horheynm commited on
Commit
e10d267
·
verified ·
1 Parent(s): 80c2d87

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
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-Small-24B-Instruct-2501",
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": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 32768,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 8,
19
+ "quantization_config": {
20
+ "config_groups": {
21
+ "group_0": {
22
+ "input_activations": {
23
+ "actorder": null,
24
+ "block_structure": null,
25
+ "dynamic": true,
26
+ "group_size": null,
27
+ "num_bits": 8,
28
+ "observer": null,
29
+ "observer_kwargs": {},
30
+ "strategy": "token",
31
+ "symmetric": true,
32
+ "type": "float"
33
+ },
34
+ "output_activations": null,
35
+ "targets": [
36
+ "Linear"
37
+ ],
38
+ "weights": {
39
+ "actorder": null,
40
+ "block_structure": null,
41
+ "dynamic": false,
42
+ "group_size": null,
43
+ "num_bits": 8,
44
+ "observer": "minmax",
45
+ "observer_kwargs": {},
46
+ "strategy": "channel",
47
+ "symmetric": true,
48
+ "type": "float"
49
+ }
50
+ }
51
+ },
52
+ "format": "float-quantized",
53
+ "global_compression_ratio": 1.5302466391371097,
54
+ "ignore": [
55
+ "lm_head"
56
+ ],
57
+ "kv_cache_scheme": null,
58
+ "quant_method": "compressed-tensors",
59
+ "quantization_status": "compressed"
60
+ },
61
+ "rms_norm_eps": 1e-05,
62
+ "rope_theta": 100000000.0,
63
+ "sliding_window": null,
64
+ "tie_word_embeddings": false,
65
+ "torch_dtype": "bfloat16",
66
+ "transformers_version": "4.48.0",
67
+ "use_cache": true,
68
+ "vocab_size": 131072
69
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "temperature": 0.15,
7
+ "transformers_version": "4.48.0"
8
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b1961ba6792853fd28db85cac3089cfe2f6ef041c411253be0fdb129953922
3
+ size 4898056608
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36b6e32fd3a300bbf0d3e338ae837156d0a8700eb3a4a0d8af11f54e46f9f897
3
+ size 4835545032
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c94395119aba8e292e1d4c2ad8367169720c95e3392a507fc65a5b88d1fd520
3
+ size 4982401040
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2be802f382e29ea4f5f50907b09552d9e6995e5a62231b5767b320c62a7e5271
3
+ size 4998137864
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47489a605d2a71d88479bb4ca3dabbbc1a23f598bccfe9df37766ccf1e672bcf
3
+ size 3865305328
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58034435463df5dfb748849bb5002d84b1ad1a1b308dfe26f5420e3e0a340cba
3
+ size 1342177408
model.safetensors.index.json ADDED
@@ -0,0 +1,650 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 24921548800
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00006.safetensors",
18
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00006.safetensors",
20
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00006.safetensors",
22
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00006.safetensors",
27
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
28
+ "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00006.safetensors",
29
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
30
+ "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00006.safetensors",
31
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
32
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
33
+ "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00006.safetensors",
34
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
35
+ "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00006.safetensors",
36
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
37
+ "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00006.safetensors",
38
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
39
+ "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00006.safetensors",
40
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
41
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.10.mlp.down_proj.weight_scale": "model-00002-of-00006.safetensors",
43
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.10.mlp.gate_proj.weight_scale": "model-00002-of-00006.safetensors",
45
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
46
+ "model.layers.10.mlp.up_proj.weight_scale": "model-00002-of-00006.safetensors",
47
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
48
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
49
+ "model.layers.10.self_attn.k_proj.weight_scale": "model-00002-of-00006.safetensors",
50
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
51
+ "model.layers.10.self_attn.o_proj.weight_scale": "model-00002-of-00006.safetensors",
52
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
53
+ "model.layers.10.self_attn.q_proj.weight_scale": "model-00002-of-00006.safetensors",
54
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
55
+ "model.layers.10.self_attn.v_proj.weight_scale": "model-00002-of-00006.safetensors",
56
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
57
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
58
+ "model.layers.11.mlp.down_proj.weight_scale": "model-00002-of-00006.safetensors",
59
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
60
+ "model.layers.11.mlp.gate_proj.weight_scale": "model-00002-of-00006.safetensors",
61
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
62
+ "model.layers.11.mlp.up_proj.weight_scale": "model-00002-of-00006.safetensors",
63
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
64
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
65
+ "model.layers.11.self_attn.k_proj.weight_scale": "model-00002-of-00006.safetensors",
66
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
67
+ "model.layers.11.self_attn.o_proj.weight_scale": "model-00002-of-00006.safetensors",
68
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
69
+ "model.layers.11.self_attn.q_proj.weight_scale": "model-00002-of-00006.safetensors",
70
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
71
+ "model.layers.11.self_attn.v_proj.weight_scale": "model-00002-of-00006.safetensors",
72
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
73
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
74
+ "model.layers.12.mlp.down_proj.weight_scale": "model-00002-of-00006.safetensors",
75
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
76
+ "model.layers.12.mlp.gate_proj.weight_scale": "model-00002-of-00006.safetensors",
77
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
78
+ "model.layers.12.mlp.up_proj.weight_scale": "model-00002-of-00006.safetensors",
79
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
80
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
81
+ "model.layers.12.self_attn.k_proj.weight_scale": "model-00002-of-00006.safetensors",
82
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
83
+ "model.layers.12.self_attn.o_proj.weight_scale": "model-00002-of-00006.safetensors",
84
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
85
+ "model.layers.12.self_attn.q_proj.weight_scale": "model-00002-of-00006.safetensors",
86
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
87
+ "model.layers.12.self_attn.v_proj.weight_scale": "model-00002-of-00006.safetensors",
88
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
89
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
90
+ "model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00006.safetensors",
91
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
92
+ "model.layers.13.mlp.gate_proj.weight_scale": "model-00002-of-00006.safetensors",
93
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
94
+ "model.layers.13.mlp.up_proj.weight_scale": "model-00002-of-00006.safetensors",
95
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
96
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
97
+ "model.layers.13.self_attn.k_proj.weight_scale": "model-00002-of-00006.safetensors",
98
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
99
+ "model.layers.13.self_attn.o_proj.weight_scale": "model-00002-of-00006.safetensors",
100
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
101
+ "model.layers.13.self_attn.q_proj.weight_scale": "model-00002-of-00006.safetensors",
102
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
103
+ "model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00006.safetensors",
104
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
105
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
106
+ "model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00006.safetensors",
107
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
108
+ "model.layers.14.mlp.gate_proj.weight_scale": "model-00002-of-00006.safetensors",
109
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
110
+ "model.layers.14.mlp.up_proj.weight_scale": "model-00002-of-00006.safetensors",
111
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
112
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
113
+ "model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00006.safetensors",
114
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
115
+ "model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00006.safetensors",
116
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
117
+ "model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00006.safetensors",
118
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
119
+ "model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00006.safetensors",
120
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
121
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
122
+ "model.layers.15.mlp.down_proj.weight_scale": "model-00003-of-00006.safetensors",
123
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
124
+ "model.layers.15.mlp.gate_proj.weight_scale": "model-00003-of-00006.safetensors",
125
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
126
+ "model.layers.15.mlp.up_proj.weight_scale": "model-00003-of-00006.safetensors",
127
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
128
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
129
+ "model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00006.safetensors",
130
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
131
+ "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00006.safetensors",
132
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
133
+ "model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00006.safetensors",
134
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
135
+ "model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00006.safetensors",
136
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
137
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
138
+ "model.layers.16.mlp.down_proj.weight_scale": "model-00003-of-00006.safetensors",
139
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
140
+ "model.layers.16.mlp.gate_proj.weight_scale": "model-00003-of-00006.safetensors",
141
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
142
+ "model.layers.16.mlp.up_proj.weight_scale": "model-00003-of-00006.safetensors",
143
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
144
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
145
+ "model.layers.16.self_attn.k_proj.weight_scale": "model-00003-of-00006.safetensors",
146
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
147
+ "model.layers.16.self_attn.o_proj.weight_scale": "model-00003-of-00006.safetensors",
148
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
149
+ "model.layers.16.self_attn.q_proj.weight_scale": "model-00003-of-00006.safetensors",
150
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
151
+ "model.layers.16.self_attn.v_proj.weight_scale": "model-00003-of-00006.safetensors",
152
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
153
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
154
+ "model.layers.17.mlp.down_proj.weight_scale": "model-00003-of-00006.safetensors",
155
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
156
+ "model.layers.17.mlp.gate_proj.weight_scale": "model-00003-of-00006.safetensors",
157
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
158
+ "model.layers.17.mlp.up_proj.weight_scale": "model-00003-of-00006.safetensors",
159
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
160
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
161
+ "model.layers.17.self_attn.k_proj.weight_scale": "model-00003-of-00006.safetensors",
162
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
163
+ "model.layers.17.self_attn.o_proj.weight_scale": "model-00003-of-00006.safetensors",
164
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
165
+ "model.layers.17.self_attn.q_proj.weight_scale": "model-00003-of-00006.safetensors",
166
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
167
+ "model.layers.17.self_attn.v_proj.weight_scale": "model-00003-of-00006.safetensors",
168
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
169
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
170
+ "model.layers.18.mlp.down_proj.weight_scale": "model-00003-of-00006.safetensors",
171
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
172
+ "model.layers.18.mlp.gate_proj.weight_scale": "model-00003-of-00006.safetensors",
173
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
174
+ "model.layers.18.mlp.up_proj.weight_scale": "model-00003-of-00006.safetensors",
175
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
176
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
177
+ "model.layers.18.self_attn.k_proj.weight_scale": "model-00003-of-00006.safetensors",
178
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
179
+ "model.layers.18.self_attn.o_proj.weight_scale": "model-00003-of-00006.safetensors",
180
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
181
+ "model.layers.18.self_attn.q_proj.weight_scale": "model-00003-of-00006.safetensors",
182
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
183
+ "model.layers.18.self_attn.v_proj.weight_scale": "model-00003-of-00006.safetensors",
184
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
185
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
186
+ "model.layers.19.mlp.down_proj.weight_scale": "model-00003-of-00006.safetensors",
187
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
188
+ "model.layers.19.mlp.gate_proj.weight_scale": "model-00003-of-00006.safetensors",
189
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
190
+ "model.layers.19.mlp.up_proj.weight_scale": "model-00003-of-00006.safetensors",
191
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
192
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
193
+ "model.layers.19.self_attn.k_proj.weight_scale": "model-00003-of-00006.safetensors",
194
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
195
+ "model.layers.19.self_attn.o_proj.weight_scale": "model-00003-of-00006.safetensors",
196
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
197
+ "model.layers.19.self_attn.q_proj.weight_scale": "model-00003-of-00006.safetensors",
198
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
199
+ "model.layers.19.self_attn.v_proj.weight_scale": "model-00003-of-00006.safetensors",
200
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
201
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
202
+ "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00006.safetensors",
203
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
204
+ "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00006.safetensors",
205
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
206
+ "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00006.safetensors",
207
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
208
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
209
+ "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00006.safetensors",
210
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
211
+ "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00006.safetensors",
212
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
213
+ "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00006.safetensors",
214
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
215
+ "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00006.safetensors",
216
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
217
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
218
+ "model.layers.20.mlp.down_proj.weight_scale": "model-00003-of-00006.safetensors",
219
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
220
+ "model.layers.20.mlp.gate_proj.weight_scale": "model-00003-of-00006.safetensors",
221
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
222
+ "model.layers.20.mlp.up_proj.weight_scale": "model-00003-of-00006.safetensors",
223
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
224
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
225
+ "model.layers.20.self_attn.k_proj.weight_scale": "model-00003-of-00006.safetensors",
226
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
227
+ "model.layers.20.self_attn.o_proj.weight_scale": "model-00003-of-00006.safetensors",
228
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
229
+ "model.layers.20.self_attn.q_proj.weight_scale": "model-00003-of-00006.safetensors",
230
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
231
+ "model.layers.20.self_attn.v_proj.weight_scale": "model-00003-of-00006.safetensors",
232
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
233
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
234
+ "model.layers.21.mlp.down_proj.weight_scale": "model-00003-of-00006.safetensors",
235
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
236
+ "model.layers.21.mlp.gate_proj.weight_scale": "model-00003-of-00006.safetensors",
237
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
238
+ "model.layers.21.mlp.up_proj.weight_scale": "model-00003-of-00006.safetensors",
239
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
240
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
241
+ "model.layers.21.self_attn.k_proj.weight_scale": "model-00003-of-00006.safetensors",
242
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
243
+ "model.layers.21.self_attn.o_proj.weight_scale": "model-00003-of-00006.safetensors",
244
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
245
+ "model.layers.21.self_attn.q_proj.weight_scale": "model-00003-of-00006.safetensors",
246
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
247
+ "model.layers.21.self_attn.v_proj.weight_scale": "model-00003-of-00006.safetensors",
248
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
249
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
250
+ "model.layers.22.mlp.down_proj.weight_scale": "model-00003-of-00006.safetensors",
251
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
252
+ "model.layers.22.mlp.gate_proj.weight_scale": "model-00003-of-00006.safetensors",
253
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
254
+ "model.layers.22.mlp.up_proj.weight_scale": "model-00003-of-00006.safetensors",
255
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
256
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
257
+ "model.layers.22.self_attn.k_proj.weight_scale": "model-00003-of-00006.safetensors",
258
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
259
+ "model.layers.22.self_attn.o_proj.weight_scale": "model-00003-of-00006.safetensors",
260
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
261
+ "model.layers.22.self_attn.q_proj.weight_scale": "model-00003-of-00006.safetensors",
262
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
263
+ "model.layers.22.self_attn.v_proj.weight_scale": "model-00003-of-00006.safetensors",
264
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
265
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
266
+ "model.layers.23.mlp.down_proj.weight_scale": "model-00003-of-00006.safetensors",
267
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
268
+ "model.layers.23.mlp.gate_proj.weight_scale": "model-00003-of-00006.safetensors",
269
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
270
+ "model.layers.23.mlp.up_proj.weight_scale": "model-00003-of-00006.safetensors",
271
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
272
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
273
+ "model.layers.23.self_attn.k_proj.weight_scale": "model-00003-of-00006.safetensors",
274
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
275
+ "model.layers.23.self_attn.o_proj.weight_scale": "model-00003-of-00006.safetensors",
276
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
277
+ "model.layers.23.self_attn.q_proj.weight_scale": "model-00003-of-00006.safetensors",
278
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
279
+ "model.layers.23.self_attn.v_proj.weight_scale": "model-00003-of-00006.safetensors",
280
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
281
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
282
+ "model.layers.24.mlp.down_proj.weight_scale": "model-00004-of-00006.safetensors",
283
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
284
+ "model.layers.24.mlp.gate_proj.weight_scale": "model-00004-of-00006.safetensors",
285
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
286
+ "model.layers.24.mlp.up_proj.weight_scale": "model-00004-of-00006.safetensors",
287
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
288
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
289
+ "model.layers.24.self_attn.k_proj.weight_scale": "model-00003-of-00006.safetensors",
290
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
291
+ "model.layers.24.self_attn.o_proj.weight_scale": "model-00004-of-00006.safetensors",
292
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
293
+ "model.layers.24.self_attn.q_proj.weight_scale": "model-00003-of-00006.safetensors",
294
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
295
+ "model.layers.24.self_attn.v_proj.weight_scale": "model-00003-of-00006.safetensors",
296
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
297
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
298
+ "model.layers.25.mlp.down_proj.weight_scale": "model-00004-of-00006.safetensors",
299
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
300
+ "model.layers.25.mlp.gate_proj.weight_scale": "model-00004-of-00006.safetensors",
301
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
302
+ "model.layers.25.mlp.up_proj.weight_scale": "model-00004-of-00006.safetensors",
303
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
304
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
305
+ "model.layers.25.self_attn.k_proj.weight_scale": "model-00004-of-00006.safetensors",
306
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
307
+ "model.layers.25.self_attn.o_proj.weight_scale": "model-00004-of-00006.safetensors",
308
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
309
+ "model.layers.25.self_attn.q_proj.weight_scale": "model-00004-of-00006.safetensors",
310
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
311
+ "model.layers.25.self_attn.v_proj.weight_scale": "model-00004-of-00006.safetensors",
312
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
313
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
314
+ "model.layers.26.mlp.down_proj.weight_scale": "model-00004-of-00006.safetensors",
315
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
316
+ "model.layers.26.mlp.gate_proj.weight_scale": "model-00004-of-00006.safetensors",
317
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
318
+ "model.layers.26.mlp.up_proj.weight_scale": "model-00004-of-00006.safetensors",
319
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
320
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
321
+ "model.layers.26.self_attn.k_proj.weight_scale": "model-00004-of-00006.safetensors",
322
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
323
+ "model.layers.26.self_attn.o_proj.weight_scale": "model-00004-of-00006.safetensors",
324
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
325
+ "model.layers.26.self_attn.q_proj.weight_scale": "model-00004-of-00006.safetensors",
326
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
327
+ "model.layers.26.self_attn.v_proj.weight_scale": "model-00004-of-00006.safetensors",
328
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
329
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
330
+ "model.layers.27.mlp.down_proj.weight_scale": "model-00004-of-00006.safetensors",
331
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
332
+ "model.layers.27.mlp.gate_proj.weight_scale": "model-00004-of-00006.safetensors",
333
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
334
+ "model.layers.27.mlp.up_proj.weight_scale": "model-00004-of-00006.safetensors",
335
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
336
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
337
+ "model.layers.27.self_attn.k_proj.weight_scale": "model-00004-of-00006.safetensors",
338
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
339
+ "model.layers.27.self_attn.o_proj.weight_scale": "model-00004-of-00006.safetensors",
340
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
341
+ "model.layers.27.self_attn.q_proj.weight_scale": "model-00004-of-00006.safetensors",
342
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
343
+ "model.layers.27.self_attn.v_proj.weight_scale": "model-00004-of-00006.safetensors",
344
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
345
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
346
+ "model.layers.28.mlp.down_proj.weight_scale": "model-00004-of-00006.safetensors",
347
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
348
+ "model.layers.28.mlp.gate_proj.weight_scale": "model-00004-of-00006.safetensors",
349
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
350
+ "model.layers.28.mlp.up_proj.weight_scale": "model-00004-of-00006.safetensors",
351
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
352
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
353
+ "model.layers.28.self_attn.k_proj.weight_scale": "model-00004-of-00006.safetensors",
354
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
355
+ "model.layers.28.self_attn.o_proj.weight_scale": "model-00004-of-00006.safetensors",
356
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
357
+ "model.layers.28.self_attn.q_proj.weight_scale": "model-00004-of-00006.safetensors",
358
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
359
+ "model.layers.28.self_attn.v_proj.weight_scale": "model-00004-of-00006.safetensors",
360
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
361
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
362
+ "model.layers.29.mlp.down_proj.weight_scale": "model-00004-of-00006.safetensors",
363
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
364
+ "model.layers.29.mlp.gate_proj.weight_scale": "model-00004-of-00006.safetensors",
365
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
366
+ "model.layers.29.mlp.up_proj.weight_scale": "model-00004-of-00006.safetensors",
367
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
368
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
369
+ "model.layers.29.self_attn.k_proj.weight_scale": "model-00004-of-00006.safetensors",
370
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
371
+ "model.layers.29.self_attn.o_proj.weight_scale": "model-00004-of-00006.safetensors",
372
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
373
+ "model.layers.29.self_attn.q_proj.weight_scale": "model-00004-of-00006.safetensors",
374
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
375
+ "model.layers.29.self_attn.v_proj.weight_scale": "model-00004-of-00006.safetensors",
376
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
377
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
378
+ "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00006.safetensors",
379
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
380
+ "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00006.safetensors",
381
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
382
+ "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00006.safetensors",
383
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
384
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
385
+ "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00006.safetensors",
386
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
387
+ "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00006.safetensors",
388
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
389
+ "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00006.safetensors",
390
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
391
+ "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00006.safetensors",
392
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
393
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
394
+ "model.layers.30.mlp.down_proj.weight_scale": "model-00004-of-00006.safetensors",
395
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
396
+ "model.layers.30.mlp.gate_proj.weight_scale": "model-00004-of-00006.safetensors",
397
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
398
+ "model.layers.30.mlp.up_proj.weight_scale": "model-00004-of-00006.safetensors",
399
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
400
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
401
+ "model.layers.30.self_attn.k_proj.weight_scale": "model-00004-of-00006.safetensors",
402
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
403
+ "model.layers.30.self_attn.o_proj.weight_scale": "model-00004-of-00006.safetensors",
404
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
405
+ "model.layers.30.self_attn.q_proj.weight_scale": "model-00004-of-00006.safetensors",
406
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
407
+ "model.layers.30.self_attn.v_proj.weight_scale": "model-00004-of-00006.safetensors",
408
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
409
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
410
+ "model.layers.31.mlp.down_proj.weight_scale": "model-00004-of-00006.safetensors",
411
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
412
+ "model.layers.31.mlp.gate_proj.weight_scale": "model-00004-of-00006.safetensors",
413
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
414
+ "model.layers.31.mlp.up_proj.weight_scale": "model-00004-of-00006.safetensors",
415
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
416
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
417
+ "model.layers.31.self_attn.k_proj.weight_scale": "model-00004-of-00006.safetensors",
418
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
419
+ "model.layers.31.self_attn.o_proj.weight_scale": "model-00004-of-00006.safetensors",
420
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
421
+ "model.layers.31.self_attn.q_proj.weight_scale": "model-00004-of-00006.safetensors",
422
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
423
+ "model.layers.31.self_attn.v_proj.weight_scale": "model-00004-of-00006.safetensors",
424
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
425
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
426
+ "model.layers.32.mlp.down_proj.weight_scale": "model-00004-of-00006.safetensors",
427
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
428
+ "model.layers.32.mlp.gate_proj.weight_scale": "model-00004-of-00006.safetensors",
429
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
430
+ "model.layers.32.mlp.up_proj.weight_scale": "model-00004-of-00006.safetensors",
431
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
432
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
433
+ "model.layers.32.self_attn.k_proj.weight_scale": "model-00004-of-00006.safetensors",
434
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
435
+ "model.layers.32.self_attn.o_proj.weight_scale": "model-00004-of-00006.safetensors",
436
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
437
+ "model.layers.32.self_attn.q_proj.weight_scale": "model-00004-of-00006.safetensors",
438
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
439
+ "model.layers.32.self_attn.v_proj.weight_scale": "model-00004-of-00006.safetensors",
440
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
441
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
442
+ "model.layers.33.mlp.down_proj.weight_scale": "model-00005-of-00006.safetensors",
443
+ "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
444
+ "model.layers.33.mlp.gate_proj.weight_scale": "model-00005-of-00006.safetensors",
445
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
446
+ "model.layers.33.mlp.up_proj.weight_scale": "model-00005-of-00006.safetensors",
447
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
448
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
449
+ "model.layers.33.self_attn.k_proj.weight_scale": "model-00004-of-00006.safetensors",
450
+ "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
451
+ "model.layers.33.self_attn.o_proj.weight_scale": "model-00005-of-00006.safetensors",
452
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
453
+ "model.layers.33.self_attn.q_proj.weight_scale": "model-00004-of-00006.safetensors",
454
+ "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
455
+ "model.layers.33.self_attn.v_proj.weight_scale": "model-00005-of-00006.safetensors",
456
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
457
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
458
+ "model.layers.34.mlp.down_proj.weight_scale": "model-00005-of-00006.safetensors",
459
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
460
+ "model.layers.34.mlp.gate_proj.weight_scale": "model-00005-of-00006.safetensors",
461
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
462
+ "model.layers.34.mlp.up_proj.weight_scale": "model-00005-of-00006.safetensors",
463
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
464
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
465
+ "model.layers.34.self_attn.k_proj.weight_scale": "model-00005-of-00006.safetensors",
466
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
467
+ "model.layers.34.self_attn.o_proj.weight_scale": "model-00005-of-00006.safetensors",
468
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
469
+ "model.layers.34.self_attn.q_proj.weight_scale": "model-00005-of-00006.safetensors",
470
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
471
+ "model.layers.34.self_attn.v_proj.weight_scale": "model-00005-of-00006.safetensors",
472
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
473
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
474
+ "model.layers.35.mlp.down_proj.weight_scale": "model-00005-of-00006.safetensors",
475
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
476
+ "model.layers.35.mlp.gate_proj.weight_scale": "model-00005-of-00006.safetensors",
477
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
478
+ "model.layers.35.mlp.up_proj.weight_scale": "model-00005-of-00006.safetensors",
479
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
480
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
481
+ "model.layers.35.self_attn.k_proj.weight_scale": "model-00005-of-00006.safetensors",
482
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
483
+ "model.layers.35.self_attn.o_proj.weight_scale": "model-00005-of-00006.safetensors",
484
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
485
+ "model.layers.35.self_attn.q_proj.weight_scale": "model-00005-of-00006.safetensors",
486
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
487
+ "model.layers.35.self_attn.v_proj.weight_scale": "model-00005-of-00006.safetensors",
488
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
489
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
490
+ "model.layers.36.mlp.down_proj.weight_scale": "model-00005-of-00006.safetensors",
491
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
492
+ "model.layers.36.mlp.gate_proj.weight_scale": "model-00005-of-00006.safetensors",
493
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
494
+ "model.layers.36.mlp.up_proj.weight_scale": "model-00005-of-00006.safetensors",
495
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
496
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
497
+ "model.layers.36.self_attn.k_proj.weight_scale": "model-00005-of-00006.safetensors",
498
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
499
+ "model.layers.36.self_attn.o_proj.weight_scale": "model-00005-of-00006.safetensors",
500
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
501
+ "model.layers.36.self_attn.q_proj.weight_scale": "model-00005-of-00006.safetensors",
502
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
503
+ "model.layers.36.self_attn.v_proj.weight_scale": "model-00005-of-00006.safetensors",
504
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
505
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
506
+ "model.layers.37.mlp.down_proj.weight_scale": "model-00005-of-00006.safetensors",
507
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
508
+ "model.layers.37.mlp.gate_proj.weight_scale": "model-00005-of-00006.safetensors",
509
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
510
+ "model.layers.37.mlp.up_proj.weight_scale": "model-00005-of-00006.safetensors",
511
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
512
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
513
+ "model.layers.37.self_attn.k_proj.weight_scale": "model-00005-of-00006.safetensors",
514
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
515
+ "model.layers.37.self_attn.o_proj.weight_scale": "model-00005-of-00006.safetensors",
516
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
517
+ "model.layers.37.self_attn.q_proj.weight_scale": "model-00005-of-00006.safetensors",
518
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
519
+ "model.layers.37.self_attn.v_proj.weight_scale": "model-00005-of-00006.safetensors",
520
+ "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
521
+ "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
522
+ "model.layers.38.mlp.down_proj.weight_scale": "model-00005-of-00006.safetensors",
523
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
524
+ "model.layers.38.mlp.gate_proj.weight_scale": "model-00005-of-00006.safetensors",
525
+ "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
526
+ "model.layers.38.mlp.up_proj.weight_scale": "model-00005-of-00006.safetensors",
527
+ "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
528
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
529
+ "model.layers.38.self_attn.k_proj.weight_scale": "model-00005-of-00006.safetensors",
530
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
531
+ "model.layers.38.self_attn.o_proj.weight_scale": "model-00005-of-00006.safetensors",
532
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
533
+ "model.layers.38.self_attn.q_proj.weight_scale": "model-00005-of-00006.safetensors",
534
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
535
+ "model.layers.38.self_attn.v_proj.weight_scale": "model-00005-of-00006.safetensors",
536
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
537
+ "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
538
+ "model.layers.39.mlp.down_proj.weight_scale": "model-00005-of-00006.safetensors",
539
+ "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
540
+ "model.layers.39.mlp.gate_proj.weight_scale": "model-00005-of-00006.safetensors",
541
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
542
+ "model.layers.39.mlp.up_proj.weight_scale": "model-00005-of-00006.safetensors",
543
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
544
+ "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
545
+ "model.layers.39.self_attn.k_proj.weight_scale": "model-00005-of-00006.safetensors",
546
+ "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
547
+ "model.layers.39.self_attn.o_proj.weight_scale": "model-00005-of-00006.safetensors",
548
+ "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
549
+ "model.layers.39.self_attn.q_proj.weight_scale": "model-00005-of-00006.safetensors",
550
+ "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
551
+ "model.layers.39.self_attn.v_proj.weight_scale": "model-00005-of-00006.safetensors",
552
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
553
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
554
+ "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00006.safetensors",
555
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
556
+ "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00006.safetensors",
557
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
558
+ "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00006.safetensors",
559
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
560
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
561
+ "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00006.safetensors",
562
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
563
+ "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00006.safetensors",
564
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
565
+ "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00006.safetensors",
566
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
567
+ "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00006.safetensors",
568
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
569
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
570
+ "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00006.safetensors",
571
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
572
+ "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00006.safetensors",
573
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
574
+ "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00006.safetensors",
575
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
576
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
577
+ "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00006.safetensors",
578
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
579
+ "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00006.safetensors",
580
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
581
+ "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00006.safetensors",
582
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
583
+ "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00006.safetensors",
584
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
585
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
586
+ "model.layers.6.mlp.down_proj.weight_scale": "model-00002-of-00006.safetensors",
587
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
588
+ "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00006.safetensors",
589
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
590
+ "model.layers.6.mlp.up_proj.weight_scale": "model-00002-of-00006.safetensors",
591
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
592
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
593
+ "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00006.safetensors",
594
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
595
+ "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00006.safetensors",
596
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
597
+ "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00006.safetensors",
598
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
599
+ "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00006.safetensors",
600
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
601
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
602
+ "model.layers.7.mlp.down_proj.weight_scale": "model-00002-of-00006.safetensors",
603
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
604
+ "model.layers.7.mlp.gate_proj.weight_scale": "model-00002-of-00006.safetensors",
605
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
606
+ "model.layers.7.mlp.up_proj.weight_scale": "model-00002-of-00006.safetensors",
607
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
608
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
609
+ "model.layers.7.self_attn.k_proj.weight_scale": "model-00002-of-00006.safetensors",
610
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
611
+ "model.layers.7.self_attn.o_proj.weight_scale": "model-00002-of-00006.safetensors",
612
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
613
+ "model.layers.7.self_attn.q_proj.weight_scale": "model-00002-of-00006.safetensors",
614
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
615
+ "model.layers.7.self_attn.v_proj.weight_scale": "model-00002-of-00006.safetensors",
616
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
617
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
618
+ "model.layers.8.mlp.down_proj.weight_scale": "model-00002-of-00006.safetensors",
619
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
620
+ "model.layers.8.mlp.gate_proj.weight_scale": "model-00002-of-00006.safetensors",
621
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
622
+ "model.layers.8.mlp.up_proj.weight_scale": "model-00002-of-00006.safetensors",
623
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
624
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
625
+ "model.layers.8.self_attn.k_proj.weight_scale": "model-00002-of-00006.safetensors",
626
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
627
+ "model.layers.8.self_attn.o_proj.weight_scale": "model-00002-of-00006.safetensors",
628
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
629
+ "model.layers.8.self_attn.q_proj.weight_scale": "model-00002-of-00006.safetensors",
630
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
631
+ "model.layers.8.self_attn.v_proj.weight_scale": "model-00002-of-00006.safetensors",
632
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
633
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
634
+ "model.layers.9.mlp.down_proj.weight_scale": "model-00002-of-00006.safetensors",
635
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
636
+ "model.layers.9.mlp.gate_proj.weight_scale": "model-00002-of-00006.safetensors",
637
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
638
+ "model.layers.9.mlp.up_proj.weight_scale": "model-00002-of-00006.safetensors",
639
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
640
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
641
+ "model.layers.9.self_attn.k_proj.weight_scale": "model-00002-of-00006.safetensors",
642
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
643
+ "model.layers.9.self_attn.o_proj.weight_scale": "model-00002-of-00006.safetensors",
644
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
645
+ "model.layers.9.self_attn.q_proj.weight_scale": "model-00002-of-00006.safetensors",
646
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
647
+ "model.layers.9.self_attn.v_proj.weight_scale": "model-00002-of-00006.safetensors",
648
+ "model.norm.weight": "model-00005-of-00006.safetensors"
649
+ }
650
+ }
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ DEFAULT_stage:
2
+ DEFAULT_modifiers:
3
+ QuantizationModifier:
4
+ ignore: [lm_head]
5
+ targets: [Linear]
6
+ scheme: FP8_DYNAMIC
special_tokens_map.json ADDED
@@ -0,0 +1,1025 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "[INST]",
7
+ "[/INST]",
8
+ "[AVAILABLE_TOOLS]",
9
+ "[/AVAILABLE_TOOLS]",
10
+ "[TOOL_RESULTS]",
11
+ "[/TOOL_RESULTS]",
12
+ "[TOOL_CALLS]",
13
+ "[IMG]",
14
+ "<pad>",
15
+ "[IMG_BREAK]",
16
+ "[IMG_END]",
17
+ "[PREFIX]",
18
+ "[MIDDLE]",
19
+ "[SUFFIX]",
20
+ "[SYSTEM_PROMPT]",
21
+ "[/SYSTEM_PROMPT]",
22
+ "[TOOL_CONTENT]",
23
+ "<SPECIAL_20>",
24
+ "<SPECIAL_21>",
25
+ "<SPECIAL_22>",
26
+ "<SPECIAL_23>",
27
+ "<SPECIAL_24>",
28
+ "<SPECIAL_25>",
29
+ "<SPECIAL_26>",
30
+ "<SPECIAL_27>",
31
+ "<SPECIAL_28>",
32
+ "<SPECIAL_29>",
33
+ "<SPECIAL_30>",
34
+ "<SPECIAL_31>",
35
+ "<SPECIAL_32>",
36
+ "<SPECIAL_33>",
37
+ "<SPECIAL_34>",
38
+ "<SPECIAL_35>",
39
+ "<SPECIAL_36>",
40
+ "<SPECIAL_37>",
41
+ "<SPECIAL_38>",
42
+ "<SPECIAL_39>",
43
+ "<SPECIAL_40>",
44
+ "<SPECIAL_41>",
45
+ "<SPECIAL_42>",
46
+ "<SPECIAL_43>",
47
+ "<SPECIAL_44>",
48
+ "<SPECIAL_45>",
49
+ "<SPECIAL_46>",
50
+ "<SPECIAL_47>",
51
+ "<SPECIAL_48>",
52
+ "<SPECIAL_49>",
53
+ "<SPECIAL_50>",
54
+ "<SPECIAL_51>",
55
+ "<SPECIAL_52>",
56
+ "<SPECIAL_53>",
57
+ "<SPECIAL_54>",
58
+ "<SPECIAL_55>",
59
+ "<SPECIAL_56>",
60
+ "<SPECIAL_57>",
61
+ "<SPECIAL_58>",
62
+ "<SPECIAL_59>",
63
+ "<SPECIAL_60>",
64
+ "<SPECIAL_61>",
65
+ "<SPECIAL_62>",
66
+ "<SPECIAL_63>",
67
+ "<SPECIAL_64>",
68
+ "<SPECIAL_65>",
69
+ "<SPECIAL_66>",
70
+ "<SPECIAL_67>",
71
+ "<SPECIAL_68>",
72
+ "<SPECIAL_69>",
73
+ "<SPECIAL_70>",
74
+ "<SPECIAL_71>",
75
+ "<SPECIAL_72>",
76
+ "<SPECIAL_73>",
77
+ "<SPECIAL_74>",
78
+ "<SPECIAL_75>",
79
+ "<SPECIAL_76>",
80
+ "<SPECIAL_77>",
81
+ "<SPECIAL_78>",
82
+ "<SPECIAL_79>",
83
+ "<SPECIAL_80>",
84
+ "<SPECIAL_81>",
85
+ "<SPECIAL_82>",
86
+ "<SPECIAL_83>",
87
+ "<SPECIAL_84>",
88
+ "<SPECIAL_85>",
89
+ "<SPECIAL_86>",
90
+ "<SPECIAL_87>",
91
+ "<SPECIAL_88>",
92
+ "<SPECIAL_89>",
93
+ "<SPECIAL_90>",
94
+ "<SPECIAL_91>",
95
+ "<SPECIAL_92>",
96
+ "<SPECIAL_93>",
97
+ "<SPECIAL_94>",
98
+ "<SPECIAL_95>",
99
+ "<SPECIAL_96>",
100
+ "<SPECIAL_97>",
101
+ "<SPECIAL_98>",
102
+ "<SPECIAL_99>",
103
+ "<SPECIAL_100>",
104
+ "<SPECIAL_101>",
105
+ "<SPECIAL_102>",
106
+ "<SPECIAL_103>",
107
+ "<SPECIAL_104>",
108
+ "<SPECIAL_105>",
109
+ "<SPECIAL_106>",
110
+ "<SPECIAL_107>",
111
+ "<SPECIAL_108>",
112
+ "<SPECIAL_109>",
113
+ "<SPECIAL_110>",
114
+ "<SPECIAL_111>",
115
+ "<SPECIAL_112>",
116
+ "<SPECIAL_113>",
117
+ "<SPECIAL_114>",
118
+ "<SPECIAL_115>",
119
+ "<SPECIAL_116>",
120
+ "<SPECIAL_117>",
121
+ "<SPECIAL_118>",
122
+ "<SPECIAL_119>",
123
+ "<SPECIAL_120>",
124
+ "<SPECIAL_121>",
125
+ "<SPECIAL_122>",
126
+ "<SPECIAL_123>",
127
+ "<SPECIAL_124>",
128
+ "<SPECIAL_125>",
129
+ "<SPECIAL_126>",
130
+ "<SPECIAL_127>",
131
+ "<SPECIAL_128>",
132
+ "<SPECIAL_129>",
133
+ "<SPECIAL_130>",
134
+ "<SPECIAL_131>",
135
+ "<SPECIAL_132>",
136
+ "<SPECIAL_133>",
137
+ "<SPECIAL_134>",
138
+ "<SPECIAL_135>",
139
+ "<SPECIAL_136>",
140
+ "<SPECIAL_137>",
141
+ "<SPECIAL_138>",
142
+ "<SPECIAL_139>",
143
+ "<SPECIAL_140>",
144
+ "<SPECIAL_141>",
145
+ "<SPECIAL_142>",
146
+ "<SPECIAL_143>",
147
+ "<SPECIAL_144>",
148
+ "<SPECIAL_145>",
149
+ "<SPECIAL_146>",
150
+ "<SPECIAL_147>",
151
+ "<SPECIAL_148>",
152
+ "<SPECIAL_149>",
153
+ "<SPECIAL_150>",
154
+ "<SPECIAL_151>",
155
+ "<SPECIAL_152>",
156
+ "<SPECIAL_153>",
157
+ "<SPECIAL_154>",
158
+ "<SPECIAL_155>",
159
+ "<SPECIAL_156>",
160
+ "<SPECIAL_157>",
161
+ "<SPECIAL_158>",
162
+ "<SPECIAL_159>",
163
+ "<SPECIAL_160>",
164
+ "<SPECIAL_161>",
165
+ "<SPECIAL_162>",
166
+ "<SPECIAL_163>",
167
+ "<SPECIAL_164>",
168
+ "<SPECIAL_165>",
169
+ "<SPECIAL_166>",
170
+ "<SPECIAL_167>",
171
+ "<SPECIAL_168>",
172
+ "<SPECIAL_169>",
173
+ "<SPECIAL_170>",
174
+ "<SPECIAL_171>",
175
+ "<SPECIAL_172>",
176
+ "<SPECIAL_173>",
177
+ "<SPECIAL_174>",
178
+ "<SPECIAL_175>",
179
+ "<SPECIAL_176>",
180
+ "<SPECIAL_177>",
181
+ "<SPECIAL_178>",
182
+ "<SPECIAL_179>",
183
+ "<SPECIAL_180>",
184
+ "<SPECIAL_181>",
185
+ "<SPECIAL_182>",
186
+ "<SPECIAL_183>",
187
+ "<SPECIAL_184>",
188
+ "<SPECIAL_185>",
189
+ "<SPECIAL_186>",
190
+ "<SPECIAL_187>",
191
+ "<SPECIAL_188>",
192
+ "<SPECIAL_189>",
193
+ "<SPECIAL_190>",
194
+ "<SPECIAL_191>",
195
+ "<SPECIAL_192>",
196
+ "<SPECIAL_193>",
197
+ "<SPECIAL_194>",
198
+ "<SPECIAL_195>",
199
+ "<SPECIAL_196>",
200
+ "<SPECIAL_197>",
201
+ "<SPECIAL_198>",
202
+ "<SPECIAL_199>",
203
+ "<SPECIAL_200>",
204
+ "<SPECIAL_201>",
205
+ "<SPECIAL_202>",
206
+ "<SPECIAL_203>",
207
+ "<SPECIAL_204>",
208
+ "<SPECIAL_205>",
209
+ "<SPECIAL_206>",
210
+ "<SPECIAL_207>",
211
+ "<SPECIAL_208>",
212
+ "<SPECIAL_209>",
213
+ "<SPECIAL_210>",
214
+ "<SPECIAL_211>",
215
+ "<SPECIAL_212>",
216
+ "<SPECIAL_213>",
217
+ "<SPECIAL_214>",
218
+ "<SPECIAL_215>",
219
+ "<SPECIAL_216>",
220
+ "<SPECIAL_217>",
221
+ "<SPECIAL_218>",
222
+ "<SPECIAL_219>",
223
+ "<SPECIAL_220>",
224
+ "<SPECIAL_221>",
225
+ "<SPECIAL_222>",
226
+ "<SPECIAL_223>",
227
+ "<SPECIAL_224>",
228
+ "<SPECIAL_225>",
229
+ "<SPECIAL_226>",
230
+ "<SPECIAL_227>",
231
+ "<SPECIAL_228>",
232
+ "<SPECIAL_229>",
233
+ "<SPECIAL_230>",
234
+ "<SPECIAL_231>",
235
+ "<SPECIAL_232>",
236
+ "<SPECIAL_233>",
237
+ "<SPECIAL_234>",
238
+ "<SPECIAL_235>",
239
+ "<SPECIAL_236>",
240
+ "<SPECIAL_237>",
241
+ "<SPECIAL_238>",
242
+ "<SPECIAL_239>",
243
+ "<SPECIAL_240>",
244
+ "<SPECIAL_241>",
245
+ "<SPECIAL_242>",
246
+ "<SPECIAL_243>",
247
+ "<SPECIAL_244>",
248
+ "<SPECIAL_245>",
249
+ "<SPECIAL_246>",
250
+ "<SPECIAL_247>",
251
+ "<SPECIAL_248>",
252
+ "<SPECIAL_249>",
253
+ "<SPECIAL_250>",
254
+ "<SPECIAL_251>",
255
+ "<SPECIAL_252>",
256
+ "<SPECIAL_253>",
257
+ "<SPECIAL_254>",
258
+ "<SPECIAL_255>",
259
+ "<SPECIAL_256>",
260
+ "<SPECIAL_257>",
261
+ "<SPECIAL_258>",
262
+ "<SPECIAL_259>",
263
+ "<SPECIAL_260>",
264
+ "<SPECIAL_261>",
265
+ "<SPECIAL_262>",
266
+ "<SPECIAL_263>",
267
+ "<SPECIAL_264>",
268
+ "<SPECIAL_265>",
269
+ "<SPECIAL_266>",
270
+ "<SPECIAL_267>",
271
+ "<SPECIAL_268>",
272
+ "<SPECIAL_269>",
273
+ "<SPECIAL_270>",
274
+ "<SPECIAL_271>",
275
+ "<SPECIAL_272>",
276
+ "<SPECIAL_273>",
277
+ "<SPECIAL_274>",
278
+ "<SPECIAL_275>",
279
+ "<SPECIAL_276>",
280
+ "<SPECIAL_277>",
281
+ "<SPECIAL_278>",
282
+ "<SPECIAL_279>",
283
+ "<SPECIAL_280>",
284
+ "<SPECIAL_281>",
285
+ "<SPECIAL_282>",
286
+ "<SPECIAL_283>",
287
+ "<SPECIAL_284>",
288
+ "<SPECIAL_285>",
289
+ "<SPECIAL_286>",
290
+ "<SPECIAL_287>",
291
+ "<SPECIAL_288>",
292
+ "<SPECIAL_289>",
293
+ "<SPECIAL_290>",
294
+ "<SPECIAL_291>",
295
+ "<SPECIAL_292>",
296
+ "<SPECIAL_293>",
297
+ "<SPECIAL_294>",
298
+ "<SPECIAL_295>",
299
+ "<SPECIAL_296>",
300
+ "<SPECIAL_297>",
301
+ "<SPECIAL_298>",
302
+ "<SPECIAL_299>",
303
+ "<SPECIAL_300>",
304
+ "<SPECIAL_301>",
305
+ "<SPECIAL_302>",
306
+ "<SPECIAL_303>",
307
+ "<SPECIAL_304>",
308
+ "<SPECIAL_305>",
309
+ "<SPECIAL_306>",
310
+ "<SPECIAL_307>",
311
+ "<SPECIAL_308>",
312
+ "<SPECIAL_309>",
313
+ "<SPECIAL_310>",
314
+ "<SPECIAL_311>",
315
+ "<SPECIAL_312>",
316
+ "<SPECIAL_313>",
317
+ "<SPECIAL_314>",
318
+ "<SPECIAL_315>",
319
+ "<SPECIAL_316>",
320
+ "<SPECIAL_317>",
321
+ "<SPECIAL_318>",
322
+ "<SPECIAL_319>",
323
+ "<SPECIAL_320>",
324
+ "<SPECIAL_321>",
325
+ "<SPECIAL_322>",
326
+ "<SPECIAL_323>",
327
+ "<SPECIAL_324>",
328
+ "<SPECIAL_325>",
329
+ "<SPECIAL_326>",
330
+ "<SPECIAL_327>",
331
+ "<SPECIAL_328>",
332
+ "<SPECIAL_329>",
333
+ "<SPECIAL_330>",
334
+ "<SPECIAL_331>",
335
+ "<SPECIAL_332>",
336
+ "<SPECIAL_333>",
337
+ "<SPECIAL_334>",
338
+ "<SPECIAL_335>",
339
+ "<SPECIAL_336>",
340
+ "<SPECIAL_337>",
341
+ "<SPECIAL_338>",
342
+ "<SPECIAL_339>",
343
+ "<SPECIAL_340>",
344
+ "<SPECIAL_341>",
345
+ "<SPECIAL_342>",
346
+ "<SPECIAL_343>",
347
+ "<SPECIAL_344>",
348
+ "<SPECIAL_345>",
349
+ "<SPECIAL_346>",
350
+ "<SPECIAL_347>",
351
+ "<SPECIAL_348>",
352
+ "<SPECIAL_349>",
353
+ "<SPECIAL_350>",
354
+ "<SPECIAL_351>",
355
+ "<SPECIAL_352>",
356
+ "<SPECIAL_353>",
357
+ "<SPECIAL_354>",
358
+ "<SPECIAL_355>",
359
+ "<SPECIAL_356>",
360
+ "<SPECIAL_357>",
361
+ "<SPECIAL_358>",
362
+ "<SPECIAL_359>",
363
+ "<SPECIAL_360>",
364
+ "<SPECIAL_361>",
365
+ "<SPECIAL_362>",
366
+ "<SPECIAL_363>",
367
+ "<SPECIAL_364>",
368
+ "<SPECIAL_365>",
369
+ "<SPECIAL_366>",
370
+ "<SPECIAL_367>",
371
+ "<SPECIAL_368>",
372
+ "<SPECIAL_369>",
373
+ "<SPECIAL_370>",
374
+ "<SPECIAL_371>",
375
+ "<SPECIAL_372>",
376
+ "<SPECIAL_373>",
377
+ "<SPECIAL_374>",
378
+ "<SPECIAL_375>",
379
+ "<SPECIAL_376>",
380
+ "<SPECIAL_377>",
381
+ "<SPECIAL_378>",
382
+ "<SPECIAL_379>",
383
+ "<SPECIAL_380>",
384
+ "<SPECIAL_381>",
385
+ "<SPECIAL_382>",
386
+ "<SPECIAL_383>",
387
+ "<SPECIAL_384>",
388
+ "<SPECIAL_385>",
389
+ "<SPECIAL_386>",
390
+ "<SPECIAL_387>",
391
+ "<SPECIAL_388>",
392
+ "<SPECIAL_389>",
393
+ "<SPECIAL_390>",
394
+ "<SPECIAL_391>",
395
+ "<SPECIAL_392>",
396
+ "<SPECIAL_393>",
397
+ "<SPECIAL_394>",
398
+ "<SPECIAL_395>",
399
+ "<SPECIAL_396>",
400
+ "<SPECIAL_397>",
401
+ "<SPECIAL_398>",
402
+ "<SPECIAL_399>",
403
+ "<SPECIAL_400>",
404
+ "<SPECIAL_401>",
405
+ "<SPECIAL_402>",
406
+ "<SPECIAL_403>",
407
+ "<SPECIAL_404>",
408
+ "<SPECIAL_405>",
409
+ "<SPECIAL_406>",
410
+ "<SPECIAL_407>",
411
+ "<SPECIAL_408>",
412
+ "<SPECIAL_409>",
413
+ "<SPECIAL_410>",
414
+ "<SPECIAL_411>",
415
+ "<SPECIAL_412>",
416
+ "<SPECIAL_413>",
417
+ "<SPECIAL_414>",
418
+ "<SPECIAL_415>",
419
+ "<SPECIAL_416>",
420
+ "<SPECIAL_417>",
421
+ "<SPECIAL_418>",
422
+ "<SPECIAL_419>",
423
+ "<SPECIAL_420>",
424
+ "<SPECIAL_421>",
425
+ "<SPECIAL_422>",
426
+ "<SPECIAL_423>",
427
+ "<SPECIAL_424>",
428
+ "<SPECIAL_425>",
429
+ "<SPECIAL_426>",
430
+ "<SPECIAL_427>",
431
+ "<SPECIAL_428>",
432
+ "<SPECIAL_429>",
433
+ "<SPECIAL_430>",
434
+ "<SPECIAL_431>",
435
+ "<SPECIAL_432>",
436
+ "<SPECIAL_433>",
437
+ "<SPECIAL_434>",
438
+ "<SPECIAL_435>",
439
+ "<SPECIAL_436>",
440
+ "<SPECIAL_437>",
441
+ "<SPECIAL_438>",
442
+ "<SPECIAL_439>",
443
+ "<SPECIAL_440>",
444
+ "<SPECIAL_441>",
445
+ "<SPECIAL_442>",
446
+ "<SPECIAL_443>",
447
+ "<SPECIAL_444>",
448
+ "<SPECIAL_445>",
449
+ "<SPECIAL_446>",
450
+ "<SPECIAL_447>",
451
+ "<SPECIAL_448>",
452
+ "<SPECIAL_449>",
453
+ "<SPECIAL_450>",
454
+ "<SPECIAL_451>",
455
+ "<SPECIAL_452>",
456
+ "<SPECIAL_453>",
457
+ "<SPECIAL_454>",
458
+ "<SPECIAL_455>",
459
+ "<SPECIAL_456>",
460
+ "<SPECIAL_457>",
461
+ "<SPECIAL_458>",
462
+ "<SPECIAL_459>",
463
+ "<SPECIAL_460>",
464
+ "<SPECIAL_461>",
465
+ "<SPECIAL_462>",
466
+ "<SPECIAL_463>",
467
+ "<SPECIAL_464>",
468
+ "<SPECIAL_465>",
469
+ "<SPECIAL_466>",
470
+ "<SPECIAL_467>",
471
+ "<SPECIAL_468>",
472
+ "<SPECIAL_469>",
473
+ "<SPECIAL_470>",
474
+ "<SPECIAL_471>",
475
+ "<SPECIAL_472>",
476
+ "<SPECIAL_473>",
477
+ "<SPECIAL_474>",
478
+ "<SPECIAL_475>",
479
+ "<SPECIAL_476>",
480
+ "<SPECIAL_477>",
481
+ "<SPECIAL_478>",
482
+ "<SPECIAL_479>",
483
+ "<SPECIAL_480>",
484
+ "<SPECIAL_481>",
485
+ "<SPECIAL_482>",
486
+ "<SPECIAL_483>",
487
+ "<SPECIAL_484>",
488
+ "<SPECIAL_485>",
489
+ "<SPECIAL_486>",
490
+ "<SPECIAL_487>",
491
+ "<SPECIAL_488>",
492
+ "<SPECIAL_489>",
493
+ "<SPECIAL_490>",
494
+ "<SPECIAL_491>",
495
+ "<SPECIAL_492>",
496
+ "<SPECIAL_493>",
497
+ "<SPECIAL_494>",
498
+ "<SPECIAL_495>",
499
+ "<SPECIAL_496>",
500
+ "<SPECIAL_497>",
501
+ "<SPECIAL_498>",
502
+ "<SPECIAL_499>",
503
+ "<SPECIAL_500>",
504
+ "<SPECIAL_501>",
505
+ "<SPECIAL_502>",
506
+ "<SPECIAL_503>",
507
+ "<SPECIAL_504>",
508
+ "<SPECIAL_505>",
509
+ "<SPECIAL_506>",
510
+ "<SPECIAL_507>",
511
+ "<SPECIAL_508>",
512
+ "<SPECIAL_509>",
513
+ "<SPECIAL_510>",
514
+ "<SPECIAL_511>",
515
+ "<SPECIAL_512>",
516
+ "<SPECIAL_513>",
517
+ "<SPECIAL_514>",
518
+ "<SPECIAL_515>",
519
+ "<SPECIAL_516>",
520
+ "<SPECIAL_517>",
521
+ "<SPECIAL_518>",
522
+ "<SPECIAL_519>",
523
+ "<SPECIAL_520>",
524
+ "<SPECIAL_521>",
525
+ "<SPECIAL_522>",
526
+ "<SPECIAL_523>",
527
+ "<SPECIAL_524>",
528
+ "<SPECIAL_525>",
529
+ "<SPECIAL_526>",
530
+ "<SPECIAL_527>",
531
+ "<SPECIAL_528>",
532
+ "<SPECIAL_529>",
533
+ "<SPECIAL_530>",
534
+ "<SPECIAL_531>",
535
+ "<SPECIAL_532>",
536
+ "<SPECIAL_533>",
537
+ "<SPECIAL_534>",
538
+ "<SPECIAL_535>",
539
+ "<SPECIAL_536>",
540
+ "<SPECIAL_537>",
541
+ "<SPECIAL_538>",
542
+ "<SPECIAL_539>",
543
+ "<SPECIAL_540>",
544
+ "<SPECIAL_541>",
545
+ "<SPECIAL_542>",
546
+ "<SPECIAL_543>",
547
+ "<SPECIAL_544>",
548
+ "<SPECIAL_545>",
549
+ "<SPECIAL_546>",
550
+ "<SPECIAL_547>",
551
+ "<SPECIAL_548>",
552
+ "<SPECIAL_549>",
553
+ "<SPECIAL_550>",
554
+ "<SPECIAL_551>",
555
+ "<SPECIAL_552>",
556
+ "<SPECIAL_553>",
557
+ "<SPECIAL_554>",
558
+ "<SPECIAL_555>",
559
+ "<SPECIAL_556>",
560
+ "<SPECIAL_557>",
561
+ "<SPECIAL_558>",
562
+ "<SPECIAL_559>",
563
+ "<SPECIAL_560>",
564
+ "<SPECIAL_561>",
565
+ "<SPECIAL_562>",
566
+ "<SPECIAL_563>",
567
+ "<SPECIAL_564>",
568
+ "<SPECIAL_565>",
569
+ "<SPECIAL_566>",
570
+ "<SPECIAL_567>",
571
+ "<SPECIAL_568>",
572
+ "<SPECIAL_569>",
573
+ "<SPECIAL_570>",
574
+ "<SPECIAL_571>",
575
+ "<SPECIAL_572>",
576
+ "<SPECIAL_573>",
577
+ "<SPECIAL_574>",
578
+ "<SPECIAL_575>",
579
+ "<SPECIAL_576>",
580
+ "<SPECIAL_577>",
581
+ "<SPECIAL_578>",
582
+ "<SPECIAL_579>",
583
+ "<SPECIAL_580>",
584
+ "<SPECIAL_581>",
585
+ "<SPECIAL_582>",
586
+ "<SPECIAL_583>",
587
+ "<SPECIAL_584>",
588
+ "<SPECIAL_585>",
589
+ "<SPECIAL_586>",
590
+ "<SPECIAL_587>",
591
+ "<SPECIAL_588>",
592
+ "<SPECIAL_589>",
593
+ "<SPECIAL_590>",
594
+ "<SPECIAL_591>",
595
+ "<SPECIAL_592>",
596
+ "<SPECIAL_593>",
597
+ "<SPECIAL_594>",
598
+ "<SPECIAL_595>",
599
+ "<SPECIAL_596>",
600
+ "<SPECIAL_597>",
601
+ "<SPECIAL_598>",
602
+ "<SPECIAL_599>",
603
+ "<SPECIAL_600>",
604
+ "<SPECIAL_601>",
605
+ "<SPECIAL_602>",
606
+ "<SPECIAL_603>",
607
+ "<SPECIAL_604>",
608
+ "<SPECIAL_605>",
609
+ "<SPECIAL_606>",
610
+ "<SPECIAL_607>",
611
+ "<SPECIAL_608>",
612
+ "<SPECIAL_609>",
613
+ "<SPECIAL_610>",
614
+ "<SPECIAL_611>",
615
+ "<SPECIAL_612>",
616
+ "<SPECIAL_613>",
617
+ "<SPECIAL_614>",
618
+ "<SPECIAL_615>",
619
+ "<SPECIAL_616>",
620
+ "<SPECIAL_617>",
621
+ "<SPECIAL_618>",
622
+ "<SPECIAL_619>",
623
+ "<SPECIAL_620>",
624
+ "<SPECIAL_621>",
625
+ "<SPECIAL_622>",
626
+ "<SPECIAL_623>",
627
+ "<SPECIAL_624>",
628
+ "<SPECIAL_625>",
629
+ "<SPECIAL_626>",
630
+ "<SPECIAL_627>",
631
+ "<SPECIAL_628>",
632
+ "<SPECIAL_629>",
633
+ "<SPECIAL_630>",
634
+ "<SPECIAL_631>",
635
+ "<SPECIAL_632>",
636
+ "<SPECIAL_633>",
637
+ "<SPECIAL_634>",
638
+ "<SPECIAL_635>",
639
+ "<SPECIAL_636>",
640
+ "<SPECIAL_637>",
641
+ "<SPECIAL_638>",
642
+ "<SPECIAL_639>",
643
+ "<SPECIAL_640>",
644
+ "<SPECIAL_641>",
645
+ "<SPECIAL_642>",
646
+ "<SPECIAL_643>",
647
+ "<SPECIAL_644>",
648
+ "<SPECIAL_645>",
649
+ "<SPECIAL_646>",
650
+ "<SPECIAL_647>",
651
+ "<SPECIAL_648>",
652
+ "<SPECIAL_649>",
653
+ "<SPECIAL_650>",
654
+ "<SPECIAL_651>",
655
+ "<SPECIAL_652>",
656
+ "<SPECIAL_653>",
657
+ "<SPECIAL_654>",
658
+ "<SPECIAL_655>",
659
+ "<SPECIAL_656>",
660
+ "<SPECIAL_657>",
661
+ "<SPECIAL_658>",
662
+ "<SPECIAL_659>",
663
+ "<SPECIAL_660>",
664
+ "<SPECIAL_661>",
665
+ "<SPECIAL_662>",
666
+ "<SPECIAL_663>",
667
+ "<SPECIAL_664>",
668
+ "<SPECIAL_665>",
669
+ "<SPECIAL_666>",
670
+ "<SPECIAL_667>",
671
+ "<SPECIAL_668>",
672
+ "<SPECIAL_669>",
673
+ "<SPECIAL_670>",
674
+ "<SPECIAL_671>",
675
+ "<SPECIAL_672>",
676
+ "<SPECIAL_673>",
677
+ "<SPECIAL_674>",
678
+ "<SPECIAL_675>",
679
+ "<SPECIAL_676>",
680
+ "<SPECIAL_677>",
681
+ "<SPECIAL_678>",
682
+ "<SPECIAL_679>",
683
+ "<SPECIAL_680>",
684
+ "<SPECIAL_681>",
685
+ "<SPECIAL_682>",
686
+ "<SPECIAL_683>",
687
+ "<SPECIAL_684>",
688
+ "<SPECIAL_685>",
689
+ "<SPECIAL_686>",
690
+ "<SPECIAL_687>",
691
+ "<SPECIAL_688>",
692
+ "<SPECIAL_689>",
693
+ "<SPECIAL_690>",
694
+ "<SPECIAL_691>",
695
+ "<SPECIAL_692>",
696
+ "<SPECIAL_693>",
697
+ "<SPECIAL_694>",
698
+ "<SPECIAL_695>",
699
+ "<SPECIAL_696>",
700
+ "<SPECIAL_697>",
701
+ "<SPECIAL_698>",
702
+ "<SPECIAL_699>",
703
+ "<SPECIAL_700>",
704
+ "<SPECIAL_701>",
705
+ "<SPECIAL_702>",
706
+ "<SPECIAL_703>",
707
+ "<SPECIAL_704>",
708
+ "<SPECIAL_705>",
709
+ "<SPECIAL_706>",
710
+ "<SPECIAL_707>",
711
+ "<SPECIAL_708>",
712
+ "<SPECIAL_709>",
713
+ "<SPECIAL_710>",
714
+ "<SPECIAL_711>",
715
+ "<SPECIAL_712>",
716
+ "<SPECIAL_713>",
717
+ "<SPECIAL_714>",
718
+ "<SPECIAL_715>",
719
+ "<SPECIAL_716>",
720
+ "<SPECIAL_717>",
721
+ "<SPECIAL_718>",
722
+ "<SPECIAL_719>",
723
+ "<SPECIAL_720>",
724
+ "<SPECIAL_721>",
725
+ "<SPECIAL_722>",
726
+ "<SPECIAL_723>",
727
+ "<SPECIAL_724>",
728
+ "<SPECIAL_725>",
729
+ "<SPECIAL_726>",
730
+ "<SPECIAL_727>",
731
+ "<SPECIAL_728>",
732
+ "<SPECIAL_729>",
733
+ "<SPECIAL_730>",
734
+ "<SPECIAL_731>",
735
+ "<SPECIAL_732>",
736
+ "<SPECIAL_733>",
737
+ "<SPECIAL_734>",
738
+ "<SPECIAL_735>",
739
+ "<SPECIAL_736>",
740
+ "<SPECIAL_737>",
741
+ "<SPECIAL_738>",
742
+ "<SPECIAL_739>",
743
+ "<SPECIAL_740>",
744
+ "<SPECIAL_741>",
745
+ "<SPECIAL_742>",
746
+ "<SPECIAL_743>",
747
+ "<SPECIAL_744>",
748
+ "<SPECIAL_745>",
749
+ "<SPECIAL_746>",
750
+ "<SPECIAL_747>",
751
+ "<SPECIAL_748>",
752
+ "<SPECIAL_749>",
753
+ "<SPECIAL_750>",
754
+ "<SPECIAL_751>",
755
+ "<SPECIAL_752>",
756
+ "<SPECIAL_753>",
757
+ "<SPECIAL_754>",
758
+ "<SPECIAL_755>",
759
+ "<SPECIAL_756>",
760
+ "<SPECIAL_757>",
761
+ "<SPECIAL_758>",
762
+ "<SPECIAL_759>",
763
+ "<SPECIAL_760>",
764
+ "<SPECIAL_761>",
765
+ "<SPECIAL_762>",
766
+ "<SPECIAL_763>",
767
+ "<SPECIAL_764>",
768
+ "<SPECIAL_765>",
769
+ "<SPECIAL_766>",
770
+ "<SPECIAL_767>",
771
+ "<SPECIAL_768>",
772
+ "<SPECIAL_769>",
773
+ "<SPECIAL_770>",
774
+ "<SPECIAL_771>",
775
+ "<SPECIAL_772>",
776
+ "<SPECIAL_773>",
777
+ "<SPECIAL_774>",
778
+ "<SPECIAL_775>",
779
+ "<SPECIAL_776>",
780
+ "<SPECIAL_777>",
781
+ "<SPECIAL_778>",
782
+ "<SPECIAL_779>",
783
+ "<SPECIAL_780>",
784
+ "<SPECIAL_781>",
785
+ "<SPECIAL_782>",
786
+ "<SPECIAL_783>",
787
+ "<SPECIAL_784>",
788
+ "<SPECIAL_785>",
789
+ "<SPECIAL_786>",
790
+ "<SPECIAL_787>",
791
+ "<SPECIAL_788>",
792
+ "<SPECIAL_789>",
793
+ "<SPECIAL_790>",
794
+ "<SPECIAL_791>",
795
+ "<SPECIAL_792>",
796
+ "<SPECIAL_793>",
797
+ "<SPECIAL_794>",
798
+ "<SPECIAL_795>",
799
+ "<SPECIAL_796>",
800
+ "<SPECIAL_797>",
801
+ "<SPECIAL_798>",
802
+ "<SPECIAL_799>",
803
+ "<SPECIAL_800>",
804
+ "<SPECIAL_801>",
805
+ "<SPECIAL_802>",
806
+ "<SPECIAL_803>",
807
+ "<SPECIAL_804>",
808
+ "<SPECIAL_805>",
809
+ "<SPECIAL_806>",
810
+ "<SPECIAL_807>",
811
+ "<SPECIAL_808>",
812
+ "<SPECIAL_809>",
813
+ "<SPECIAL_810>",
814
+ "<SPECIAL_811>",
815
+ "<SPECIAL_812>",
816
+ "<SPECIAL_813>",
817
+ "<SPECIAL_814>",
818
+ "<SPECIAL_815>",
819
+ "<SPECIAL_816>",
820
+ "<SPECIAL_817>",
821
+ "<SPECIAL_818>",
822
+ "<SPECIAL_819>",
823
+ "<SPECIAL_820>",
824
+ "<SPECIAL_821>",
825
+ "<SPECIAL_822>",
826
+ "<SPECIAL_823>",
827
+ "<SPECIAL_824>",
828
+ "<SPECIAL_825>",
829
+ "<SPECIAL_826>",
830
+ "<SPECIAL_827>",
831
+ "<SPECIAL_828>",
832
+ "<SPECIAL_829>",
833
+ "<SPECIAL_830>",
834
+ "<SPECIAL_831>",
835
+ "<SPECIAL_832>",
836
+ "<SPECIAL_833>",
837
+ "<SPECIAL_834>",
838
+ "<SPECIAL_835>",
839
+ "<SPECIAL_836>",
840
+ "<SPECIAL_837>",
841
+ "<SPECIAL_838>",
842
+ "<SPECIAL_839>",
843
+ "<SPECIAL_840>",
844
+ "<SPECIAL_841>",
845
+ "<SPECIAL_842>",
846
+ "<SPECIAL_843>",
847
+ "<SPECIAL_844>",
848
+ "<SPECIAL_845>",
849
+ "<SPECIAL_846>",
850
+ "<SPECIAL_847>",
851
+ "<SPECIAL_848>",
852
+ "<SPECIAL_849>",
853
+ "<SPECIAL_850>",
854
+ "<SPECIAL_851>",
855
+ "<SPECIAL_852>",
856
+ "<SPECIAL_853>",
857
+ "<SPECIAL_854>",
858
+ "<SPECIAL_855>",
859
+ "<SPECIAL_856>",
860
+ "<SPECIAL_857>",
861
+ "<SPECIAL_858>",
862
+ "<SPECIAL_859>",
863
+ "<SPECIAL_860>",
864
+ "<SPECIAL_861>",
865
+ "<SPECIAL_862>",
866
+ "<SPECIAL_863>",
867
+ "<SPECIAL_864>",
868
+ "<SPECIAL_865>",
869
+ "<SPECIAL_866>",
870
+ "<SPECIAL_867>",
871
+ "<SPECIAL_868>",
872
+ "<SPECIAL_869>",
873
+ "<SPECIAL_870>",
874
+ "<SPECIAL_871>",
875
+ "<SPECIAL_872>",
876
+ "<SPECIAL_873>",
877
+ "<SPECIAL_874>",
878
+ "<SPECIAL_875>",
879
+ "<SPECIAL_876>",
880
+ "<SPECIAL_877>",
881
+ "<SPECIAL_878>",
882
+ "<SPECIAL_879>",
883
+ "<SPECIAL_880>",
884
+ "<SPECIAL_881>",
885
+ "<SPECIAL_882>",
886
+ "<SPECIAL_883>",
887
+ "<SPECIAL_884>",
888
+ "<SPECIAL_885>",
889
+ "<SPECIAL_886>",
890
+ "<SPECIAL_887>",
891
+ "<SPECIAL_888>",
892
+ "<SPECIAL_889>",
893
+ "<SPECIAL_890>",
894
+ "<SPECIAL_891>",
895
+ "<SPECIAL_892>",
896
+ "<SPECIAL_893>",
897
+ "<SPECIAL_894>",
898
+ "<SPECIAL_895>",
899
+ "<SPECIAL_896>",
900
+ "<SPECIAL_897>",
901
+ "<SPECIAL_898>",
902
+ "<SPECIAL_899>",
903
+ "<SPECIAL_900>",
904
+ "<SPECIAL_901>",
905
+ "<SPECIAL_902>",
906
+ "<SPECIAL_903>",
907
+ "<SPECIAL_904>",
908
+ "<SPECIAL_905>",
909
+ "<SPECIAL_906>",
910
+ "<SPECIAL_907>",
911
+ "<SPECIAL_908>",
912
+ "<SPECIAL_909>",
913
+ "<SPECIAL_910>",
914
+ "<SPECIAL_911>",
915
+ "<SPECIAL_912>",
916
+ "<SPECIAL_913>",
917
+ "<SPECIAL_914>",
918
+ "<SPECIAL_915>",
919
+ "<SPECIAL_916>",
920
+ "<SPECIAL_917>",
921
+ "<SPECIAL_918>",
922
+ "<SPECIAL_919>",
923
+ "<SPECIAL_920>",
924
+ "<SPECIAL_921>",
925
+ "<SPECIAL_922>",
926
+ "<SPECIAL_923>",
927
+ "<SPECIAL_924>",
928
+ "<SPECIAL_925>",
929
+ "<SPECIAL_926>",
930
+ "<SPECIAL_927>",
931
+ "<SPECIAL_928>",
932
+ "<SPECIAL_929>",
933
+ "<SPECIAL_930>",
934
+ "<SPECIAL_931>",
935
+ "<SPECIAL_932>",
936
+ "<SPECIAL_933>",
937
+ "<SPECIAL_934>",
938
+ "<SPECIAL_935>",
939
+ "<SPECIAL_936>",
940
+ "<SPECIAL_937>",
941
+ "<SPECIAL_938>",
942
+ "<SPECIAL_939>",
943
+ "<SPECIAL_940>",
944
+ "<SPECIAL_941>",
945
+ "<SPECIAL_942>",
946
+ "<SPECIAL_943>",
947
+ "<SPECIAL_944>",
948
+ "<SPECIAL_945>",
949
+ "<SPECIAL_946>",
950
+ "<SPECIAL_947>",
951
+ "<SPECIAL_948>",
952
+ "<SPECIAL_949>",
953
+ "<SPECIAL_950>",
954
+ "<SPECIAL_951>",
955
+ "<SPECIAL_952>",
956
+ "<SPECIAL_953>",
957
+ "<SPECIAL_954>",
958
+ "<SPECIAL_955>",
959
+ "<SPECIAL_956>",
960
+ "<SPECIAL_957>",
961
+ "<SPECIAL_958>",
962
+ "<SPECIAL_959>",
963
+ "<SPECIAL_960>",
964
+ "<SPECIAL_961>",
965
+ "<SPECIAL_962>",
966
+ "<SPECIAL_963>",
967
+ "<SPECIAL_964>",
968
+ "<SPECIAL_965>",
969
+ "<SPECIAL_966>",
970
+ "<SPECIAL_967>",
971
+ "<SPECIAL_968>",
972
+ "<SPECIAL_969>",
973
+ "<SPECIAL_970>",
974
+ "<SPECIAL_971>",
975
+ "<SPECIAL_972>",
976
+ "<SPECIAL_973>",
977
+ "<SPECIAL_974>",
978
+ "<SPECIAL_975>",
979
+ "<SPECIAL_976>",
980
+ "<SPECIAL_977>",
981
+ "<SPECIAL_978>",
982
+ "<SPECIAL_979>",
983
+ "<SPECIAL_980>",
984
+ "<SPECIAL_981>",
985
+ "<SPECIAL_982>",
986
+ "<SPECIAL_983>",
987
+ "<SPECIAL_984>",
988
+ "<SPECIAL_985>",
989
+ "<SPECIAL_986>",
990
+ "<SPECIAL_987>",
991
+ "<SPECIAL_988>",
992
+ "<SPECIAL_989>",
993
+ "<SPECIAL_990>",
994
+ "<SPECIAL_991>",
995
+ "<SPECIAL_992>",
996
+ "<SPECIAL_993>",
997
+ "<SPECIAL_994>",
998
+ "<SPECIAL_995>",
999
+ "<SPECIAL_996>",
1000
+ "<SPECIAL_997>",
1001
+ "<SPECIAL_998>",
1002
+ "<SPECIAL_999>"
1003
+ ],
1004
+ "bos_token": {
1005
+ "content": "<s>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false
1010
+ },
1011
+ "eos_token": {
1012
+ "content": "</s>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false
1017
+ },
1018
+ "unk_token": {
1019
+ "content": "<unk>",
1020
+ "lstrip": false,
1021
+ "normalized": false,
1022
+ "rstrip": false,
1023
+ "single_word": false
1024
+ }
1025
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
3
+ size 17078037
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff