+ "dtype": "BF16"
488
+ },
489
+ "model.layers.10.post_feedforward_layernorm.weight": {
490
+ "shardIndex": 9,
491
+ "offset": 43700224,
492
+ "size": 2304,
493
+ "shape": [
494
+ 1152
495
+ ],
496
+ "dtype": "BF16"
497
+ },
498
+ "model.layers.10.pre_feedforward_layernorm.weight": {
499
+ "shardIndex": 9,
500
+ "offset": 43704320,
501
+ "size": 2304,
502
+ "shape": [
503
+ 1152
504
+ ],
505
+ "dtype": "BF16"
506
+ },
507
+ "model.layers.10.self_attn.k_norm.weight": {
508
+ "shardIndex": 9,
509
+ "offset": 43708416,
510
+ "size": 512,
511
+ "shape": [
512
+ 256
513
+ ],
514
+ "dtype": "BF16"
515
+ },
516
+ "model.layers.10.self_attn.k_proj.weight": {
517
+ "shardIndex": 9,
518
+ "offset": 43712512,
519
+ "size": 165888,
520
+ "shape": [
521
+ 256,
522
+ 1152
523
+ ],
524
+ "dtype": "Q4_K_M"
525
+ },
526
+ "model.layers.10.self_attn.o_proj.weight": {
527
+ "shardIndex": 9,
528
+ "offset": 43880448,
529
+ "size": 663552,
530
+ "shape": [
531
+ 1152,
532
+ 1024
533
+ ],
534
+ "dtype": "Q4_K_M"
535
+ },
536
+ "model.layers.10.self_attn.q_norm.weight": {
537
+ "shardIndex": 9,
538
+ "offset": 44544000,
539
+ "size": 512,
540
+ "shape": [
541
+ 256
542
+ ],
543
+ "dtype": "BF16"
544
+ },
545
+ "model.layers.10.self_attn.q_proj.weight": {
546
+ "shardIndex": 9,
547
+ "offset": 44548096,
548
+ "size": 663552,
549
+ "shape": [
550
+ 1024,
551
+ 1152
552
+ ],
553
+ "dtype": "Q4_K_M"
554
+ },
555
+ "model.layers.10.self_attn.v_proj.weight": {
556
+ "shardIndex": 9,
557
+ "offset": 45211648,
558
+ "size": 165888,
559
+ "shape": [
560
+ 256,
561
+ 1152
562
+ ],
563
+ "dtype": "Q4_K_M"
564
+ },
565
+ "model.layers.11.input_layernorm.weight": {
566
+ "shardIndex": 9,
567
+ "offset": 45379584,
568
+ "size": 2304,
569
+ "shape": [
570
+ 1152
571
+ ],
572
+ "dtype": "BF16"
573
+ },
574
+ "model.layers.11.mlp.down_proj.weight": {
575
+ "shardIndex": 9,
576
+ "offset": 45383680,
577
+ "size": 4478976,
578
+ "shape": [
579
+ 1152,
580
+ 6912
581
+ ],
582
+ "dtype": "Q4_K_M"
583
+ },
584
+ "model.layers.11.mlp.gate_up_proj.weight": {
585
+ "shardIndex": 9,
586
+ "offset": 49864704,
587
+ "size": 8957952,
588
+ "shape": [
589
+ 13824,
590
+ 1152
591
+ ],
592
+ "dtype": "Q4_K_M"
593
+ },
594
+ "model.layers.11.post_attention_layernorm.weight": {
595
+ "shardIndex": 9,
596
+ "offset": 58822656,
597
+ "size": 2304,
598
+ "shape": [
599
+ 1152
600
+ ],
601
+ "dtype": "BF16"
602
+ },
603
+ "model.layers.11.post_feedforward_layernorm.weight": {
604
+ "shardIndex": 9,
605
+ "offset": 58826752,
606
+ "size": 2304,
607
+ "shape": [
608
+ 1152
609
+ ],
610
+ "dtype": "BF16"
611
+ },
612
+ "model.layers.11.pre_feedforward_layernorm.weight": {
613
+ "shardIndex": 9,
614
+ "offset": 58830848,
615
+ "size": 2304,
616
+ "shape": [
617
+ 1152
618
+ ],
619
+ "dtype": "BF16"
620
+ },
621
+ "model.layers.11.self_attn.k_norm.weight": {
622
+ "shardIndex": 9,
623
+ "offset": 58834944,
624
+ "size": 512,
625
+ "shape": [
626
+ 256
627
+ ],
628
+ "dtype": "BF16"
629
+ },
630
+ "model.layers.11.self_attn.k_proj.weight": {
631
+ "shardIndex": 9,
632
+ "offset": 58839040,
633
+ "size": 165888,
634
+ "shape": [
635
+ 256,
636
+ 1152
637
+ ],
638
+ "dtype": "Q4_K_M"
639
+ },
640
+ "model.layers.11.self_attn.o_proj.weight": {
641
+ "shardIndex": 9,
642
+ "offset": 59006976,
643
+ "size": 663552,
644
+ "shape": [
645
+ 1152,
646
+ 1024
647
+ ],
648
+ "dtype": "Q4_K_M"
649
+ },
650
+ "model.layers.11.self_attn.q_norm.weight": {
651
+ "shardIndex": 9,
652
+ "offset": 59670528,
653
+ "size": 512,
654
+ "shape": [
655
+ 256
656
+ ],
657
+ "dtype": "BF16"
658
+ },
659
+ "model.layers.11.self_attn.q_proj.weight": {
660
+ "shardIndex": 9,
661
+ "offset": 59674624,
662
+ "size": 663552,
663
+ "shape": [
664
+ 1024,
665
+ 1152
666
+ ],
667
+ "dtype": "Q4_K_M"
668
+ },
669
+ "model.layers.11.self_attn.v_proj.weight": {
670
+ "shardIndex": 9,
671
+ "offset": 60338176,
672
+ "size": 165888,
673
+ "shape": [
674
+ 256,
675
+ 1152
676
+ ],
677
+ "dtype": "Q4_K_M"
678
+ },
679
+ "model.layers.12.input_layernorm.weight": {
680
+ "shardIndex": 9,
681
+ "offset": 60506112,
682
+ "size": 2304,
683
+ "shape": [
684
+ 1152
685
+ ],
686
+ "dtype": "BF16"
687
+ },
688
+ "model.layers.12.mlp.down_proj.weight": {
689
+ "shardIndex": 9,
690
+ "offset": 60510208,
691
+ "size": 4478976,
692
+ "shape": [
693
+ 1152,
694
+ 6912
695
+ ],
696
+ "dtype": "Q4_K_M"
697
+ },
698
+ "model.layers.12.mlp.gate_up_proj.weight": {
699
+ "shardIndex": 10,
700
+ "offset": 0,
701
+ "size": 8957952,
702
+ "shape": [
703
+ 13824,
704
+ 1152
705
+ ],
706
+ "dtype": "Q4_K_M"
707
+ },
708
+ "model.layers.12.post_attention_layernorm.weight": {
709
+ "shardIndex": 10,
710
+ "offset": 8957952,
711
+ "size": 2304,
712
+ "shape": [
713
+ 1152
714
+ ],
715
+ "dtype": "BF16"
716
+ },
717
+ "model.layers.12.post_feedforward_layernorm.weight": {
718
+ "shardIndex": 10,
719
+ "offset": 8962048,
720
+ "size": 2304,
721
+ "shape": [
722
+ 1152
723
+ ],
724
+ "dtype": "BF16"
725
+ },
726
+ "model.layers.12.pre_feedforward_layernorm.weight": {
727
+ "shardIndex": 10,
728
+ "offset": 8966144,
729
+ "size": 2304,
730
+ "shape": [
731
+ 1152
732
+ ],
733
+ "dtype": "BF16"
734
+ },
735
+ "model.layers.12.self_attn.k_norm.weight": {
736
+ "shardIndex": 10,
737
+ "offset": 8970240,
738
+ "size": 512,
739
+ "shape": [
740
+ 256
741
+ ],
742
+ "dtype": "BF16"
743
+ },
744
+ "model.layers.12.self_attn.k_proj.weight": {
745
+ "shardIndex": 10,
746
+ "offset": 8974336,
747
+ "size": 165888,
748
+ "shape": [
749
+ 256,
750
+ 1152
751
+ ],
752
+ "dtype": "Q4_K_M"
753
+ },
754
+ "model.layers.12.self_attn.o_proj.weight": {
755
+ "shardIndex": 10,
756
+ "offset": 9142272,
757
+ "size": 663552,
758
+ "shape": [
759
+ 1152,
760
+ 1024
761
+ ],
762
+ "dtype": "Q4_K_M"
763
+ },
764
+ "model.layers.12.self_attn.q_norm.weight": {
765
+ "shardIndex": 10,
766
+ "offset": 9805824,
767
+ "size": 512,
768
+ "shape": [
769
+ 256
770
+ ],
771
+ "dtype": "BF16"
772
+ },
773
+ "model.layers.12.self_attn.q_proj.weight": {
774
+ "shardIndex": 10,
775
+ "offset": 9809920,
776
+ "size": 663552,
777
+ "shape": [
778
+ 1024,
779
+ 1152
780
+ ],
781
+ "dtype": "Q4_K_M"
782
+ },
783
+ "model.layers.12.self_attn.v_proj.weight": {
784
+ "shardIndex": 10,
785
+ "offset": 10473472,
786
+ "size": 165888,
787
+ "shape": [
788
+ 256,
789
+ 1152
790
+ ],
791
+ "dtype": "Q4_K_M"
792
+ },
793
+ "model.layers.13.input_layernorm.weight": {
794
+ "shardIndex": 10,
795
+ "offset": 10641408,
796
+ "size": 2304,
797
+ "shape": [
798
+ 1152
799
+ ],
800
+ "dtype": "BF16"
801
+ },
802
+ "model.layers.13.mlp.down_proj.weight": {
803
+ "shardIndex": 10,
804
+ "offset": 10645504,
805
+ "size": 4478976,
806
+ "shape": [
807
+ 1152,
808
+ 6912
809
+ ],
810
+ "dtype": "Q4_K_M"
811
+ },
812
+ "model.layers.13.mlp.gate_up_proj.weight": {
813
+ "shardIndex": 10,
814
+ "offset": 15126528,
815
+ "size": 8957952,
816
+ "shape": [
817
+ 13824,
818
+ 1152
819
+ ],
820
+ "dtype": "Q4_K_M"
821
+ },
822
+ "model.layers.13.post_attention_layernorm.weight": {
823
+ "shardIndex": 10,
824
+ "offset": 24084480,
825
+ "size": 2304,
826
+ "shape": [
827
+ 1152
828
+ ],
829
+ "dtype": "BF16"
830
+ },
831
+ "model.layers.13.post_feedforward_layernorm.weight": {
832
+ "shardIndex": 10,
833
+ "offset": 24088576,
834
+ "size": 2304,
835
+ "shape": [
836
+ 1152
837
+ ],
838
+ "dtype": "BF16"
839
+ },
840
+ "model.layers.13.pre_feedforward_layernorm.weight": {
841
+ "shardIndex": 10,
842
+ "offset": 24092672,
843
+ "size": 2304,
844
+ "shape": [
845
+ 1152
846
+ ],
847
+ "dtype": "BF16"
848
+ },
849
+ "model.layers.13.self_attn.k_norm.weight": {
850
+ "shardIndex": 10,
851
+ "offset": 24096768,
852
+ "size": 512,
853
+ "shape": [
854
+ 256
855
+ ],
856
+ "dtype": "BF16"
857
+ },
858
+ "model.layers.13.self_attn.k_proj.weight": {
859
+ "shardIndex": 10,
860
+ "offset": 24100864,
861
+ "size": 165888,
862
+ "shape": [
863
+ 256,
864
+ 1152
865
+ ],
866
+ "dtype": "Q4_K_M"
867
+ },
868
+ "model.layers.13.self_attn.o_proj.weight": {
869
+ "shardIndex": 10,
870
+ "offset": 24268800,
871
+ "size": 663552,
872
+ "shape": [
873
+ 1152,
874
+ 1024
875
+ ],
876
+ "dtype": "Q4_K_M"
877
+ },
878
+ "model.layers.13.self_attn.q_norm.weight": {
879
+ "shardIndex": 10,
880
+ "offset": 24932352,
881
+ "size": 512,
882
+ "shape": [
883
+ 256
884
+ ],
885
+ "dtype": "BF16"
886
+ },
887
+ "model.layers.13.self_attn.q_proj.weight": {
888
+ "shardIndex": 10,
889
+ "offset": 24936448,
890
+ "size": 663552,
891
+ "shape": [
892
+ 1024,
893
+ 1152
894
+ ],
895
+ "dtype": "Q4_K_M"
896
+ },
897
+ "model.layers.13.self_attn.v_proj.weight": {
898
+ "shardIndex": 10,
899
+ "offset": 25600000,
900
+ "size": 165888,
901
+ "shape": [
902
+ 256,
903
+ 1152
904
+ ],
905
+ "dtype": "Q4_K_M"
906
+ },
907
+ "model.layers.14.input_layernorm.weight": {
908
+ "shardIndex": 10,
909
+ "offset": 25767936,
910
+ "size": 2304,
911
+ "shape": [
912
+ 1152
913
+ ],
914
+ "dtype": "BF16"
915
+ },
916
+ "model.layers.14.mlp.down_proj.weight": {
917
+ "shardIndex": 10,
918
+ "offset": 25772032,
919
+ "size": 4478976,
920
+ "shape": [
921
+ 1152,
922
+ 6912
923
+ ],
924
+ "dtype": "Q4_K_M"
925
+ },
926
+ "model.layers.14.mlp.gate_up_proj.weight": {
927
+ "shardIndex": 10,
928
+ "offset": 30253056,
929
+ "size": 8957952,
930
+ "shape": [
931
+ 13824,
932
+ 1152
933
+ ],
934
+ "dtype": "Q4_K_M"
935
+ },
936
+ "model.layers.14.post_attention_layernorm.weight": {
937
+ "shardIndex": 10,
938
+ "offset": 39211008,
939
+ "size": 2304,
940
+ "shape": [
941
+ 1152
942
+ ],
943
+ "dtype": "BF16"
944
+ },
945
+ "model.layers.14.post_feedforward_layernorm.weight": {
946
+ "shardIndex": 10,
947
+ "offset": 39215104,
948
+ "size": 2304,
949
+ "shape": [
950
+ 1152
951
+ ],
952
+ "dtype": "BF16"
953
+ },
954
+ "model.layers.14.pre_feedforward_layernorm.weight": {
955
+ "shardIndex": 10,
956
+ "offset": 39219200,
957
+ "size": 2304,
958
+ "shape": [
959
+ 1152
960
+ ],
961
+ "dtype": "BF16"
962
+ },
963
+ "model.layers.14.self_attn.k_norm.weight": {
964
+ "shardIndex": 10,
965
+ "offset": 39223296,
966
+ "size": 512,
967
+ "shape": [
968
+ 256
969
+ ],
970
+ "dtype": "BF16"
971
+ },
972
+ "model.layers.14.self_attn.k_proj.weight": {
973
+ "shardIndex": 10,
974
+ "offset": 39227392,
975
+ "size": 165888,
976
+ "shape": [
977
+ 256,
978
+ 1152
979
+ ],
980
+ "dtype": "Q4_K_M"
981
+ },
982
+ "model.layers.14.self_attn.o_proj.weight": {
983
+ "shardIndex": 10,
984
+ "offset": 39395328,
985
+ "size": 663552,
986
+ "shape": [
987
+ 1152,
988
+ 1024
989
+ ],
990
+ "dtype": "Q4_K_M"
991
+ },
992
+ "model.layers.14.self_attn.q_norm.weight": {
993
+ "shardIndex": 10,
994
+ "offset": 40058880,
995
+ "size": 512,
996
+ "shape": [
997
+ 256
998
+ ],
999
+ "dtype": "BF16"
1000
+ },
1001
+ "model.layers.14.self_attn.q_proj.weight": {
1002
+ "shardIndex": 10,
1003
+ "offset": 40062976,
1004
+ "size": 663552,
1005
+ "shape": [
1006
+ 1024,
1007
+ 1152
1008
+ ],
1009
+ "dtype": "Q4_K_M"
1010
+ },
1011
+ "model.layers.14.self_attn.v_proj.weight": {
1012
+ "shardIndex": 10,
1013
+ "offset": 40726528,
1014
+ "size": 165888,
1015
+ "shape": [
1016
+ 256,
1017
+ 1152
1018
+ ],
1019
+ "dtype": "Q4_K_M"
1020
+ },
1021
+ "model.layers.15.input_layernorm.weight": {
1022
+ "shardIndex": 10,
1023
+ "offset": 40894464,
1024
+ "size": 2304,
1025
+ "shape": [
1026
+ 1152
1027
+ ],
1028
+ "dtype": "BF16"
1029
+ },
1030
+ "model.layers.15.mlp.down_proj.weight": {
1031
+ "shardIndex": 10,
1032
+ "offset": 40898560,
1033
+ "size": 4478976,
1034
+ "shape": [
1035
+ 1152,
1036
+ 6912
1037
+ ],
1038
+ "dtype": "Q4_K_M"
1039
+ },
1040
+ "model.layers.15.mlp.gate_up_proj.weight": {
1041
+ "shardIndex": 10,
1042
+ "offset": 45379584,
1043
+ "size": 8957952,
1044
+ "shape": [
1045
+ 13824,
1046
+ 1152
1047
+ ],
1048
+ "dtype": "Q4_K_M"
1049
+ },
1050
+ "model.layers.15.post_attention_layernorm.weight": {
1051
+ "shardIndex": 10,
1052
+ "offset": 54337536,
1053
+ "size": 2304,
1054
+ "shape": [
1055
+ 1152
1056
+ ],
1057
+ "dtype": "BF16"
1058
+ },
1059
+ "model.layers.15.post_feedforward_layernorm.weight": {
1060
+ "shardIndex": 10,
1061
+ "offset": 54341632,
1062
+ "size": 2304,
1063
+ "shape": [
1064
+ 1152
1065
+ ],
1066
+ "dtype": "BF16"
1067
+ },
1068
+ "model.layers.15.pre_feedforward_layernorm.weight": {
1069
+ "shardIndex": 10,
1070
+ "offset": 54345728,
1071
+ "size": 2304,
1072
+ "shape": [
1073
+ 1152
1074
+ ],
1075
+ "dtype": "BF16"
1076
+ },
1077
+ "model.layers.15.self_attn.k_norm.weight": {
1078
+ "shardIndex": 10,
1079
+ "offset": 54349824,
1080
+ "size": 512,
1081
+ "shape": [
1082
+ 256
1083
+ ],
1084
+ "dtype": "BF16"
1085
+ },
1086
+ "model.layers.15.self_attn.k_proj.weight": {
1087
+ "shardIndex": 10,
1088
+ "offset": 54353920,
1089
+ "size": 165888,
1090
+ "shape": [
1091
+ 256,
1092
+ 1152
1093
+ ],
1094
+ "dtype": "Q4_K_M"
1095
+ },
1096
+ "model.layers.15.self_attn.o_proj.weight": {
1097
+ "shardIndex": 10,
1098
+ "offset": 54521856,
1099
+ "size": 663552,
1100
+ "shape": [
1101
+ 1152,
1102
+ 1024
1103
+ ],
1104
+ "dtype": "Q4_K_M"
1105
+ },
1106
+ "model.layers.15.self_attn.q_norm.weight": {
1107
+ "shardIndex": 10,
1108
+ "offset": 55185408,
1109
+ "size": 512,
1110
+ "shape": [
1111
+ 256
1112
+ ],
1113
+ "dtype": "BF16"
1114
+ },
1115
+ "model.layers.15.self_attn.q_proj.weight": {
1116
+ "shardIndex": 10,
1117
+ "offset": 55189504,
1118
+ "size": 663552,
1119
+ "shape": [
1120
+ 1024,
1121
+ 1152
1122
+ ],
1123
+ "dtype": "Q4_K_M"
1124
+ },
1125
+ "model.layers.15.self_attn.v_proj.weight": {
1126
+ "shardIndex": 10,
1127
+ "offset": 55853056,
1128
+ "size": 165888,
1129
+ "shape": [
1130
+ 256,
1131
+ 1152
1132
+ ],
1133
+ "dtype": "Q4_K_M"
1134
+ },
1135
+ "model.layers.16.input_layernorm.weight": {
1136
+ "shardIndex": 10,
1137
+ "offset": 56020992,
1138
+ "size": 2304,
1139
+ "shape": [
1140
+ 1152
1141
+ ],
1142
+ "dtype": "BF16"
1143
+ },
1144
+ "model.layers.16.mlp.down_proj.weight": {
1145
+ "shardIndex": 10,
1146
+ "offset": 56025088,
1147
+ "size": 4478976,
1148
+ "shape": [
1149
+ 1152,
1150
+ 6912
1151
+ ],
1152
+ "dtype": "Q4_K_M"
1153
+ },
1154
+ "model.layers.16.mlp.gate_up_proj.weight": {
1155
+ "shardIndex": 11,
1156
+ "offset": 0,
1157
+ "size": 8957952,
1158
+ "shape": [
1159
+ 13824,
1160
+ 1152
1161
+ ],
1162
+ "dtype": "Q4_K_M"
1163
+ },
1164
+ "model.layers.16.post_attention_layernorm.weight": {
1165
+ "shardIndex": 11,
1166
+ "offset": 8957952,
1167
+ "size": 2304,
1168
+ "shape": [
1169
+ 1152
1170
+ ],
1171
+ "dtype": "BF16"
1172
+ },
1173
+ "model.layers.16.post_feedforward_layernorm.weight": {
1174
+ "shardIndex": 11,
1175
+ "offset": 8962048,
1176
+ "size": 2304,
1177
+ "shape": [
1178
+ 1152
1179
+ ],
1180
+ "dtype": "BF16"
1181
+ },
1182
+ "model.layers.16.pre_feedforward_layernorm.weight": {
1183
+ "shardIndex": 11,
1184
+ "offset": 8966144,
1185
+ "size": 2304,
1186
+ "shape": [
1187
+ 1152
1188
+ ],
1189
+ "dtype": "BF16"
1190
+ },
1191
+ "model.layers.16.self_attn.k_norm.weight": {
1192
+ "shardIndex": 11,
1193
+ "offset": 8970240,
1194
+ "size": 512,
1195
+ "shape": [
1196
+ 256
1197
+ ],
1198
+ "dtype": "BF16"
1199
+ },
1200
+ "model.layers.16.self_attn.k_proj.weight": {
1201
+ "shardIndex": 11,
1202
+ "offset": 8974336,
1203
+ "size": 165888,
1204
+ "shape": [
1205
+ 256,
1206
+ 1152
1207
+ ],
1208
+ "dtype": "Q4_K_M"
1209
+ },
1210
+ "model.layers.16.self_attn.o_proj.weight": {
1211
+ "shardIndex": 11,
1212
+ "offset": 9142272,
1213
+ "size": 663552,
1214
+ "shape": [
1215
+ 1152,
1216
+ 1024
1217
+ ],
1218
+ "dtype": "Q4_K_M"
1219
+ },
1220
+ "model.layers.16.self_attn.q_norm.weight": {
1221
+ "shardIndex": 11,
1222
+ "offset": 9805824,
1223
+ "size": 512,
1224
+ "shape": [
1225
+ 256
1226
+ ],
1227
+ "dtype": "BF16"
1228
+ },
1229
+ "model.layers.16.self_attn.q_proj.weight": {
1230
+ "shardIndex": 11,
1231
+ "offset": 9809920,
1232
+ "size": 663552,
1233
+ "shape": [
1234
+ 1024,
1235
+ 1152
1236
+ ],
1237
+ "dtype": "Q4_K_M"
1238
+ },
1239
+ "model.layers.16.self_attn.v_proj.weight": {
1240
+ "shardIndex": 11,
1241
+ "offset": 10473472,
1242
+ "size": 165888,
1243
+ "shape": [
1244
+ 256,
1245
+ 1152
1246
+ ],
1247
+ "dtype": "Q4_K_M"
1248
+ },
1249
+ "model.layers.17.input_layernorm.weight": {
1250
+ "shardIndex": 11,
1251
+ "offset": 10641408,
1252
+ "size": 2304,
1253
+ "shape": [
1254
+ 1152
1255
+ ],
1256
+ "dtype": "BF16"
1257
+ },
1258
+ "model.layers.17.mlp.down_proj.weight": {
1259
+ "shardIndex": 11,
1260
+ "offset": 10645504,
1261
+ "size": 4478976,
1262
+ "shape": [
1263
+ 1152,
1264
+ 6912
1265
+ ],
1266
+ "dtype": "Q4_K_M"
1267
+ },
1268
+ "model.layers.17.mlp.gate_up_proj.weight": {
1269
+ "shardIndex": 11,
1270
+ "offset": 15126528,
1271
+ "size": 8957952,
1272
+ "shape": [
1273
+ 13824,
1274
+ 1152
1275
+ ],
1276
+ "dtype": "Q4_K_M"
1277
+ },
1278
+ "model.layers.17.post_attention_layernorm.weight": {
1279
+ "shardIndex": 11,
1280
+ "offset": 24084480,
1281
+ "size": 2304,
1282
+ "shape": [
1283
+ 1152
1284
+ ],
1285
+ "dtype": "BF16"
1286
+ },
1287
+ "model.layers.17.post_feedforward_layernorm.weight": {
1288
+ "shardIndex": 11,
1289
+ "offset": 24088576,
1290
+ "size": 2304,
1291
+ "shape": [
1292
+ 1152
1293
+ ],
1294
+ "dtype": "BF16"
1295
+ },
1296
+ "model.layers.17.pre_feedforward_layernorm.weight": {
1297
+ "shardIndex": 11,
1298
+ "offset": 24092672,
1299
+ "size": 2304,
1300
+ "shape": [
1301
+ 1152
1302
+ ],
1303
+ "dtype": "BF16"
1304
+ },
1305
+ "model.layers.17.self_attn.k_norm.weight": {
1306
+ "shardIndex": 11,
1307
+ "offset": 24096768,
1308
+ "size": 512,
1309
+ "shape": [
1310
+ 256
1311
+ ],
1312
+ "dtype": "BF16"
1313
+ },
1314
+ "model.layers.17.self_attn.k_proj.weight": {
1315
+ "shardIndex": 11,
1316
+ "offset": 24100864,
1317
+ "size": 165888,
1318
+ "shape": [
1319
+ 256,
1320
+ 1152
1321
+ ],
1322
+ "dtype": "Q4_K_M"
1323
+ },
1324
+ "model.layers.17.self_attn.o_proj.weight": {
1325
+ "shardIndex": 11,
1326
+ "offset": 24268800,
1327
+ "size": 663552,
1328
+ "shape": [
1329
+ 1152,
1330
+ 1024
1331
+ ],
1332
+ "dtype": "Q4_K_M"
1333
+ },
1334
+ "model.layers.17.self_attn.q_norm.weight": {
1335
+ "shardIndex": 11,
1336
+ "offset": 24932352,
1337
+ "size": 512,
1338
+ "shape": [
1339
+ 256
1340
+ ],
1341
+ "dtype": "BF16"
1342
+ },
1343
+ "model.layers.17.self_attn.q_proj.weight": {
1344
+ "shardIndex": 11,
1345
+ "offset": 24936448,
1346
+ "size": 663552,
1347
+ "shape": [
1348
+ 1024,
1349
+ 1152
1350
+ ],
1351
+ "dtype": "Q4_K_M"
1352
+ },
1353
+ "model.layers.17.self_attn.v_proj.weight": {
1354
+ "shardIndex": 11,
1355
+ "offset": 25600000,
1356
+ "size": 165888,
1357
+ "shape": [
1358
+ 256,
1359
+ 1152
1360
+ ],
1361
+ "dtype": "Q4_K_M"
1362
+ },
1363
+ "model.layers.18.input_layernorm.weight": {
1364
+ "shardIndex": 11,
1365
+ "offset": 25767936,
1366
+ "size": 2304,
1367
+ "shape": [
1368
+ 1152
1369
+ ],
1370
+ "dtype": "BF16"
1371
+ },
1372
+ "model.layers.18.mlp.down_proj.weight": {
1373
+ "shardIndex": 11,
1374
+ "offset": 25772032,
1375
+ "size": 4478976,
1376
+ "shape": [
1377
+ 1152,
1378
+ 6912
1379
+ ],
1380
+ "dtype": "Q4_K_M"
1381
+ },
1382
+ "model.layers.18.mlp.gate_up_proj.weight": {
1383
+ "shardIndex": 11,
1384
+ "offset": 30253056,
1385
+ "size": 8957952,
1386
+ "shape": [
1387
+ 13824,
1388
+ 1152
1389
+ ],
1390
+ "dtype": "Q4_K_M"
1391
+ },
1392
+ "model.layers.18.post_attention_layernorm.weight": {
1393
+ "shardIndex": 11,
1394
+ "offset": 39211008,
1395
+ "size": 2304,
1396
+ "shape": [
1397
+ 1152
1398
+ ],
1399
+ "dtype": "BF16"
1400
+ },
1401
+ "model.layers.18.post_feedforward_layernorm.weight": {
1402
+ "shardIndex": 11,
1403
+ "offset": 39215104,
1404
+ "size": 2304,
1405
+ "shape": [
1406
+ 1152
1407
+ ],
1408
+ "dtype": "BF16"
1409
+ },
1410
+ "model.layers.18.pre_feedforward_layernorm.weight": {
1411
+ "shardIndex": 11,
1412
+ "offset": 39219200,
1413
+ "size": 2304,
1414
+ "shape": [
1415
+ 1152
1416
+ ],
1417
+ "dtype": "BF16"
1418
+ },
1419
+ "model.layers.18.self_attn.k_norm.weight": {
1420
+ "shardIndex": 11,
1421
+ "offset": 39223296,
1422
+ "size": 512,
1423
+ "shape": [
1424
+ 256
1425
+ ],
1426
+ "dtype": "BF16"
1427
+ },
1428
+ "model.layers.18.self_attn.k_proj.weight": {
1429
+ "shardIndex": 11,
1430
+ "offset": 39227392,
1431
+ "size": 165888,
1432
+ "shape": [
1433
+ 256,
1434
+ 1152
1435
+ ],
1436
+ "dtype": "Q4_K_M"
1437
+ },
1438
+ "model.layers.18.self_attn.o_proj.weight": {
1439
+ "shardIndex": 11,
1440
+ "offset": 39395328,
1441
+ "size": 663552,
1442
+ "shape": [
1443
+ 1152,
1444
+ 1024
1445
+ ],
1446
+ "dtype": "Q4_K_M"
1447
+ },
1448
+ "model.layers.18.self_attn.q_norm.weight": {
1449
+ "shardIndex": 11,
1450
+ "offset": 40058880,
1451
+ "size": 512,
1452
+ "shape": [
1453
+ 256
1454
+ ],
1455
+ "dtype": "BF16"
1456
+ },
1457
+ "model.layers.18.self_attn.q_proj.weight": {
1458
+ "shardIndex": 11,
1459
+ "offset": 40062976,
1460
+ "size": 663552,
1461
+ "shape": [
1462
+ 1024,
1463
+ 1152
1464
+ ],
1465
+ "dtype": "Q4_K_M"
1466
+ },
1467
+ "model.layers.18.self_attn.v_proj.weight": {
1468
+ "shardIndex": 11,
1469
+ "offset": 40726528,
1470
+ "size": 165888,
1471
+ "shape": [
1472
+ 256,
1473
+ 1152
1474
+ ],
1475
+ "dtype": "Q4_K_M"
1476
+ },
1477
+ "model.layers.19.input_layernorm.weight": {
1478
+ "shardIndex": 11,
1479
+ "offset": 40894464,
1480
+ "size": 2304,
1481
+ "shape": [
1482
+ 1152
1483
+ ],
1484
+ "dtype": "BF16"
1485
+ },
1486
+ "model.layers.19.mlp.down_proj.weight": {
1487
+ "shardIndex": 11,
1488
+ "offset": 40898560,
1489
+ "size": 4478976,
1490
+ "shape": [
1491
+ 1152,
1492
+ 6912
1493
+ ],
1494
+ "dtype": "Q4_K_M"
1495
+ },
1496
+ "model.layers.19.mlp.gate_up_proj.weight": {
1497
+ "shardIndex": 11,
1498
+ "offset": 45379584,
1499
+ "size": 8957952,
1500
+ "shape": [
1501
+ 13824,
1502
+ 1152
1503
+ ],
1504
+ "dtype": "Q4_K_M"
1505
+ },
1506
+ "model.layers.19.post_attention_layernorm.weight": {
1507
+ "shardIndex": 11,
1508
+ "offset": 54337536,
1509
+ "size": 2304,
1510
+ "shape": [
1511
+ 1152
1512
+ ],
1513
+ "dtype": "BF16"
1514
+ },
1515
+ "model.layers.19.post_feedforward_layernorm.weight": {
1516
+ "shardIndex": 11,
1517
+ "offset": 54341632,
1518
+ "size": 2304,
1519
+ "shape": [
1520
+ 1152
1521
+ ],
1522
+ "dtype": "BF16"
1523
+ },
1524
+ "model.layers.19.pre_feedforward_layernorm.weight": {
1525
+ "shardIndex": 11,
1526
+ "offset": 54345728,
1527
+ "size": 2304,
1528
+ "shape": [
1529
+ 1152
1530
+ ],
1531
+ "dtype": "BF16"
1532
+ },
1533
+ "model.layers.19.self_attn.k_norm.weight": {
1534
+ "shardIndex": 11,
1535
+ "offset": 54349824,
1536
+ "size": 512,
1537
+ "shape": [
1538
+ 256
1539
+ ],
1540
+ "dtype": "BF16"
1541
+ },
1542
+ "model.layers.19.self_attn.k_proj.weight": {
1543
+ "shardIndex": 11,
1544
+ "offset": 54353920,
1545
+ "size": 165888,
1546
+ "shape": [
1547
+ 256,
1548
+ 1152
1549
+ ],
1550
+ "dtype": "Q4_K_M"
1551
+ },
1552
+ "model.layers.19.self_attn.o_proj.weight": {
1553
+ "shardIndex": 11,
1554
+ "offset": 54521856,
1555
+ "size": 663552,
1556
+ "shape": [
1557
+ 1152,
1558
+ 1024
1559
+ ],
1560
+ "dtype": "Q4_K_M"
1561
+ },
1562
+ "model.layers.19.self_attn.q_norm.weight": {
1563
+ "shardIndex": 11,
1564
+ "offset": 55185408,
1565
+ "size": 512,
1566
+ "shape": [
1567
+ 256
1568
+ ],
1569
+ "dtype": "BF16"
1570
+ },
1571
+ "model.layers.19.self_attn.q_proj.weight": {
1572
+ "shardIndex": 11,
1573
+ "offset": 55189504,
1574
+ "size": 663552,
1575
+ "shape": [
1576
+ 1024,
1577
+ 1152
1578
+ ],
1579
+ "dtype": "Q4_K_M"
1580
+ },
1581
+ "model.layers.19.self_attn.v_proj.weight": {
1582
+ "shardIndex": 11,
1583
+ "offset": 55853056,
1584
+ "size": 165888,
1585
+ "shape": [
1586
+ 256,
1587
+ 1152
1588
+ ],
1589
+ "dtype": "Q4_K_M"
1590
+ },
1591
+ "model.layers.2.input_layernorm.weight": {
1592
+ "shardIndex": 11,
1593
+ "offset": 56020992,
1594
+ "size": 2304,
1595
+ "shape": [
1596
+ 1152
1597
+ ],
1598
+ "dtype": "BF16"
1599
+ },
1600
+ "model.layers.2.mlp.down_proj.weight": {
1601
+ "shardIndex": 11,
1602
+ "offset": 56025088,
1603
+ "size": 4478976,
1604
+ "shape": [
1605
+ 1152,
1606
+ 6912
1607
+ ],
1608
+ "dtype": "Q4_K_M"
1609
+ },
1610
+ "model.layers.2.mlp.gate_up_proj.weight": {
1611
+ "shardIndex": 12,
1612
+ "offset": 0,
1613
+ "size": 8957952,
1614
+ "shape": [
1615
+ 13824,
1616
+ 1152
1617
+ ],
1618
+ "dtype": "Q4_K_M"
1619
+ },
1620
+ "model.layers.2.post_attention_layernorm.weight": {
1621
+ "shardIndex": 12,
1622
+ "offset": 8957952,
1623
+ "size": 2304,
1624
+ "shape": [
1625
+ 1152
1626
+ ],
1627
+ "dtype": "BF16"
1628
+ },
1629
+ "model.layers.2.post_feedforward_layernorm.weight": {
1630
+ "shardIndex": 12,
1631
+ "offset": 8962048,
1632
+ "size": 2304,
1633
+ "shape": [
1634
+ 1152
1635
+ ],
1636
+ "dtype": "BF16"
1637
+ },
1638
+ "model.layers.2.pre_feedforward_layernorm.weight": {
1639
+ "shardIndex": 12,
1640
+ "offset": 8966144,
1641
+ "size": 2304,
1642
+ "shape": [
1643
+ 1152
1644
+ ],
1645
+ "dtype": "BF16"
1646
+ },
1647
+ "model.layers.2.self_attn.k_norm.weight": {
1648
+ "shardIndex": 12,
1649
+ "offset": 8970240,
1650
+ "size": 512,
1651
+ "shape": [
1652
+ 256
1653
+ ],
1654
+ "dtype": "BF16"
1655
+ },
1656
+ "model.layers.2.self_attn.k_proj.weight": {
1657
+ "shardIndex": 12,
1658
+ "offset": 8974336,
1659
+ "size": 165888,
1660
+ "shape": [
1661
+ 256,
1662
+ 1152
1663
+ ],
1664
+ "dtype": "Q4_K_M"
1665
+ },
1666
+ "model.layers.2.self_attn.o_proj.weight": {
1667
+ "shardIndex": 12,
1668
+ "offset": 9142272,
1669
+ "size": 663552,
1670
+ "shape": [
1671
+ 1152,
1672
+ 1024
1673
+ ],
1674
+ "dtype": "Q4_K_M"
1675
+ },
1676
+ "model.layers.2.self_attn.q_norm.weight": {
1677
+ "shardIndex": 12,
1678
+ "offset": 9805824,
1679
+ "size": 512,
1680
+ "shape": [
1681
+ 256
1682
+ ],
1683
+ "dtype": "BF16"
1684
+ },
1685
+ "model.layers.2.self_attn.q_proj.weight": {
1686
+ "shardIndex": 12,
1687
+ "offset": 9809920,
1688
+ "size": 663552,
1689
+ "shape": [
1690
+ 1024,
1691
+ 1152
1692
+ ],
1693
+ "dtype": "Q4_K_M"
1694
+ },
1695
+ "model.layers.2.self_attn.v_proj.weight": {
1696
+ "shardIndex": 12,
1697
+ "offset": 10473472,
1698
+ "size": 165888,
1699
+ "shape": [
1700
+ 256,
1701
+ 1152
1702
+ ],
1703
+ "dtype": "Q4_K_M"
1704
+ },
1705
+ "model.layers.20.input_layernorm.weight": {
1706
+ "shardIndex": 12,
1707
+ "offset": 10641408,
1708
+ "size": 2304,
1709
+ "shape": [
1710
+ 1152
1711
+ ],
1712
+ "dtype": "BF16"
1713
+ },
1714
+ "model.layers.20.mlp.down_proj.weight": {
1715
+ "shardIndex": 12,
1716
+ "offset": 10645504,
1717
+ "size": 4478976,
1718
+ "shape": [
1719
+ 1152,
1720
+ 6912
1721
+ ],
1722
+ "dtype": "Q4_K_M"
1723
+ },
1724
+ "model.layers.20.mlp.gate_up_proj.weight": {
1725
+ "shardIndex": 12,
1726
+ "offset": 15126528,
1727
+ "size": 8957952,
1728
+ "shape": [
1729
+ 13824,
1730
+ 1152
1731
+ ],
1732
+ "dtype": "Q4_K_M"
1733
+ },
1734
+ "model.layers.20.post_attention_layernorm.weight": {
1735
+ "shardIndex": 12,
1736
+ "offset": 24084480,
1737
+ "size": 2304,
1738
+ "shape": [
1739
+ 1152
1740
+ ],
1741
+ "dtype": "BF16"
1742
+ },
1743
+ "model.layers.20.post_feedforward_layernorm.weight": {
1744
+ "shardIndex": 12,
1745
+ "offset": 24088576,
1746
+ "size": 2304,
1747
+ "shape": [
1748
+ 1152
1749
+ ],
1750
+ "dtype": "BF16"
1751
+ },
1752
+ "model.layers.20.pre_feedforward_layernorm.weight": {
1753
+ "shardIndex": 12,
1754
+ "offset": 24092672,
1755
+ "size": 2304,
1756
+ "shape": [
1757
+ 1152
1758
+ ],
1759
+ "dtype": "BF16"
1760
+ },
1761
+ "model.layers.20.self_attn.k_norm.weight": {
1762
+ "shardIndex": 12,
1763
+ "offset": 24096768,
1764
+ "size": 512,
1765
+ "shape": [
1766
+ 256
1767
+ ],
1768
+ "dtype": "BF16"
1769
+ },
1770
+ "model.layers.20.self_attn.k_proj.weight": {
1771
+ "shardIndex": 12,
1772
+ "offset": 24100864,
1773
+ "size": 165888,
1774
+ "shape": [
1775
+ 256,
1776
+ 1152
1777
+ ],
1778
+ "dtype": "Q4_K_M"
1779
+ },
1780
+ "model.layers.20.self_attn.o_proj.weight": {
1781
+ "shardIndex": 12,
1782
+ "offset": 24268800,
1783
+ "size": 663552,
1784
+ "shape": [
1785
+ 1152,
1786
+ 1024
1787
+ ],
1788
+ "dtype": "Q4_K_M"
1789
+ },
1790
+ "model.layers.20.self_attn.q_norm.weight": {
1791
+ "shardIndex": 12,
1792
+ "offset": 24932352,
1793
+ "size": 512,
1794
+ "shape": [
1795
+ 256
1796
+ ],
1797
+ "dtype": "BF16"
1798
+ },
1799
+ "model.layers.20.self_attn.q_proj.weight": {
1800
+ "shardIndex": 12,
1801
+ "offset": 24936448,
1802
+ "size": 663552,
1803
+ "shape": [
1804
+ 1024,
1805
+ 1152
1806
+ ],
1807
+ "dtype": "Q4_K_M"
1808
+ },
1809
+ "model.layers.20.self_attn.v_proj.weight": {
1810
+ "shardIndex": 12,
1811
+ "offset": 25600000,
1812
+ "size": 165888,
1813
+ "shape": [
1814
+ 256,
1815
+ 1152
1816
+ ],
1817
+ "dtype": "Q4_K_M"
1818
+ },
1819
+ "model.layers.21.input_layernorm.weight": {
1820
+ "shardIndex": 12,
1821
+ "offset": 25767936,
1822
+ "size": 2304,
1823
+ "shape": [
1824
+ 1152
1825
+ ],
1826
+ "dtype": "BF16"
1827
+ },
1828
+ "model.layers.21.mlp.down_proj.weight": {
1829
+ "shardIndex": 12,
1830
+ "offset": 25772032,
1831
+ "size": 4478976,
1832
+ "shape": [
1833
+ 1152,
1834
+ 6912
1835
+ ],
1836
+ "dtype": "Q4_K_M"
1837
+ },
1838
+ "model.layers.21.mlp.gate_up_proj.weight": {
1839
+ "shardIndex": 12,
1840
+ "offset": 30253056,
1841
+ "size": 8957952,
1842
+ "shape": [
1843
+ 13824,
1844
+ 1152
1845
+ ],
1846
+ "dtype": "Q4_K_M"
1847
+ },
1848
+ "model.layers.21.post_attention_layernorm.weight": {
1849
+ "shardIndex": 12,
1850
+ "offset": 39211008,
1851
+ "size": 2304,
1852
+ "shape": [
1853
+ 1152
1854
+ ],
1855
+ "dtype": "BF16"
1856
+ },
1857
+ "model.layers.21.post_feedforward_layernorm.weight": {
1858
+ "shardIndex": 12,
1859
+ "offset": 39215104,
1860
+ "size": 2304,
1861
+ "shape": [
1862
+ 1152
1863
+ ],
1864
+ "dtype": "BF16"
1865
+ },
1866
+ "model.layers.21.pre_feedforward_layernorm.weight": {
1867
+ "shardIndex": 12,
1868
+ "offset": 39219200,
1869
+ "size": 2304,
1870
+ "shape": [
1871
+ 1152
1872
+ ],
1873
+ "dtype": "BF16"
1874
+ },
1875
+ "model.layers.21.self_attn.k_norm.weight": {
1876
+ "shardIndex": 12,
1877
+ "offset": 39223296,
1878
+ "size": 512,
1879
+ "shape": [
1880
+ 256
1881
+ ],
1882
+ "dtype": "BF16"
1883
+ },
1884
+ "model.layers.21.self_attn.k_proj.weight": {
1885
+ "shardIndex": 12,
1886
+ "offset": 39227392,
1887
+ "size": 165888,
1888
+ "shape": [
1889
+ 256,
1890
+ 1152
1891
+ ],
1892
+ "dtype": "Q4_K_M"
1893
+ },
1894
+ "model.layers.21.self_attn.o_proj.weight": {
1895
+ "shardIndex": 12,
1896
+ "offset": 39395328,
1897
+ "size": 663552,
1898
+ "shape": [
1899
+ 1152,
1900
+ 1024
1901
+ ],
1902
+ "dtype": "Q4_K_M"
1903
+ },
1904
+ "model.layers.21.self_attn.q_norm.weight": {
1905
+ "shardIndex": 12,
1906
+ "offset": 40058880,
1907
+ "size": 512,
1908
+ "shape": [
1909
+ 256
1910
+ ],
1911
+ "dtype": "BF16"
1912
+ },
1913
+ "model.layers.21.self_attn.q_proj.weight": {
1914
+ "shardIndex": 12,
1915
+ "offset": 40062976,
1916
+ "size": 663552,
1917
+ "shape": [
1918
+ 1024,
1919
+ 1152
1920
+ ],
1921
+ "dtype": "Q4_K_M"
1922
+ },
1923
+ "model.layers.21.self_attn.v_proj.weight": {
1924
+ "shardIndex": 12,
1925
+ "offset": 40726528,
1926
+ "size": 165888,
1927
+ "shape": [
1928
+ 256,
1929
+ 1152
1930
+ ],
1931
+ "dtype": "Q4_K_M"
1932
+ },
1933
+ "model.layers.22.input_layernorm.weight": {
1934
+ "shardIndex": 12,
1935
+ "offset": 40894464,
1936
+ "size": 2304,
1937
+ "shape": [
1938
+ 1152
1939
+ ],
1940
+ "dtype": "BF16"
1941
+ },
1942
+ "model.layers.22.mlp.down_proj.weight": {
1943
+ "shardIndex": 12,
1944
+ "offset": 40898560,
1945
+ "size": 4478976,
1946
+ "shape": [
1947
+ 1152,
1948
+ 6912
1949
+ ],
1950
+ "dtype": "Q4_K_M"
1951
+ },
1952
+ "model.layers.22.mlp.gate_up_proj.weight": {
1953
+ "shardIndex": 12,
1954
+ "offset": 45379584,
1955
+ "size": 8957952,
1956
+ "shape": [
1957
+ 13824,
1958
+ 1152
1959
+ ],
1960
+ "dtype": "Q4_K_M"
1961
+ },
1962
+ "model.layers.22.post_attention_layernorm.weight": {
1963
+ "shardIndex": 12,
1964
+ "offset": 54337536,
1965
+ "size": 2304,
1966
+ "shape": [
1967
+ 1152
1968
+ ],
1969
+ "dtype": "BF16"
1970
+ },
1971
+ "model.layers.22.post_feedforward_layernorm.weight": {
1972
+ "shardIndex": 12,
1973
+ "offset": 54341632,
1974
+ "size": 2304,
1975
+ "shape": [
1976
+ 1152
1977
+ ],
1978
+ "dtype": "BF16"
1979
+ },
1980
+ "model.layers.22.pre_feedforward_layernorm.weight": {
1981
+ "shardIndex": 12,
1982
+ "offset": 54345728,
1983
+ "size": 2304,
1984
+ "shape": [
1985
+ 1152
1986
+ ],
1987
+ "dtype": "BF16"
1988
+ },
1989
+ "model.layers.22.self_attn.k_norm.weight": {
1990
+ "shardIndex": 12,
1991
+ "offset": 54349824,
1992
+ "size": 512,
1993
+ "shape": [
1994
+ 256
1995
+ ],
1996
+ "dtype": "BF16"
1997
+ },
1998
+ "model.layers.22.self_attn.k_proj.weight": {
1999
+ "shardIndex": 12,
2000
+ "offset": 54353920,
2001
+ "size": 165888,
2002
+ "shape": [
2003
+ 256,
2004
+ 1152
2005
+ ],
2006
+ "dtype": "Q4_K_M"
2007
+ },
2008
+ "model.layers.22.self_attn.o_proj.weight": {
2009
+ "shardIndex": 12,
2010
+ "offset": 54521856,
2011
+ "size": 663552,
2012
+ "shape": [
2013
+ 1152,
2014
+ 1024
2015
+ ],
2016
+ "dtype": "Q4_K_M"
2017
+ },
2018
+ "model.layers.22.self_attn.q_norm.weight": {
2019
+ "shardIndex": 12,
2020
+ "offset": 55185408,
2021
+ "size": 512,
2022
+ "shape": [
2023
+ 256
2024
+ ],
2025
+ "dtype": "BF16"
2026
+ },
2027
+ "model.layers.22.self_attn.q_proj.weight": {
2028
+ "shardIndex": 12,
2029
+ "offset": 55189504,
2030
+ "size": 663552,
2031
+ "shape": [
2032
+ 1024,
2033
+ 1152
2034
+ ],
2035
+ "dtype": "Q4_K_M"
2036
+ },
2037
+ "model.layers.22.self_attn.v_proj.weight": {
2038
+ "shardIndex": 12,
2039
+ "offset": 55853056,
2040
+ "size": 165888,
2041
+ "shape": [
2042
+ 256,
2043
+ 1152
2044
+ ],
2045
+ "dtype": "Q4_K_M"
2046
+ },
2047
+ "model.layers.23.input_layernorm.weight": {
2048
+ "shardIndex": 12,
2049
+ "offset": 56020992,
2050
+ "size": 2304,
2051
+ "shape": [
2052
+ 1152
2053
+ ],
2054
+ "dtype": "BF16"
2055
+ },
2056
+ "model.layers.23.mlp.down_proj.weight": {
2057
+ "shardIndex": 12,
2058
+ "offset": 56025088,
2059
+ "size": 4478976,
2060
+ "shape": [
2061
+ 1152,
2062
+ 6912
2063
+ ],
2064
+ "dtype": "Q4_K_M"
2065
+ },
2066
+ "model.layers.23.mlp.gate_up_proj.weight": {
2067
+ "shardIndex": 13,
2068
+ "offset": 0,
2069
+ "size": 8957952,
2070
+ "shape": [
2071
+ 13824,
2072
+ 1152
2073
+ ],
2074
+ "dtype": "Q4_K_M"
2075
+ },
2076
+ "model.layers.23.post_attention_layernorm.weight": {
2077
+ "shardIndex": 13,
2078
+ "offset": 8957952,
2079
+ "size": 2304,
2080
+ "shape": [
2081
+ 1152
2082
+ ],
2083
+ "dtype": "BF16"
2084
+ },
2085
+ "model.layers.23.post_feedforward_layernorm.weight": {
2086
+ "shardIndex": 13,
2087
+ "offset": 8962048,
2088
+ "size": 2304,
2089
+ "shape": [
2090
+ 1152
2091
+ ],
2092
+ "dtype": "BF16"
2093
+ },
2094
+ "model.layers.23.pre_feedforward_layernorm.weight": {
2095
+ "shardIndex": 13,
2096
+ "offset": 8966144,
2097
+ "size": 2304,
2098
+ "shape": [
2099
+ 1152
2100
+ ],
2101
+ "dtype": "BF16"
2102
+ },
2103
+ "model.layers.23.self_attn.k_norm.weight": {
2104
+ "shardIndex": 13,
2105
+ "offset": 8970240,
2106
+ "size": 512,
2107
+ "shape": [
2108
+ 256
2109
+ ],
2110
+ "dtype": "BF16"
2111
+ },
2112
+ "model.layers.23.self_attn.k_proj.weight": {
2113
+ "shardIndex": 13,
2114
+ "offset": 8974336,
2115
+ "size": 165888,
2116
+ "shape": [
2117
+ 256,
2118
+ 1152
2119
+ ],
2120
+ "dtype": "Q4_K_M"
2121
+ },
2122
+ "model.layers.23.self_attn.o_proj.weight": {
2123
+ "shardIndex": 13,
2124
+ "offset": 9142272,
2125
+ "size": 663552,
2126
+ "shape": [
2127
+ 1152,
2128
+ 1024
2129
+ ],
2130
+ "dtype": "Q4_K_M"
2131
+ },
2132
+ "model.layers.23.self_attn.q_norm.weight": {
2133
+ "shardIndex": 13,
2134
+ "offset": 9805824,
2135
+ "size": 512,
2136
+ "shape": [
2137
+ 256
2138
+ ],
2139
+ "dtype": "BF16"
2140
+ },
2141
+ "model.layers.23.self_attn.q_proj.weight": {
2142
+ "shardIndex": 13,
2143
+ "offset": 9809920,
2144
+ "size": 663552,
2145
+ "shape": [
2146
+ 1024,
2147
+ 1152
2148
+ ],
2149
+ "dtype": "Q4_K_M"
2150
+ },
2151
+ "model.layers.23.self_attn.v_proj.weight": {
2152
+ "shardIndex": 13,
2153
+ "offset": 10473472,
2154
+ "size": 165888,
2155
+ "shape": [
2156
+ 256,
2157
+ 1152
2158
+ ],
2159
+ "dtype": "Q4_K_M"
2160
+ },
2161
+ "model.layers.24.input_layernorm.weight": {
2162
+ "shardIndex": 13,
2163
+ "offset": 10641408,
2164
+ "size": 2304,
2165
+ "shape": [
2166
+ 1152
2167
+ ],
2168
+ "dtype": "BF16"
2169
+ },
2170
+ "model.layers.24.mlp.down_proj.weight": {
2171
+ "shardIndex": 13,
2172
+ "offset": 10645504,
2173
+ "size": 4478976,
2174
+ "shape": [
2175
+ 1152,
2176
+ 6912
2177
+ ],
2178
+ "dtype": "Q4_K_M"
2179
+ },
2180
+ "model.layers.24.mlp.gate_up_proj.weight": {
2181
+ "shardIndex": 13,
2182
+ "offset": 15126528,
2183
+ "size": 8957952,
2184
+ "shape": [
2185
+ 13824,
2186
+ 1152
2187
+ ],
2188
+ "dtype": "Q4_K_M"
2189
+ },
2190
+ "model.layers.24.post_attention_layernorm.weight": {
2191
+ "shardIndex": 13,
2192
+ "offset": 24084480,
2193
+ "size": 2304,
2194
+ "shape": [
2195
+ 1152
2196
+ ],
2197
+ "dtype": "BF16"
2198
+ },
2199
+ "model.layers.24.post_feedforward_layernorm.weight": {
2200
+ "shardIndex": 13,
2201
+ "offset": 24088576,
2202
+ "size": 2304,
2203
+ "shape": [
2204
+ 1152
2205
+ ],
2206
+ "dtype": "BF16"
2207
+ },
2208
+ "model.layers.24.pre_feedforward_layernorm.weight": {
2209
+ "shardIndex": 13,
2210
+ "offset": 24092672,
2211
+ "size": 2304,
2212
+ "shape": [
2213
+ 1152
2214
+ ],
2215
+ "dtype": "BF16"
2216
+ },
2217
+ "model.layers.24.self_attn.k_norm.weight": {
2218
+ "shardIndex": 13,
2219
+ "offset": 24096768,
2220
+ "size": 512,
2221
+ "shape": [
2222
+ 256
2223
+ ],
2224
+ "dtype": "BF16"
2225
+ },
2226
+ "model.layers.24.self_attn.k_proj.weight": {
2227
+ "shardIndex": 13,
2228
+ "offset": 24100864,
2229
+ "size": 165888,
2230
+ "shape": [
2231
+ 256,
2232
+ 1152
2233
+ ],
2234
+ "dtype": "Q4_K_M"
2235
+ },
2236
+ "model.layers.24.self_attn.o_proj.weight": {
2237
+ "shardIndex": 13,
2238
+ "offset": 24268800,
2239
+ "size": 663552,
2240
+ "shape": [
2241
+ 1152,
2242
+ 1024
2243
+ ],
2244
+ "dtype": "Q4_K_M"
2245
+ },
2246
+ "model.layers.24.self_attn.q_norm.weight": {
2247
+ "shardIndex": 13,
2248
+ "offset": 24932352,
2249
+ "size": 512,
2250
+ "shape": [
2251
+ 256
2252
+ ],
2253
+ "dtype": "BF16"
2254
+ },
2255
+ "model.layers.24.self_attn.q_proj.weight": {
2256
+ "shardIndex": 13,
2257
+ "offset": 24936448,
2258
+ "size": 663552,
2259
+ "shape": [
2260
+ 1024,
2261
+ 1152
2262
+ ],
2263
+ "dtype": "Q4_K_M"
2264
+ },
2265
+ "model.layers.24.self_attn.v_proj.weight": {
2266
+ "shardIndex": 13,
2267
+ "offset": 25600000,
2268
+ "size": 165888,
2269
+ "shape": [
2270
+ 256,
2271
+ 1152
2272
+ ],
2273
+ "dtype": "Q4_K_M"
2274
+ },
2275
+ "model.layers.25.input_layernorm.weight": {
2276
+ "shardIndex": 13,
2277
+ "offset": 25767936,
2278
+ "size": 2304,
2279
+ "shape": [
2280
+ 1152
2281
+ ],
2282
+ "dtype": "BF16"
2283
+ },
2284
+ "model.layers.25.mlp.down_proj.weight": {
2285
+ "shardIndex": 13,
2286
+ "offset": 25772032,
2287
+ "size": 4478976,
2288
+ "shape": [
2289
+ 1152,
2290
+ 6912
2291
+ ],
2292
+ "dtype": "Q4_K_M"
2293
+ },
2294
+ "model.layers.25.mlp.gate_up_proj.weight": {
2295
+ "shardIndex": 13,
2296
+ "offset": 30253056,
2297
+ "size": 8957952,
2298
+ "shape": [
2299
+ 13824,
2300
+ 1152
2301
+ ],
2302
+ "dtype": "Q4_K_M"
2303
+ },
2304
+ "model.layers.25.post_attention_layernorm.weight": {
2305
+ "shardIndex": 13,
2306
+ "offset": 39211008,
2307
+ "size": 2304,
2308
+ "shape": [
2309
+ 1152
2310
+ ],
2311
+ "dtype": "BF16"
2312
+ },
2313
+ "model.layers.25.post_feedforward_layernorm.weight": {
2314
+ "shardIndex": 13,
2315
+ "offset": 39215104,
2316
+ "size": 2304,
2317
+ "shape": [
2318
+ 1152
2319
+ ],
2320
+ "dtype": "BF16"
2321
+ },
2322
+ "model.layers.25.pre_feedforward_layernorm.weight": {
2323
+ "shardIndex": 13,
2324
+ "offset": 39219200,
2325
+ "size": 2304,
2326
+ "shape": [
2327
+ 1152
2328
+ ],
2329
+ "dtype": "BF16"
2330
+ },
2331
+ "model.layers.25.self_attn.k_norm.weight": {
2332
+ "shardIndex": 13,
2333
+ "offset": 39223296,
2334
+ "size": 512,
2335
+ "shape": [
2336
+ 256
2337
+ ],
2338
+ "dtype": "BF16"
2339
+ },
2340
+ "model.layers.25.self_attn.k_proj.weight": {
2341
+ "shardIndex": 13,
2342
+ "offset": 39227392,
2343
+ "size": 165888,
2344
+ "shape": [
2345
+ 256,
2346
+ 1152
2347
+ ],
2348
+ "dtype": "Q4_K_M"
2349
+ },
2350
+ "model.layers.25.self_attn.o_proj.weight": {
2351
+ "shardIndex": 13,
2352
+ "offset": 39395328,
2353
+ "size": 663552,
2354
+ "shape": [
2355
+ 1152,
2356
+ 1024
2357
+ ],
2358
+ "dtype": "Q4_K_M"
2359
+ },
2360
+ "model.layers.25.self_attn.q_norm.weight": {
2361
+ "shardIndex": 13,
2362
+ "offset": 40058880,
2363
+ "size": 512,
2364
+ "shape": [
2365
+ 256
2366
+ ],
2367
+ "dtype": "BF16"
2368
+ },
2369
+ "model.layers.25.self_attn.q_proj.weight": {
2370
+ "shardIndex": 13,
2371
+ "offset": 40062976,
2372
+ "size": 663552,
2373
+ "shape": [
2374
+ 1024,
2375
+ 1152
2376
+ ],
2377
+ "dtype": "Q4_K_M"
2378
+ },
2379
+ "model.layers.25.self_attn.v_proj.weight": {
2380
+ "shardIndex": 13,
2381
+ "offset": 40726528,
2382
+ "size": 165888,
2383
+ "shape": [
2384
+ 256,
2385
+ 1152
2386
+ ],
2387
+ "dtype": "Q4_K_M"
2388
+ },
2389
+ "model.layers.3.input_layernorm.weight": {
2390
+ "shardIndex": 13,
2391
+ "offset": 40894464,
2392
+ "size": 2304,
2393
+ "shape": [
2394
+ 1152
2395
+ ],
2396
+ "dtype": "BF16"
2397
+ },
2398
+ "model.layers.3.mlp.down_proj.weight": {
2399
+ "shardIndex": 13,
2400
+ "offset": 40898560,
2401
+ "size": 4478976,
2402
+ "shape": [
2403
+ 1152,
2404
+ 6912
2405
+ ],
2406
+ "dtype": "Q4_K_M"
2407
+ },
2408
+ "model.layers.3.mlp.gate_up_proj.weight": {
2409
+ "shardIndex": 13,
2410
+ "offset": 45379584,
2411
+ "size": 8957952,
2412
+ "shape": [
2413
+ 13824,
2414
+ 1152
2415
+ ],
2416
+ "dtype": "Q4_K_M"
2417
+ },
2418
+ "model.layers.3.post_attention_layernorm.weight": {
2419
+ "shardIndex": 13,
2420
+ "offset": 54337536,
2421
+ "size": 2304,
2422
+ "shape": [
2423
+ 1152
2424
+ ],
2425
+ "dtype": "BF16"
2426
+ },
2427
+ "model.layers.3.post_feedforward_layernorm.weight": {
2428
+ "shardIndex": 13,
2429
+ "offset": 54341632,
2430
+ "size": 2304,
2431
+ "shape": [
2432
+ 1152
2433
+ ],
2434
+ "dtype": "BF16"
2435
+ },
2436
+ "model.layers.3.pre_feedforward_layernorm.weight": {
2437
+ "shardIndex": 13,
2438
+ "offset": 54345728,
2439
+ "size": 2304,
2440
+ "shape": [
2441
+ 1152
2442
+ ],
2443
+ "dtype": "BF16"
2444
+ },
2445
+ "model.layers.3.self_attn.k_norm.weight": {
2446
+ "shardIndex": 13,
2447
+ "offset": 54349824,
2448
+ "size": 512,
2449
+ "shape": [
2450
+ 256
2451
+ ],
2452
+ "dtype": "BF16"
2453
+ },
2454
+ "model.layers.3.self_attn.k_proj.weight": {
2455
+ "shardIndex": 13,
2456
+ "offset": 54353920,
2457
+ "size": 165888,
2458
+ "shape": [
2459
+ 256,
2460
+ 1152
2461
+ ],
2462
+ "dtype": "Q4_K_M"
2463
+ },
2464
+ "model.layers.3.self_attn.o_proj.weight": {
2465
+ "shardIndex": 13,
2466
+ "offset": 54521856,
2467
+ "size": 663552,
2468
+ "shape": [
2469
+ 1152,
2470
+ 1024
2471
+ ],
2472
+ "dtype": "Q4_K_M"
2473
+ },
2474
+ "model.layers.3.self_attn.q_norm.weight": {
2475
+ "shardIndex": 13,
2476
+ "offset": 55185408,
2477
+ "size": 512,
2478
+ "shape": [
2479
+ 256
2480
+ ],
2481
+ "dtype": "BF16"
2482
+ },
2483
+ "model.layers.3.self_attn.q_proj.weight": {
2484
+ "shardIndex": 13,
2485
+ "offset": 55189504,
2486
+ "size": 663552,
2487
+ "shape": [
2488
+ 1024,
2489
+ 1152
2490
+ ],
2491
+ "dtype": "Q4_K_M"
2492
+ },
2493
+ "model.layers.3.self_attn.v_proj.weight": {
2494
+ "shardIndex": 13,
2495
+ "offset": 55853056,
2496
+ "size": 165888,
2497
+ "shape": [
2498
+ 256,
2499
+ 1152
2500
+ ],
2501
+ "dtype": "Q4_K_M"
2502
+ },
2503
+ "model.layers.4.input_layernorm.weight": {
2504
+ "shardIndex": 13,
2505
+ "offset": 56020992,
2506
+ "size": 2304,
2507
+ "shape": [
2508
+ 1152
2509
+ ],
2510
+ "dtype": "BF16"
2511
+ },
2512
+ "model.layers.4.mlp.down_proj.weight": {
2513
+ "shardIndex": 13,
2514
+ "offset": 56025088,
2515
+ "size": 4478976,
2516
+ "shape": [
2517
+ 1152,
2518
+ 6912
2519
+ ],
2520
+ "dtype": "Q4_K_M"
2521
+ },
2522
+ "model.layers.4.mlp.gate_up_proj.weight": {
2523
+ "shardIndex": 14,
2524
+ "offset": 0,
2525
+ "size": 8957952,
2526
+ "shape": [
2527
+ 13824,
2528
+ 1152
2529
+ ],
2530
+ "dtype": "Q4_K_M"
2531
+ },
2532
+ "model.layers.4.post_attention_layernorm.weight": {
2533
+ "shardIndex": 14,
2534
+ "offset": 8957952,
2535
+ "size": 2304,
2536
+ "shape": [
2537
+ 1152
2538
+ ],
2539
+ "dtype": "BF16"
2540
+ },
2541
+ "model.layers.4.post_feedforward_layernorm.weight": {
2542
+ "shardIndex": 14,
2543
+ "offset": 8962048,
2544
+ "size": 2304,
2545
+ "shape": [
2546
+ 1152
2547
+ ],
2548
+ "dtype": "BF16"
2549
+ },
2550
+ "model.layers.4.pre_feedforward_layernorm.weight": {
2551
+ "shardIndex": 14,
2552
+ "offset": 8966144,
2553
+ "size": 2304,
2554
+ "shape": [
2555
+ 1152
2556
+ ],
2557
+ "dtype": "BF16"
2558
+ },
2559
+ "model.layers.4.self_attn.k_norm.weight": {
2560
+ "shardIndex": 14,
2561
+ "offset": 8970240,
2562
+ "size": 512,
2563
+ "shape": [
2564
+ 256
2565
+ ],
2566
+ "dtype": "BF16"
2567
+ },
2568
+ "model.layers.4.self_attn.k_proj.weight": {
2569
+ "shardIndex": 14,
2570
+ "offset": 8974336,
2571
+ "size": 165888,
2572
+ "shape": [
2573
+ 256,
2574
+ 1152
2575
+ ],
2576
+ "dtype": "Q4_K_M"
2577
+ },
2578
+ "model.layers.4.self_attn.o_proj.weight": {
2579
+ "shardIndex": 14,
2580
+ "offset": 9142272,
2581
+ "size": 663552,
2582
+ "shape": [
2583
+ 1152,
2584
+ 1024
2585
+ ],
2586
+ "dtype": "Q4_K_M"
2587
+ },
2588
+ "model.layers.4.self_attn.q_norm.weight": {
2589
+ "shardIndex": 14,
2590
+ "offset": 9805824,
2591
+ "size": 512,
2592
+ "shape": [
2593
+ 256
2594
+ ],
2595
+ "dtype": "BF16"
2596
+ },
2597
+ "model.layers.4.self_attn.q_proj.weight": {
2598
+ "shardIndex": 14,
2599
+ "offset": 9809920,
2600
+ "size": 663552,
2601
+ "shape": [
2602
+ 1024,
2603
+ 1152
2604
+ ],
2605
+ "dtype": "Q4_K_M"
2606
+ },
2607
+ "model.layers.4.self_attn.v_proj.weight": {
2608
+ "shardIndex": 14,
2609
+ "offset": 10473472,
2610
+ "size": 165888,
2611
+ "shape": [
2612
+ 256,
2613
+ 1152
2614
+ ],
2615
+ "dtype": "Q4_K_M"
2616
+ },
2617
+ "model.layers.5.input_layernorm.weight": {
2618
+ "shardIndex": 14,
2619
+ "offset": 10641408,
2620
+ "size": 2304,
2621
+ "shape": [
2622
+ 1152
2623
+ ],
2624
+ "dtype": "BF16"
2625
+ },
2626
+ "model.layers.5.mlp.down_proj.weight": {
2627
+ "shardIndex": 14,
2628
+ "offset": 10645504,
2629
+ "size": 4478976,
2630
+ "shape": [
2631
+ 1152,
2632
+ 6912
2633
+ ],
2634
+ "dtype": "Q4_K_M"
2635
+ },
2636
+ "model.layers.5.mlp.gate_up_proj.weight": {
2637
+ "shardIndex": 14,
2638
+ "offset": 15126528,
2639
+ "size": 8957952,
2640
+ "shape": [
2641
+ 13824,
2642
+ 1152
2643
+ ],
2644
+ "dtype": "Q4_K_M"
2645
+ },
2646
+ "model.layers.5.post_attention_layernorm.weight": {
2647
+ "shardIndex": 14,
2648
+ "offset": 24084480,
2649
+ "size": 2304,
2650
+ "shape": [
2651
+ 1152
2652
+ ],
2653
+ "dtype": "BF16"
2654
+ },
2655
+ "model.layers.5.post_feedforward_layernorm.weight": {
2656
+ "shardIndex": 14,
2657
+ "offset": 24088576,
2658
+ "size": 2304,
2659
+ "shape": [
2660
+ 1152
2661
+ ],
2662
+ "dtype": "BF16"
2663
+ },
2664
+ "model.layers.5.pre_feedforward_layernorm.weight": {
2665
+ "shardIndex": 14,
2666
+ "offset": 24092672,
2667
+ "size": 2304,
2668
+ "shape": [
2669
+ 1152
2670
+ ],
2671
+ "dtype": "BF16"
2672
+ },
2673
+ "model.layers.5.self_attn.k_norm.weight": {
2674
+ "shardIndex": 14,
2675
+ "offset": 24096768,
2676
+ "size": 512,
2677
+ "shape": [
2678
+ 256
2679
+ ],
2680
+ "dtype": "BF16"
2681
+ },
2682
+ "model.layers.5.self_attn.k_proj.weight": {
2683
+ "shardIndex": 14,
2684
+ "offset": 24100864,
2685
+ "size": 165888,
2686
+ "shape": [
2687
+ 256,
2688
+ 1152
2689
+ ],
2690
+ "dtype": "Q4_K_M"
2691
+ },
2692
+ "model.layers.5.self_attn.o_proj.weight": {
2693
+ "shardIndex": 14,
2694
+ "offset": 24268800,
2695
+ "size": 663552,
2696
+ "shape": [
2697
+ 1152,
2698
+ 1024
2699
+ ],
2700
+ "dtype": "Q4_K_M"
2701
+ },
2702
+ "model.layers.5.self_attn.q_norm.weight": {
2703
+ "shardIndex": 14,
2704
+ "offset": 24932352,
2705
+ "size": 512,
2706
+ "shape": [
2707
+ 256
2708
+ ],
2709
+ "dtype": "BF16"
2710
+ },
2711
+ "model.layers.5.self_attn.q_proj.weight": {
2712
+ "shardIndex": 14,
2713
+ "offset": 24936448,
2714
+ "size": 663552,
2715
+ "shape": [
2716
+ 1024,
2717
+ 1152
2718
+ ],
2719
+ "dtype": "Q4_K_M"
2720
+ },
2721
+ "model.layers.5.self_attn.v_proj.weight": {
2722
+ "shardIndex": 14,
2723
+ "offset": 25600000,
2724
+ "size": 165888,
2725
+ "shape": [
2726
+ 256,
2727
+ 1152
2728
+ ],
2729
+ "dtype": "Q4_K_M"
2730
+ },
2731
+ "model.layers.6.input_layernorm.weight": {
2732
+ "shardIndex": 14,
2733
+ "offset": 25767936,
2734
+ "size": 2304,
2735
+ "shape": [
2736
+ 1152
2737
+ ],
2738
+ "dtype": "BF16"
2739
+ },
2740
+ "model.layers.6.mlp.down_proj.weight": {
2741
+ "shardIndex": 14,
2742
+ "offset": 25772032,
2743
+ "size": 4478976,
2744
+ "shape": [
2745
+ 1152,
2746
+ 6912
2747
+ ],
2748
+ "dtype": "Q4_K_M"
2749
+ },
2750
+ "model.layers.6.mlp.gate_up_proj.weight": {
2751
+ "shardIndex": 14,
2752
+ "offset": 30253056,
2753
+ "size": 8957952,
2754
+ "shape": [
2755
+ 13824,
2756
+ 1152
2757
+ ],
2758
+ "dtype": "Q4_K_M"
2759
+ },
2760
+ "model.layers.6.post_attention_layernorm.weight": {
2761
+ "shardIndex": 14,
2762
+ "offset": 39211008,
2763
+ "size": 2304,
2764
+ "shape": [
2765
+ 1152
2766
+ ],
2767
+ "dtype": "BF16"
2768
+ },
2769
+ "model.layers.6.post_feedforward_layernorm.weight": {
2770
+ "shardIndex": 14,
2771
+ "offset": 39215104,
2772
+ "size": 2304,
2773
+ "shape": [
2774
+ 1152
2775
+ ],
2776
+ "dtype": "BF16"
2777
+ },
2778
+ "model.layers.6.pre_feedforward_layernorm.weight": {
2779
+ "shardIndex": 14,
2780
+ "offset": 39219200,
2781
+ "size": 2304,
2782
+ "shape": [
2783
+ 1152
2784
+ ],
2785
+ "dtype": "BF16"
2786
+ },
2787
+ "model.layers.6.self_attn.k_norm.weight": {
2788
+ "shardIndex": 14,
2789
+ "offset": 39223296,
2790
+ "size": 512,
2791
+ "shape": [
2792
+ 256
2793
+ ],
2794
+ "dtype": "BF16"
2795
+ },
2796
+ "model.layers.6.self_attn.k_proj.weight": {
2797
+ "shardIndex": 14,
2798
+ "offset": 39227392,
2799
+ "size": 165888,
2800
+ "shape": [
2801
+ 256,
2802
+ 1152
2803
+ ],
2804
+ "dtype": "Q4_K_M"
2805
+ },
2806
+ "model.layers.6.self_attn.o_proj.weight": {
2807
+ "shardIndex": 14,
2808
+ "offset": 39395328,
2809
+ "size": 663552,
2810
+ "shape": [
2811
+ 1152,
2812
+ 1024
2813
+ ],
2814
+ "dtype": "Q4_K_M"
2815
+ },
2816
+ "model.layers.6.self_attn.q_norm.weight": {
2817
+ "shardIndex": 14,
2818
+ "offset": 40058880,
2819
+ "size": 512,
2820
+ "shape": [
2821
+ 256
2822
+ ],
2823
+ "dtype": "BF16"
2824
+ },
2825
+ "model.layers.6.self_attn.q_proj.weight": {
2826
+ "shardIndex": 14,
2827
+ "offset": 40062976,
2828
+ "size": 663552,
2829
+ "shape": [
2830
+ 1024,
2831
+ 1152
2832
+ ],
2833
+ "dtype": "Q4_K_M"
2834
+ },
2835
+ "model.layers.6.self_attn.v_proj.weight": {
2836
+ "shardIndex": 14,
2837
+ "offset": 40726528,
2838
+ "size": 165888,
2839
+ "shape": [
2840
+ 256,
2841
+ 1152
2842
+ ],
2843
+ "dtype": "Q4_K_M"
2844
+ },
2845
+ "model.layers.7.input_layernorm.weight": {
2846
+ "shardIndex": 14,
2847
+ "offset": 40894464,
2848
+ "size": 2304,
2849
+ "shape": [
2850
+ 1152
2851
+ ],
2852
+ "dtype": "BF16"
2853
+ },
2854
+ "model.layers.7.mlp.down_proj.weight": {
2855
+ "shardIndex": 14,
2856
+ "offset": 40898560,
2857
+ "size": 4478976,
2858
+ "shape": [
2859
+ 1152,
2860
+ 6912
2861
+ ],
2862
+ "dtype": "Q4_K_M"
2863
+ },
2864
+ "model.layers.7.mlp.gate_up_proj.weight": {
2865
+ "shardIndex": 14,
2866
+ "offset": 45379584,
2867
+ "size": 8957952,
2868
+ "shape": [
2869
+ 13824,
2870
+ 1152
2871
+ ],
2872
+ "dtype": "Q4_K_M"
2873
+ },
2874
+ "model.layers.7.post_attention_layernorm.weight": {
2875
+ "shardIndex": 14,
2876
+ "offset": 54337536,
2877
+ "size": 2304,
2878
+ "shape": [
2879
+ 1152
2880
+ ],
2881
+ "dtype": "BF16"
2882
+ },
2883
+ "model.layers.7.post_feedforward_layernorm.weight": {
2884
+ "shardIndex": 14,
2885
+ "offset": 54341632,
2886
+ "size": 2304,
2887
+ "shape": [
2888
+ 1152
2889
+ ],
2890
+ "dtype": "BF16"
2891
+ },
2892
+ "model.layers.7.pre_feedforward_layernorm.weight": {
2893
+ "shardIndex": 14,
2894
+ "offset": 54345728,
2895
+ "size": 2304,
2896
+ "shape": [
2897
+ 1152
2898
+ ],
2899
+ "dtype": "BF16"
2900
+ },
2901
+ "model.layers.7.self_attn.k_norm.weight": {
2902
+ "shardIndex": 14,
2903
+ "offset": 54349824,
2904
+ "size": 512,
2905
+ "shape": [
2906
+ 256
2907
+ ],
2908
+ "dtype": "BF16"
2909
+ },
2910
+ "model.layers.7.self_attn.k_proj.weight": {
2911
+ "shardIndex": 14,
2912
+ "offset": 54353920,
2913
+ "size": 165888,
2914
+ "shape": [
2915
+ 256,
2916
+ 1152
2917
+ ],
2918
+ "dtype": "Q4_K_M"
2919
+ },
2920
+ "model.layers.7.self_attn.o_proj.weight": {
2921
+ "shardIndex": 14,
2922
+ "offset": 54521856,
2923
+ "size": 663552,
2924
+ "shape": [
2925
+ 1152,
2926
+ 1024
2927
+ ],
2928
+ "dtype": "Q4_K_M"
2929
+ },
2930
+ "model.layers.7.self_attn.q_norm.weight": {
2931
+ "shardIndex": 14,
2932
+ "offset": 55185408,
2933
+ "size": 512,
2934
+ "shape": [
2935
+ 256
2936
+ ],
2937
+ "dtype": "BF16"
2938
+ },
2939
+ "model.layers.7.self_attn.q_proj.weight": {
2940
+ "shardIndex": 14,
2941
+ "offset": 55189504,
2942
+ "size": 663552,
2943
+ "shape": [
2944
+ 1024,
2945
+ 1152
2946
+ ],
2947
+ "dtype": "Q4_K_M"
2948
+ },
2949
+ "model.layers.7.self_attn.v_proj.weight": {
2950
+ "shardIndex": 14,
2951
+ "offset": 55853056,
2952
+ "size": 165888,
2953
+ "shape": [
2954
+ 256,
2955
+ 1152
2956
+ ],
2957
+ "dtype": "Q4_K_M"
2958
+ },
2959
+ "model.layers.8.input_layernorm.weight": {
2960
+ "shardIndex": 14,
2961
+ "offset": 56020992,
2962
+ "size": 2304,
2963
+ "shape": [
2964
+ 1152
2965
+ ],
2966
+ "dtype": "BF16"
2967
+ },
2968
+ "model.layers.8.mlp.down_proj.weight": {
2969
+ "shardIndex": 14,
2970
+ "offset": 56025088,
2971
+ "size": 4478976,
2972
+ "shape": [
2973
+ 1152,
2974
+ 6912
2975
+ ],
2976
+ "dtype": "Q4_K_M"
2977
+ },
2978
+ "model.layers.8.mlp.gate_up_proj.weight": {
2979
+ "shardIndex": 15,
2980
+ "offset": 0,
2981
+ "size": 8957952,
2982
+ "shape": [
2983
+ 13824,
2984
+ 1152
2985
+ ],
2986
+ "dtype": "Q4_K_M"
2987
+ },
2988
+ "model.layers.8.post_attention_layernorm.weight": {
2989
+ "shardIndex": 15,
2990
+ "offset": 8957952,
2991
+ "size": 2304,
2992
+ "shape": [
2993
+ 1152
2994
+ ],
2995
+ "dtype": "BF16"
2996
+ },
2997
+ "model.layers.8.post_feedforward_layernorm.weight": {
2998
+ "shardIndex": 15,
2999
+ "offset": 8962048,
3000
+ "size": 2304,
3001
+ "shape": [
3002
+ 1152
3003
+ ],
3004
+ "dtype": "BF16"
3005
+ },
3006
+ "model.layers.8.pre_feedforward_layernorm.weight": {
3007
+ "shardIndex": 15,
3008
+ "offset": 8966144,
3009
+ "size": 2304,
3010
+ "shape": [
3011
+ 1152
3012
+ ],
3013
+ "dtype": "BF16"
3014
+ },
3015
+ "model.layers.8.self_attn.k_norm.weight": {
3016
+ "shardIndex": 15,
3017
+ "offset": 8970240,
3018
+ "size": 512,
3019
+ "shape": [
3020
+ 256
3021
+ ],
3022
+ "dtype": "BF16"
3023
+ },
3024
+ "model.layers.8.self_attn.k_proj.weight": {
3025
+ "shardIndex": 15,
3026
+ "offset": 8974336,
3027
+ "size": 165888,
3028
+ "shape": [
3029
+ 256,
3030
+ 1152
3031
+ ],
3032
+ "dtype": "Q4_K_M"
3033
+ },
3034
+ "model.layers.8.self_attn.o_proj.weight": {
3035
+ "shardIndex": 15,
3036
+ "offset": 9142272,
3037
+ "size": 663552,
3038
+ "shape": [
3039
+ 1152,
3040
+ 1024
3041
+ ],
3042
+ "dtype": "Q4_K_M"
3043
+ },
3044
+ "model.layers.8.self_attn.q_norm.weight": {
3045
+ "shardIndex": 15,
3046
+ "offset": 9805824,
3047
+ "size": 512,
3048
+ "shape": [
3049
+ 256
3050
+ ],
3051
+ "dtype": "BF16"
3052
+ },
3053
+ "model.layers.8.self_attn.q_proj.weight": {
3054
+ "shardIndex": 15,
3055
+ "offset": 9809920,
3056
+ "size": 663552,
3057
+ "shape": [
3058
+ 1024,
3059
+ 1152
3060
+ ],
3061
+ "dtype": "Q4_K_M"
3062
+ },
3063
+ "model.layers.8.self_attn.v_proj.weight": {
3064
+ "shardIndex": 15,
3065
+ "offset": 10473472,
3066
+ "size": 165888,
3067
+ "shape": [
3068
+ 256,
3069
+ 1152
3070
+ ],
3071
+ "dtype": "Q4_K_M"
3072
+ },
3073
+ "model.layers.9.input_layernorm.weight": {
3074
+ "shardIndex": 15,
3075
+ "offset": 10641408,
3076
+ "size": 2304,
3077
+ "shape": [
3078
+ 1152
3079
+ ],
3080
+ "dtype": "BF16"
3081
+ },
3082
+ "model.layers.9.mlp.down_proj.weight": {
3083
+ "shardIndex": 15,
3084
+ "offset": 10645504,
3085
+ "size": 4478976,
3086
+ "shape": [
3087
+ 1152,
3088
+ 6912
3089
+ ],
3090
+ "dtype": "Q4_K_M"
3091
+ },
3092
+ "model.layers.9.mlp.gate_up_proj.weight": {
3093
+ "shardIndex": 15,
3094
+ "offset": 15126528,
3095
+ "size": 8957952,
3096
+ "shape": [
3097
+ 13824,
3098
+ 1152
3099
+ ],
3100
+ "dtype": "Q4_K_M"
3101
+ },
3102
+ "model.layers.9.post_attention_layernorm.weight": {
3103
+ "shardIndex": 15,
3104
+ "offset": 24084480,
3105
+ "size": 2304,
3106
+ "shape": [
3107
+ 1152
3108
+ ],
3109
+ "dtype": "BF16"
3110
+ },
3111
+ "model.layers.9.post_feedforward_layernorm.weight": {
3112
+ "shardIndex": 15,
3113
+ "offset": 24088576,
3114
+ "size": 2304,
3115
+ "shape": [
3116
+ 1152
3117
+ ],
3118
+ "dtype": "BF16"
3119
+ },
3120
+ "model.layers.9.pre_feedforward_layernorm.weight": {
3121
+ "shardIndex": 15,
3122
+ "offset": 24092672,
3123
+ "size": 2304,
3124
+ "shape": [
3125
+ 1152
3126
+ ],
3127
+ "dtype": "BF16"
3128
+ },
3129
+ "model.layers.9.self_attn.k_norm.weight": {
3130
+ "shardIndex": 15,
3131
+ "offset": 24096768,
3132
+ "size": 512,
3133
+ "shape": [
3134
+ 256
3135
+ ],
3136
+ "dtype": "BF16"
3137
+ },
3138
+ "model.layers.9.self_attn.k_proj.weight": {
3139
+ "shardIndex": 15,
3140
+ "offset": 24100864,
3141
+ "size": 165888,
3142
+ "shape": [
3143
+ 256,
3144
+ 1152
3145
+ ],
3146
+ "dtype": "Q4_K_M"
3147
+ },
3148
+ "model.layers.9.self_attn.o_proj.weight": {
3149
+ "shardIndex": 15,
3150
+ "offset": 24268800,
3151
+ "size": 663552,
3152
+ "shape": [
3153
+ 1152,
3154
+ 1024
3155
+ ],
3156
+ "dtype": "Q4_K_M"
3157
+ },
3158
+ "model.layers.9.self_attn.q_norm.weight": {
3159
+ "shardIndex": 15,
3160
+ "offset": 24932352,
3161
+ "size": 512,
3162
+ "shape": [
3163
+ 256
3164
+ ],
3165
+ "dtype": "BF16"
3166
+ },
3167
+ "model.layers.9.self_attn.q_proj.weight": {
3168
+ "shardIndex": 15,
3169
+ "offset": 24936448,
3170
+ "size": 663552,
3171
+ "shape": [
3172
+ 1024,
3173
+ 1152
3174
+ ],
3175
+ "dtype": "Q4_K_M"
3176
+ },
3177
+ "model.layers.9.self_attn.v_proj.weight": {
3178
+ "shardIndex": 15,
3179
+ "offset": 25600000,
3180
+ "size": 165888,
3181
+ "shape": [
3182
+ 256,
3183
+ 1152
3184
+ ],
3185
+ "dtype": "Q4_K_M"
3186
+ },
3187
+ "model.norm.weight": {
3188
+ "shardIndex": 15,
3189
+ "offset": 25767936,
3190
+ "size": 2304,
3191
+ "shape": [
3192
+ 1152
3193
+ ],
3194
+ "dtype": "BF16"
3195
+ }
3196
+ },
3197
+ "moeConfig": null,
3198
+ "totalSize": 997259520,
3199
+ "tensorCount": 314
3200
+ }
shard_00000.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce0aa445c0342d8d331dcf0ea12420ec4d958f2aa0f9d03b0d11549afd51c51f
3
+ size 67108864
shard_00001.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139db6c33ea369fa5089fbbdbece91639d7be9abdb4330d4b6f6bbb69bd8eba8
3
+ size 67108864
shard_00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23bc7a67086efe16a19f78880349ed9a5c317765455e70a1e58a00876ab2e0e0
3
+ size 67108864
shard_00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a88c622d0c6e726c6c0c3e37397295073027ff0c330c1cc5d44da39c71c8cbf4
3
+ size 67108864
shard_00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98c6a4d591d7f5877a8d973e7680ff4969edeb8e5f9cbebbf944ddd7476b1ac4
3
+ size 67108864
shard_00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faf353ffab307ec5129f24adaa86869002557318356141c3bc9d71506f29ec98
3
+ size 67108864
shard_00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e97594ce663739291e96563d5ae421382ade6a4a2f242acbbb0199c9e79b3a19
3
+ size 67108864
shard_00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b41e5abe58bdcb2016a89da6a38f25e2cb64f13fb626e4c10513b39c215a589
3
+ size 67108864
shard_00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68e2a3bc7312c7a7044a7676c41281059dcfa30df985fbf78acaaa2ce1c08e41
3
+ size 67108864
shard_00009.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e71a558b15e6036b42040a8940269a7d1ac333d24dfa8dee5e62dc2237cbe8
3
+ size 64989184
shard_00010.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440fba3e14be8879f97d9c3212403327033eb92a1d90d8e7befcd1017819310b
3
+ size 60504064
shard_00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eacd2fdc1199087368713516f5e508a547b22188f7d895959190be791f408a2a
3
+ size 60504064
shard_00012.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d913fbef5025c977adcd4c762cd45319e5ac22175da82e30aed6df8eb77551e
3
+ size 60504064
shard_00013.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972b4d936485b275a6067cd1e8a338315550d8e1943090b63ed79cc23e40a4f1
3
+ size 60504064
shard_00014.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d09003383bbd78f0d407ccd72a1531dc6feeea3eb9dab7fadfd125d825befc48
3
+ size 60504064
shard_00015.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68c92552170ce6c12f7e8b6a8d44683d6e527955d533fff685bce22cde11d13b
3
+ size 25770240
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ef59ebecae680b6ab1ebc65c3855238032d55dea31d27968a6eacf458144ee9
3
+ size 14386245