Hugging Face's logo

speakleash
/
Bielik-11B-v2.0-Instruct-FP8

Text Generation
Transformers
Safetensors
GGUF
Polish
mistral
finetuned
8bit
conversational
text-generation-inference
fp8
Model card Files Community
Remek commited on
Commit
e8d6b33
•
1 Parent(s): 7ef20f3

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. added_tokens.json +130 -0
  2. config.json +34 -0
  3. generation_config.json +6 -0
  4. model-00001-of-00003.safetensors +3 -0
  5. model-00002-of-00003.safetensors +3 -0
  6. model-00003-of-00003.safetensors +3 -0
  7. model.safetensors.index.json +1160 -0
  8. special_tokens_map.json +160 -0
  9. tokenizer.json +0 -0
  10. tokenizer.model +3 -0
  11. tokenizer_config.json +1197 -0
added_tokens.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|control_100|>": 32099,
3
+ "<|control_101|>": 32100,
4
+ "<|control_102|>": 32101,
5
+ "<|control_103|>": 32102,
6
+ "<|control_104|>": 32103,
7
+ "<|control_105|>": 32104,
8
+ "<|control_106|>": 32105,
9
+ "<|control_107|>": 32106,
10
+ "<|control_108|>": 32107,
11
+ "<|control_109|>": 32108,
12
+ "<|control_10|>": 32009,
13
+ "<|control_110|>": 32109,
14
+ "<|control_111|>": 32110,
15
+ "<|control_112|>": 32111,
16
+ "<|control_113|>": 32112,
17
+ "<|control_114|>": 32113,
18
+ "<|control_115|>": 32114,
19
+ "<|control_116|>": 32115,
20
+ "<|control_117|>": 32116,
21
+ "<|control_118|>": 32117,
22
+ "<|control_119|>": 32118,
23
+ "<|control_11|>": 32010,
24
+ "<|control_120|>": 32119,
25
+ "<|control_121|>": 32120,
26
+ "<|control_122|>": 32121,
27
+ "<|control_123|>": 32122,
28
+ "<|control_124|>": 32123,
29
+ "<|control_125|>": 32124,
30
+ "<|control_126|>": 32125,
31
+ "<|control_127|>": 32126,
32
+ "<|control_128|>": 32127,
33
+ "<|control_12|>": 32011,
34
+ "<|control_13|>": 32012,
35
+ "<|control_14|>": 32013,
36
+ "<|control_15|>": 32014,
37
+ "<|control_16|>": 32015,
38
+ "<|control_17|>": 32016,
39
+ "<|control_18|>": 32017,
40
+ "<|control_19|>": 32018,
41
+ "<|control_20|>": 32019,
42
+ "<|control_21|>": 32020,
43
+ "<|control_22|>": 32021,
44
+ "<|control_23|>": 32022,
45
+ "<|control_24|>": 32023,
46
+ "<|control_25|>": 32024,
47
+ "<|control_26|>": 32025,
48
+ "<|control_27|>": 32026,
49
+ "<|control_28|>": 32027,
50
+ "<|control_29|>": 32028,
51
+ "<|control_30|>": 32029,
52
+ "<|control_31|>": 32030,
53
+ "<|control_32|>": 32031,
54
+ "<|control_33|>": 32032,
55
+ "<|control_34|>": 32033,
56
+ "<|control_35|>": 32034,
57
+ "<|control_36|>": 32035,
58
+ "<|control_37|>": 32036,
59
+ "<|control_38|>": 32037,
60
+ "<|control_39|>": 32038,
61
+ "<|control_40|>": 32039,
62
+ "<|control_41|>": 32040,
63
+ "<|control_42|>": 32041,
64
+ "<|control_43|>": 32042,
65
+ "<|control_44|>": 32043,
66
+ "<|control_45|>": 32044,
67
+ "<|control_46|>": 32045,
68
+ "<|control_47|>": 32046,
69
+ "<|control_48|>": 32047,
70
+ "<|control_49|>": 32048,
71
+ "<|control_50|>": 32049,
72
+ "<|control_51|>": 32050,
73
+ "<|control_52|>": 32051,
74
+ "<|control_53|>": 32052,
75
+ "<|control_54|>": 32053,
76
+ "<|control_55|>": 32054,
77
+ "<|control_56|>": 32055,
78
+ "<|control_57|>": 32056,
79
+ "<|control_58|>": 32057,
80
+ "<|control_59|>": 32058,
81
+ "<|control_60|>": 32059,
82
+ "<|control_61|>": 32060,
83
+ "<|control_62|>": 32061,
84
+ "<|control_63|>": 32062,
85
+ "<|control_64|>": 32063,
86
+ "<|control_65|>": 32064,
87
+ "<|control_66|>": 32065,
88
+ "<|control_67|>": 32066,
89
+ "<|control_68|>": 32067,
90
+ "<|control_69|>": 32068,
91
+ "<|control_6|>": 32005,
92
+ "<|control_70|>": 32069,
93
+ "<|control_71|>": 32070,
94
+ "<|control_72|>": 32071,
95
+ "<|control_73|>": 32072,
96
+ "<|control_74|>": 32073,
97
+ "<|control_75|>": 32074,
98
+ "<|control_76|>": 32075,
99
+ "<|control_77|>": 32076,
100
+ "<|control_78|>": 32077,
101
+ "<|control_79|>": 32078,
102
+ "<|control_7|>": 32006,
103
+ "<|control_80|>": 32079,
104
+ "<|control_81|>": 32080,
105
+ "<|control_82|>": 32081,
106
+ "<|control_83|>": 32082,
107
+ "<|control_84|>": 32083,
108
+ "<|control_85|>": 32084,
109
+ "<|control_86|>": 32085,
110
+ "<|control_87|>": 32086,
111
+ "<|control_88|>": 32087,
112
+ "<|control_89|>": 32088,
113
+ "<|control_8|>": 32007,
114
+ "<|control_90|>": 32089,
115
+ "<|control_91|>": 32090,
116
+ "<|control_92|>": 32091,
117
+ "<|control_93|>": 32092,
118
+ "<|control_94|>": 32093,
119
+ "<|control_95|>": 32094,
120
+ "<|control_96|>": 32095,
121
+ "<|control_97|>": 32096,
122
+ "<|control_98|>": 32097,
123
+ "<|control_99|>": 32098,
124
+ "<|control_9|>": 32008,
125
+ "<|function_call|>": 32004,
126
+ "<|function_list|>": 32002,
127
+ "<|function_output|>": 32003,
128
+ "<|im_end|>": 32001,
129
+ "<|im_start|>": 32000
130
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/sda/llm/quant/models/2.0/",
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": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 50,
18
+ "num_key_value_heads": 8,
19
+ "quantization_config": {
20
+ "activation_scheme": "static",
21
+ "ignored_layers": [
22
+ "lm_head"
23
+ ],
24
+ "quant_method": "fp8"
25
+ },
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_theta": 1000000,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.44.2",
32
+ "use_cache": true,
33
+ "vocab_size": 32128
34
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.44.2"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b31681020bde6a7448c10aaf6e4e304a905f7a59a84d0379cf34ebf68170f9
3
+ size 4944433856
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:541d3eb75ea3a7cfea56e1541d0b818464188aa703e9b200cb3bb85ef7986ed2
3
+ size 4958100984
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01953630932d9af6d93f06949b31858448481ac444722b47cd8f6c69b835cb35
3
+ size 1529992664
model.safetensors.index.json ADDED
@@ -0,0 +1,1160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11432405744
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
22
+ "model.layers.0.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
23
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
25
+ "model.layers.0.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
26
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
28
+ "model.layers.0.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
29
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
31
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
36
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
38
+ "model.layers.1.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
39
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
41
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.1.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
43
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
45
+ "model.layers.1.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
46
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
47
+ "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
48
+ "model.layers.1.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
49
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
51
+ "model.layers.1.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
52
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
54
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
55
+ "model.layers.10.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
56
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
57
+ "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
58
+ "model.layers.10.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
59
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
60
+ "model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
61
+ "model.layers.10.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
62
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
63
+ "model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
64
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
65
+ "model.layers.10.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
66
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
67
+ "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
68
+ "model.layers.10.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
69
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
70
+ "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
71
+ "model.layers.10.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
72
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
73
+ "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
74
+ "model.layers.10.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
75
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
76
+ "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
77
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
78
+ "model.layers.11.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
79
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
80
+ "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
81
+ "model.layers.11.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
82
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
83
+ "model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
84
+ "model.layers.11.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
85
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
86
+ "model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
87
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
88
+ "model.layers.11.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
89
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
90
+ "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
91
+ "model.layers.11.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
92
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
93
+ "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
94
+ "model.layers.11.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
95
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
96
+ "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
97
+ "model.layers.11.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
98
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
99
+ "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
100
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
101
+ "model.layers.12.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
102
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
103
+ "model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
104
+ "model.layers.12.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
105
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
106
+ "model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
107
+ "model.layers.12.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
108
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
109
+ "model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
110
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
111
+ "model.layers.12.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
112
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
113
+ "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
114
+ "model.layers.12.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
115
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
116
+ "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
117
+ "model.layers.12.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
118
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
120
+ "model.layers.12.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
121
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
123
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.13.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
125
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
126
+ "model.layers.13.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
127
+ "model.layers.13.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
128
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
129
+ "model.layers.13.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
130
+ "model.layers.13.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
131
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
132
+ "model.layers.13.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
133
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
134
+ "model.layers.13.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
135
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
136
+ "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
137
+ "model.layers.13.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
138
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
139
+ "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
140
+ "model.layers.13.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
141
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
142
+ "model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
143
+ "model.layers.13.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
144
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
145
+ "model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
146
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
147
+ "model.layers.14.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
148
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
149
+ "model.layers.14.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
150
+ "model.layers.14.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
151
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
152
+ "model.layers.14.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
153
+ "model.layers.14.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
154
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
155
+ "model.layers.14.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
156
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
157
+ "model.layers.14.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
158
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
159
+ "model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
160
+ "model.layers.14.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
161
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
162
+ "model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
163
+ "model.layers.14.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
164
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
165
+ "model.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
166
+ "model.layers.14.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
167
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
168
+ "model.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
169
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
170
+ "model.layers.15.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
171
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
172
+ "model.layers.15.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
173
+ "model.layers.15.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
174
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
175
+ "model.layers.15.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
176
+ "model.layers.15.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
177
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
178
+ "model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
179
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
180
+ "model.layers.15.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
181
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
182
+ "model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
183
+ "model.layers.15.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
184
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
185
+ "model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
186
+ "model.layers.15.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
187
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
188
+ "model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
189
+ "model.layers.15.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
190
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
191
+ "model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
192
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
193
+ "model.layers.16.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
194
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
195
+ "model.layers.16.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
196
+ "model.layers.16.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
197
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
198
+ "model.layers.16.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
199
+ "model.layers.16.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
200
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
201
+ "model.layers.16.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
202
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
203
+ "model.layers.16.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
204
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
205
+ "model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
206
+ "model.layers.16.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
207
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
208
+ "model.layers.16.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
209
+ "model.layers.16.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
210
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
211
+ "model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
212
+ "model.layers.16.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
213
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
214
+ "model.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
215
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.17.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
217
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.17.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
219
+ "model.layers.17.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
220
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.17.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
222
+ "model.layers.17.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
223
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.17.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
225
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
226
+ "model.layers.17.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
227
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
228
+ "model.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
229
+ "model.layers.17.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
230
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
231
+ "model.layers.17.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
232
+ "model.layers.17.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
233
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
234
+ "model.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
235
+ "model.layers.17.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
236
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
237
+ "model.layers.17.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
238
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.18.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
240
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.18.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
242
+ "model.layers.18.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
243
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.18.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
245
+ "model.layers.18.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
246
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.18.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
248
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.18.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
250
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.18.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
252
+ "model.layers.18.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
253
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.18.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
255
+ "model.layers.18.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
256
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.18.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
258
+ "model.layers.18.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
259
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.18.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
261
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.19.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
263
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.19.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
265
+ "model.layers.19.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
266
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.19.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
268
+ "model.layers.19.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
269
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.19.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
271
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.19.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
273
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.19.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
275
+ "model.layers.19.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
276
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.19.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
278
+ "model.layers.19.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
279
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.19.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
281
+ "model.layers.19.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
282
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.19.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
284
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.2.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
286
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
288
+ "model.layers.2.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
289
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
291
+ "model.layers.2.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
292
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
294
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.2.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
296
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
297
+ "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
298
+ "model.layers.2.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
299
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
300
+ "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
301
+ "model.layers.2.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
302
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
303
+ "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
304
+ "model.layers.2.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
305
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
306
+ "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
307
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
308
+ "model.layers.20.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
309
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
310
+ "model.layers.20.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
311
+ "model.layers.20.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
312
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
313
+ "model.layers.20.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
314
+ "model.layers.20.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
315
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
316
+ "model.layers.20.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
317
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
318
+ "model.layers.20.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
319
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
320
+ "model.layers.20.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
321
+ "model.layers.20.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
322
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
323
+ "model.layers.20.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
324
+ "model.layers.20.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
325
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
326
+ "model.layers.20.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
327
+ "model.layers.20.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
328
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
329
+ "model.layers.20.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
330
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
331
+ "model.layers.21.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
332
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
333
+ "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
334
+ "model.layers.21.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
335
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
336
+ "model.layers.21.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
337
+ "model.layers.21.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
338
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
339
+ "model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
340
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
341
+ "model.layers.21.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
342
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
343
+ "model.layers.21.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
344
+ "model.layers.21.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
345
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
346
+ "model.layers.21.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
347
+ "model.layers.21.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
348
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
349
+ "model.layers.21.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
350
+ "model.layers.21.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
351
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
352
+ "model.layers.21.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
353
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
354
+ "model.layers.22.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
355
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
356
+ "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
357
+ "model.layers.22.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
358
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
359
+ "model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
360
+ "model.layers.22.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
361
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
362
+ "model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
363
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
364
+ "model.layers.22.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
365
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
366
+ "model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
367
+ "model.layers.22.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
368
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
369
+ "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
370
+ "model.layers.22.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
371
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
372
+ "model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
373
+ "model.layers.22.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
374
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
375
+ "model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
376
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
377
+ "model.layers.23.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
378
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
379
+ "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
380
+ "model.layers.23.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
381
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
382
+ "model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
383
+ "model.layers.23.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
384
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
385
+ "model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
386
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
387
+ "model.layers.23.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
388
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
389
+ "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
390
+ "model.layers.23.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
391
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
392
+ "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
393
+ "model.layers.23.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
394
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
395
+ "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
396
+ "model.layers.23.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
397
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
398
+ "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
399
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
400
+ "model.layers.24.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
401
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
402
+ "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
403
+ "model.layers.24.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
404
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
405
+ "model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
406
+ "model.layers.24.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
407
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
408
+ "model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
409
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
410
+ "model.layers.24.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
411
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
412
+ "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
413
+ "model.layers.24.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
414
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
415
+ "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
416
+ "model.layers.24.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
417
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
418
+ "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
419
+ "model.layers.24.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
420
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
421
+ "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
422
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
423
+ "model.layers.25.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
424
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
425
+ "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
426
+ "model.layers.25.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
427
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
428
+ "model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
429
+ "model.layers.25.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
430
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
431
+ "model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
432
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
433
+ "model.layers.25.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
434
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
435
+ "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
436
+ "model.layers.25.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
437
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
438
+ "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
439
+ "model.layers.25.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
440
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
441
+ "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
442
+ "model.layers.25.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
443
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
444
+ "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
445
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
446
+ "model.layers.26.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
447
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
448
+ "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
449
+ "model.layers.26.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
450
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
451
+ "model.layers.26.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
452
+ "model.layers.26.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
453
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
454
+ "model.layers.26.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
455
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
456
+ "model.layers.26.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
457
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
458
+ "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
459
+ "model.layers.26.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
460
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
461
+ "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
462
+ "model.layers.26.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
463
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
464
+ "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
465
+ "model.layers.26.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
466
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
467
+ "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
468
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
469
+ "model.layers.27.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
470
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
471
+ "model.layers.27.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
472
+ "model.layers.27.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
473
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
474
+ "model.layers.27.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
475
+ "model.layers.27.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
476
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
477
+ "model.layers.27.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
478
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
479
+ "model.layers.27.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
480
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
481
+ "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
482
+ "model.layers.27.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
483
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
484
+ "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
485
+ "model.layers.27.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
486
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
487
+ "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
488
+ "model.layers.27.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
489
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
490
+ "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
491
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
492
+ "model.layers.28.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
493
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
494
+ "model.layers.28.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
495
+ "model.layers.28.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
496
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
497
+ "model.layers.28.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
498
+ "model.layers.28.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
499
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
500
+ "model.layers.28.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
501
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
502
+ "model.layers.28.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
503
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
504
+ "model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
505
+ "model.layers.28.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
506
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
507
+ "model.layers.28.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
508
+ "model.layers.28.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
509
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
510
+ "model.layers.28.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
511
+ "model.layers.28.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
512
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
513
+ "model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
514
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
515
+ "model.layers.29.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
516
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
517
+ "model.layers.29.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
518
+ "model.layers.29.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
519
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
520
+ "model.layers.29.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
521
+ "model.layers.29.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
522
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
523
+ "model.layers.29.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
524
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
525
+ "model.layers.29.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
526
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
527
+ "model.layers.29.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
528
+ "model.layers.29.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
529
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
530
+ "model.layers.29.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
531
+ "model.layers.29.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
532
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
533
+ "model.layers.29.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
534
+ "model.layers.29.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
535
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
536
+ "model.layers.29.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
537
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
538
+ "model.layers.3.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
539
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
540
+ "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
541
+ "model.layers.3.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
542
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
543
+ "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
544
+ "model.layers.3.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
545
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
546
+ "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
547
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
548
+ "model.layers.3.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
549
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
550
+ "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
551
+ "model.layers.3.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
552
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
553
+ "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
554
+ "model.layers.3.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
555
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
556
+ "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
557
+ "model.layers.3.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
558
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
559
+ "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
560
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
561
+ "model.layers.30.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
562
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
563
+ "model.layers.30.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
564
+ "model.layers.30.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
565
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
566
+ "model.layers.30.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
567
+ "model.layers.30.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
568
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
569
+ "model.layers.30.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
570
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
571
+ "model.layers.30.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
572
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
573
+ "model.layers.30.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
574
+ "model.layers.30.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
575
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
576
+ "model.layers.30.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
577
+ "model.layers.30.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
578
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
579
+ "model.layers.30.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
580
+ "model.layers.30.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
581
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
582
+ "model.layers.30.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
583
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
584
+ "model.layers.31.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
585
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
586
+ "model.layers.31.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
587
+ "model.layers.31.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
588
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
589
+ "model.layers.31.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
590
+ "model.layers.31.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
591
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
592
+ "model.layers.31.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
593
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
594
+ "model.layers.31.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
595
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
596
+ "model.layers.31.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
597
+ "model.layers.31.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
598
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
599
+ "model.layers.31.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
600
+ "model.layers.31.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
601
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
602
+ "model.layers.31.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
603
+ "model.layers.31.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
604
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
605
+ "model.layers.31.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
606
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
607
+ "model.layers.32.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
608
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
609
+ "model.layers.32.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
610
+ "model.layers.32.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
611
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
612
+ "model.layers.32.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
613
+ "model.layers.32.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
614
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
615
+ "model.layers.32.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
616
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
617
+ "model.layers.32.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
618
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
619
+ "model.layers.32.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
620
+ "model.layers.32.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
621
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
622
+ "model.layers.32.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
623
+ "model.layers.32.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
624
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
625
+ "model.layers.32.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
626
+ "model.layers.32.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
627
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
628
+ "model.layers.32.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
629
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
630
+ "model.layers.33.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
631
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
632
+ "model.layers.33.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
633
+ "model.layers.33.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
634
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
635
+ "model.layers.33.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
636
+ "model.layers.33.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
637
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
638
+ "model.layers.33.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
639
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
640
+ "model.layers.33.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
641
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
642
+ "model.layers.33.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
643
+ "model.layers.33.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
644
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
645
+ "model.layers.33.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
646
+ "model.layers.33.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
647
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
648
+ "model.layers.33.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
649
+ "model.layers.33.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
650
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
651
+ "model.layers.33.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
652
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
653
+ "model.layers.34.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
654
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
655
+ "model.layers.34.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
656
+ "model.layers.34.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
657
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
658
+ "model.layers.34.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
659
+ "model.layers.34.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
660
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
661
+ "model.layers.34.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
662
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
663
+ "model.layers.34.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
664
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
665
+ "model.layers.34.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
666
+ "model.layers.34.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
667
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
668
+ "model.layers.34.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
669
+ "model.layers.34.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
670
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
671
+ "model.layers.34.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
672
+ "model.layers.34.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
673
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
674
+ "model.layers.34.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
675
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
676
+ "model.layers.35.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
677
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
678
+ "model.layers.35.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
679
+ "model.layers.35.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
680
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
681
+ "model.layers.35.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
682
+ "model.layers.35.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
683
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
684
+ "model.layers.35.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
685
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
686
+ "model.layers.35.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
687
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
688
+ "model.layers.35.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
689
+ "model.layers.35.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
690
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
691
+ "model.layers.35.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
692
+ "model.layers.35.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
693
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
694
+ "model.layers.35.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
695
+ "model.layers.35.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
696
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
697
+ "model.layers.35.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
698
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
699
+ "model.layers.36.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
700
+ "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
701
+ "model.layers.36.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
702
+ "model.layers.36.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
703
+ "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
704
+ "model.layers.36.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
705
+ "model.layers.36.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
706
+ "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
707
+ "model.layers.36.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
708
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
709
+ "model.layers.36.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
710
+ "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
711
+ "model.layers.36.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
712
+ "model.layers.36.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
713
+ "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
714
+ "model.layers.36.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
715
+ "model.layers.36.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
716
+ "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
717
+ "model.layers.36.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
718
+ "model.layers.36.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
719
+ "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
720
+ "model.layers.36.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
721
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
722
+ "model.layers.37.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
723
+ "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
724
+ "model.layers.37.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
725
+ "model.layers.37.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
726
+ "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
727
+ "model.layers.37.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
728
+ "model.layers.37.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
729
+ "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
730
+ "model.layers.37.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
731
+ "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
732
+ "model.layers.37.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
733
+ "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
734
+ "model.layers.37.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
735
+ "model.layers.37.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
736
+ "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
737
+ "model.layers.37.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
738
+ "model.layers.37.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
739
+ "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
740
+ "model.layers.37.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
741
+ "model.layers.37.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
742
+ "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
743
+ "model.layers.37.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
744
+ "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
745
+ "model.layers.38.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
746
+ "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
747
+ "model.layers.38.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
748
+ "model.layers.38.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
749
+ "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
750
+ "model.layers.38.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
751
+ "model.layers.38.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
752
+ "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
753
+ "model.layers.38.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
754
+ "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
755
+ "model.layers.38.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
756
+ "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
757
+ "model.layers.38.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
758
+ "model.layers.38.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
759
+ "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
760
+ "model.layers.38.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
761
+ "model.layers.38.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
762
+ "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
763
+ "model.layers.38.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
764
+ "model.layers.38.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
765
+ "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
766
+ "model.layers.38.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
767
+ "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
768
+ "model.layers.39.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
769
+ "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
770
+ "model.layers.39.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
771
+ "model.layers.39.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
772
+ "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
773
+ "model.layers.39.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
774
+ "model.layers.39.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
775
+ "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
776
+ "model.layers.39.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
777
+ "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
778
+ "model.layers.39.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
779
+ "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
780
+ "model.layers.39.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
781
+ "model.layers.39.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
782
+ "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
783
+ "model.layers.39.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
784
+ "model.layers.39.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
785
+ "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
786
+ "model.layers.39.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
787
+ "model.layers.39.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
788
+ "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
789
+ "model.layers.39.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
790
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
791
+ "model.layers.4.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
792
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
793
+ "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
794
+ "model.layers.4.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
795
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
796
+ "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
797
+ "model.layers.4.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
798
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
799
+ "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
800
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
801
+ "model.layers.4.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
802
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
803
+ "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
804
+ "model.layers.4.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
805
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
806
+ "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
807
+ "model.layers.4.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
808
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
809
+ "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
810
+ "model.layers.4.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
811
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
812
+ "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
813
+ "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors",
814
+ "model.layers.40.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
815
+ "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
816
+ "model.layers.40.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
817
+ "model.layers.40.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
818
+ "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
819
+ "model.layers.40.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
820
+ "model.layers.40.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
821
+ "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
822
+ "model.layers.40.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
823
+ "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
824
+ "model.layers.40.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
825
+ "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
826
+ "model.layers.40.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
827
+ "model.layers.40.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
828
+ "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
829
+ "model.layers.40.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
830
+ "model.layers.40.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
831
+ "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
832
+ "model.layers.40.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
833
+ "model.layers.40.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
834
+ "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
835
+ "model.layers.40.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
836
+ "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors",
837
+ "model.layers.41.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
838
+ "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
839
+ "model.layers.41.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
840
+ "model.layers.41.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
841
+ "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
842
+ "model.layers.41.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
843
+ "model.layers.41.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
844
+ "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
845
+ "model.layers.41.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
846
+ "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
847
+ "model.layers.41.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
848
+ "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
849
+ "model.layers.41.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
850
+ "model.layers.41.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
851
+ "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
852
+ "model.layers.41.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
853
+ "model.layers.41.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
854
+ "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
855
+ "model.layers.41.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
856
+ "model.layers.41.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
857
+ "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
858
+ "model.layers.41.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
859
+ "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors",
860
+ "model.layers.42.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
861
+ "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
862
+ "model.layers.42.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
863
+ "model.layers.42.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
864
+ "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
865
+ "model.layers.42.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
866
+ "model.layers.42.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
867
+ "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
868
+ "model.layers.42.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
869
+ "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
870
+ "model.layers.42.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
871
+ "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
872
+ "model.layers.42.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
873
+ "model.layers.42.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
874
+ "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
875
+ "model.layers.42.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
876
+ "model.layers.42.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
877
+ "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
878
+ "model.layers.42.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
879
+ "model.layers.42.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
880
+ "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
881
+ "model.layers.42.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
882
+ "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors",
883
+ "model.layers.43.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
884
+ "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
885
+ "model.layers.43.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
886
+ "model.layers.43.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
887
+ "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
888
+ "model.layers.43.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
889
+ "model.layers.43.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
890
+ "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
891
+ "model.layers.43.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
892
+ "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
893
+ "model.layers.43.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
894
+ "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
895
+ "model.layers.43.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
896
+ "model.layers.43.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
897
+ "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
898
+ "model.layers.43.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
899
+ "model.layers.43.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
900
+ "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
901
+ "model.layers.43.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
902
+ "model.layers.43.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
903
+ "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
904
+ "model.layers.43.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
905
+ "model.layers.44.input_layernorm.weight": "model-00003-of-00003.safetensors",
906
+ "model.layers.44.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
907
+ "model.layers.44.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
908
+ "model.layers.44.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
909
+ "model.layers.44.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
910
+ "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
911
+ "model.layers.44.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
912
+ "model.layers.44.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
913
+ "model.layers.44.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
914
+ "model.layers.44.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
915
+ "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
916
+ "model.layers.44.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
917
+ "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
918
+ "model.layers.44.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
919
+ "model.layers.44.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
920
+ "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
921
+ "model.layers.44.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
922
+ "model.layers.44.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
923
+ "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
924
+ "model.layers.44.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
925
+ "model.layers.44.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
926
+ "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
927
+ "model.layers.44.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
928
+ "model.layers.45.input_layernorm.weight": "model-00003-of-00003.safetensors",
929
+ "model.layers.45.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
930
+ "model.layers.45.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
931
+ "model.layers.45.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
932
+ "model.layers.45.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
933
+ "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
934
+ "model.layers.45.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
935
+ "model.layers.45.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
936
+ "model.layers.45.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
937
+ "model.layers.45.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
938
+ "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
939
+ "model.layers.45.self_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
940
+ "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
941
+ "model.layers.45.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
942
+ "model.layers.45.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
943
+ "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
944
+ "model.layers.45.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
945
+ "model.layers.45.self_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
946
+ "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
947
+ "model.layers.45.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
948
+ "model.layers.45.self_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
949
+ "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
950
+ "model.layers.45.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
951
+ "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
952
+ "model.layers.46.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
953
+ "model.layers.46.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
954
+ "model.layers.46.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
955
+ "model.layers.46.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
956
+ "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
957
+ "model.layers.46.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
958
+ "model.layers.46.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
959
+ "model.layers.46.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
960
+ "model.layers.46.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
961
+ "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
962
+ "model.layers.46.self_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
963
+ "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
964
+ "model.layers.46.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
965
+ "model.layers.46.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
966
+ "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
967
+ "model.layers.46.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
968
+ "model.layers.46.self_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
969
+ "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
970
+ "model.layers.46.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
971
+ "model.layers.46.self_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
972
+ "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
973
+ "model.layers.46.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
974
+ "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors",
975
+ "model.layers.47.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
976
+ "model.layers.47.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
977
+ "model.layers.47.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
978
+ "model.layers.47.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
979
+ "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
980
+ "model.layers.47.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
981
+ "model.layers.47.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
982
+ "model.layers.47.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
983
+ "model.layers.47.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
984
+ "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
985
+ "model.layers.47.self_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
986
+ "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
987
+ "model.layers.47.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
988
+ "model.layers.47.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
989
+ "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
990
+ "model.layers.47.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
991
+ "model.layers.47.self_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
992
+ "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
993
+ "model.layers.47.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
994
+ "model.layers.47.self_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
995
+ "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
996
+ "model.layers.47.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
997
+ "model.layers.48.input_layernorm.weight": "model-00003-of-00003.safetensors",
998
+ "model.layers.48.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
999
+ "model.layers.48.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
1000
+ "model.layers.48.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
1001
+ "model.layers.48.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
1002
+ "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
1003
+ "model.layers.48.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
1004
+ "model.layers.48.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
1005
+ "model.layers.48.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
1006
+ "model.layers.48.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
1007
+ "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
1008
+ "model.layers.48.self_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
1009
+ "model.layers.48.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
1010
+ "model.layers.48.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
1011
+ "model.layers.48.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
1012
+ "model.layers.48.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
1013
+ "model.layers.48.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
1014
+ "model.layers.48.self_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
1015
+ "model.layers.48.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
1016
+ "model.layers.48.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
1017
+ "model.layers.48.self_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
1018
+ "model.layers.48.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
1019
+ "model.layers.48.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
1020
+ "model.layers.49.input_layernorm.weight": "model-00003-of-00003.safetensors",
1021
+ "model.layers.49.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
1022
+ "model.layers.49.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
1023
+ "model.layers.49.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
1024
+ "model.layers.49.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
1025
+ "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
1026
+ "model.layers.49.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
1027
+ "model.layers.49.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
1028
+ "model.layers.49.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
1029
+ "model.layers.49.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
1030
+ "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
1031
+ "model.layers.49.self_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
1032
+ "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
1033
+ "model.layers.49.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
1034
+ "model.layers.49.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
1035
+ "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
1036
+ "model.layers.49.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
1037
+ "model.layers.49.self_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
1038
+ "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
1039
+ "model.layers.49.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
1040
+ "model.layers.49.self_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
1041
+ "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
1042
+ "model.layers.49.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
1043
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
1044
+ "model.layers.5.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
1045
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
1046
+ "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
1047
+ "model.layers.5.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
1048
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
1049
+ "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
1050
+ "model.layers.5.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
1051
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
1052
+ "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
1053
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
1054
+ "model.layers.5.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
1055
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
1056
+ "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
1057
+ "model.layers.5.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
1058
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
1059
+ "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
1060
+ "model.layers.5.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
1061
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
1062
+ "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
1063
+ "model.layers.5.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
1064
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
1065
+ "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
1066
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
1067
+ "model.layers.6.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
1068
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
1069
+ "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
1070
+ "model.layers.6.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
1071
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
1072
+ "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
1073
+ "model.layers.6.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
1074
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
1075
+ "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
1076
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
1077
+ "model.layers.6.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
1078
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
1079
+ "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
1080
+ "model.layers.6.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
1081
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
1082
+ "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
1083
+ "model.layers.6.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
1084
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
1085
+ "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
1086
+ "model.layers.6.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
1087
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
1088
+ "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
1089
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
1090
+ "model.layers.7.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
1091
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
1092
+ "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
1093
+ "model.layers.7.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
1094
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
1095
+ "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
1096
+ "model.layers.7.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
1097
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
1098
+ "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
1099
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
1100
+ "model.layers.7.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
1101
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
1102
+ "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
1103
+ "model.layers.7.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
1104
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
1105
+ "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
1106
+ "model.layers.7.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
1107
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
1108
+ "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
1109
+ "model.layers.7.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
1110
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
1111
+ "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
1112
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
1113
+ "model.layers.8.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
1114
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
1115
+ "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
1116
+ "model.layers.8.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
1117
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
1118
+ "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
1119
+ "model.layers.8.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
1120
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
1121
+ "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
1122
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
1123
+ "model.layers.8.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
1124
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
1125
+ "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
1126
+ "model.layers.8.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
1127
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
1128
+ "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
1129
+ "model.layers.8.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
1130
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
1131
+ "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
1132
+ "model.layers.8.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
1133
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
1134
+ "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
1135
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
1136
+ "model.layers.9.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
1137
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
1138
+ "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
1139
+ "model.layers.9.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
1140
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
1141
+ "model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
1142
+ "model.layers.9.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
1143
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
1144
+ "model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
1145
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
1146
+ "model.layers.9.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
1147
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
1148
+ "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
1149
+ "model.layers.9.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
1150
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
1151
+ "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
1152
+ "model.layers.9.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
1153
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
1154
+ "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
1155
+ "model.layers.9.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
1156
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
1157
+ "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
1158
+ "model.norm.weight": "model-00003-of-00003.safetensors"
1159
+ }
1160
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|function_list|>",
6
+ "<|function_output|>",
7
+ "<|function_call|>",
8
+ "<|control_6|>",
9
+ "<|control_7|>",
10
+ "<|control_8|>",
11
+ "<|control_9|>",
12
+ "<|control_10|>",
13
+ "<|control_11|>",
14
+ "<|control_12|>",
15
+ "<|control_13|>",
16
+ "<|control_14|>",
17
+ "<|control_15|>",
18
+ "<|control_16|>",
19
+ "<|control_17|>",
20
+ "<|control_18|>",
21
+ "<|control_19|>",
22
+ "<|control_20|>",
23
+ "<|control_21|>",
24
+ "<|control_22|>",
25
+ "<|control_23|>",
26
+ "<|control_24|>",
27
+ "<|control_25|>",
28
+ "<|control_26|>",
29
+ "<|control_27|>",
30
+ "<|control_28|>",
31
+ "<|control_29|>",
32
+ "<|control_30|>",
33
+ "<|control_31|>",
34
+ "<|control_32|>",
35
+ "<|control_33|>",
36
+ "<|control_34|>",
37
+ "<|control_35|>",
38
+ "<|control_36|>",
39
+ "<|control_37|>",
40
+ "<|control_38|>",
41
+ "<|control_39|>",
42
+ "<|control_40|>",
43
+ "<|control_41|>",
44
+ "<|control_42|>",
45
+ "<|control_43|>",
46
+ "<|control_44|>",
47
+ "<|control_45|>",
48
+ "<|control_46|>",
49
+ "<|control_47|>",
50
+ "<|control_48|>",
51
+ "<|control_49|>",
52
+ "<|control_50|>",
53
+ "<|control_51|>",
54
+ "<|control_52|>",
55
+ "<|control_53|>",
56
+ "<|control_54|>",
57
+ "<|control_55|>",
58
+ "<|control_56|>",
59
+ "<|control_57|>",
60
+ "<|control_58|>",
61
+ "<|control_59|>",
62
+ "<|control_60|>",
63
+ "<|control_61|>",
64
+ "<|control_62|>",
65
+ "<|control_63|>",
66
+ "<|control_64|>",
67
+ "<|control_65|>",
68
+ "<|control_66|>",
69
+ "<|control_67|>",
70
+ "<|control_68|>",
71
+ "<|control_69|>",
72
+ "<|control_70|>",
73
+ "<|control_71|>",
74
+ "<|control_72|>",
75
+ "<|control_73|>",
76
+ "<|control_74|>",
77
+ "<|control_75|>",
78
+ "<|control_76|>",
79
+ "<|control_77|>",
80
+ "<|control_78|>",
81
+ "<|control_79|>",
82
+ "<|control_80|>",
83
+ "<|control_81|>",
84
+ "<|control_82|>",
85
+ "<|control_83|>",
86
+ "<|control_84|>",
87
+ "<|control_85|>",
88
+ "<|control_86|>",
89
+ "<|control_87|>",
90
+ "<|control_88|>",
91
+ "<|control_89|>",
92
+ "<|control_90|>",
93
+ "<|control_91|>",
94
+ "<|control_92|>",
95
+ "<|control_93|>",
96
+ "<|control_94|>",
97
+ "<|control_95|>",
98
+ "<|control_96|>",
99
+ "<|control_97|>",
100
+ "<|control_98|>",
101
+ "<|control_99|>",
102
+ "<|control_100|>",
103
+ "<|control_101|>",
104
+ "<|control_102|>",
105
+ "<|control_103|>",
106
+ "<|control_104|>",
107
+ "<|control_105|>",
108
+ "<|control_106|>",
109
+ "<|control_107|>",
110
+ "<|control_108|>",
111
+ "<|control_109|>",
112
+ "<|control_110|>",
113
+ "<|control_111|>",
114
+ "<|control_112|>",
115
+ "<|control_113|>",
116
+ "<|control_114|>",
117
+ "<|control_115|>",
118
+ "<|control_116|>",
119
+ "<|control_117|>",
120
+ "<|control_118|>",
121
+ "<|control_119|>",
122
+ "<|control_120|>",
123
+ "<|control_121|>",
124
+ "<|control_122|>",
125
+ "<|control_123|>",
126
+ "<|control_124|>",
127
+ "<|control_125|>",
128
+ "<|control_126|>",
129
+ "<|control_127|>",
130
+ "<|control_128|>"
131
+ ],
132
+ "bos_token": {
133
+ "content": "<s>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false
138
+ },
139
+ "eos_token": {
140
+ "content": "</s>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false
145
+ },
146
+ "pad_token": {
147
+ "content": "</s>",
148
+ "lstrip": false,
149
+ "normalized": false,
150
+ "rstrip": false,
151
+ "single_word": false
152
+ },
153
+ "unk_token": {
154
+ "content": "<unk>",
155
+ "lstrip": false,
156
+ "normalized": false,
157
+ "rstrip": false,
158
+ "single_word": false
159
+ }
160
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,1197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|im_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|im_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|function_list|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|function_output|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|function_call|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|control_6|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|control_7|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|control_8|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|control_9|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|control_10|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|control_11|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "<|control_12|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "<|control_13|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "32013": {
135
+ "content": "<|control_14|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "32014": {
143
+ "content": "<|control_15|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "32015": {
151
+ "content": "<|control_16|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "32016": {
159
+ "content": "<|control_17|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "32017": {
167
+ "content": "<|control_18|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "32018": {
175
+ "content": "<|control_19|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "32019": {
183
+ "content": "<|control_20|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "32020": {
191
+ "content": "<|control_21|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "32021": {
199
+ "content": "<|control_22|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "32022": {
207
+ "content": "<|control_23|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "32023": {
215
+ "content": "<|control_24|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "32024": {
223
+ "content": "<|control_25|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "32025": {
231
+ "content": "<|control_26|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "32026": {
239
+ "content": "<|control_27|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "32027": {
247
+ "content": "<|control_28|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "32028": {
255
+ "content": "<|control_29|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "32029": {
263
+ "content": "<|control_30|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "32030": {
271
+ "content": "<|control_31|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "32031": {
279
+ "content": "<|control_32|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "32032": {
287
+ "content": "<|control_33|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "32033": {
295
+ "content": "<|control_34|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "32034": {
303
+ "content": "<|control_35|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "32035": {
311
+ "content": "<|control_36|>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "32036": {
319
+ "content": "<|control_37|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "32037": {
327
+ "content": "<|control_38|>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": true
333
+ },
334
+ "32038": {
335
+ "content": "<|control_39|>",
336
+ "lstrip": false,
337
+ "normalized": false,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": true
341
+ },
342
+ "32039": {
343
+ "content": "<|control_40|>",
344
+ "lstrip": false,
345
+ "normalized": false,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": true
349
+ },
350
+ "32040": {
351
+ "content": "<|control_41|>",
352
+ "lstrip": false,
353
+ "normalized": false,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": true
357
+ },
358
+ "32041": {
359
+ "content": "<|control_42|>",
360
+ "lstrip": false,
361
+ "normalized": false,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": true
365
+ },
366
+ "32042": {
367
+ "content": "<|control_43|>",
368
+ "lstrip": false,
369
+ "normalized": false,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": true
373
+ },
374
+ "32043": {
375
+ "content": "<|control_44|>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": true
381
+ },
382
+ "32044": {
383
+ "content": "<|control_45|>",
384
+ "lstrip": false,
385
+ "normalized": false,
386
+ "rstrip": false,
387
+ "single_word": false,
388
+ "special": true
389
+ },
390
+ "32045": {
391
+ "content": "<|control_46|>",
392
+ "lstrip": false,
393
+ "normalized": false,
394
+ "rstrip": false,
395
+ "single_word": false,
396
+ "special": true
397
+ },
398
+ "32046": {
399
+ "content": "<|control_47|>",
400
+ "lstrip": false,
401
+ "normalized": false,
402
+ "rstrip": false,
403
+ "single_word": false,
404
+ "special": true
405
+ },
406
+ "32047": {
407
+ "content": "<|control_48|>",
408
+ "lstrip": false,
409
+ "normalized": false,
410
+ "rstrip": false,
411
+ "single_word": false,
412
+ "special": true
413
+ },
414
+ "32048": {
415
+ "content": "<|control_49|>",
416
+ "lstrip": false,
417
+ "normalized": false,
418
+ "rstrip": false,
419
+ "single_word": false,
420
+ "special": true
421
+ },
422
+ "32049": {
423
+ "content": "<|control_50|>",
424
+ "lstrip": false,
425
+ "normalized": false,
426
+ "rstrip": false,
427
+ "single_word": false,
428
+ "special": true
429
+ },
430
+ "32050": {
431
+ "content": "<|control_51|>",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false,
436
+ "special": true
437
+ },
438
+ "32051": {
439
+ "content": "<|control_52|>",
440
+ "lstrip": false,
441
+ "normalized": false,
442
+ "rstrip": false,
443
+ "single_word": false,
444
+ "special": true
445
+ },
446
+ "32052": {
447
+ "content": "<|control_53|>",
448
+ "lstrip": false,
449
+ "normalized": false,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": true
453
+ },
454
+ "32053": {
455
+ "content": "<|control_54|>",
456
+ "lstrip": false,
457
+ "normalized": false,
458
+ "rstrip": false,
459
+ "single_word": false,
460
+ "special": true
461
+ },
462
+ "32054": {
463
+ "content": "<|control_55|>",
464
+ "lstrip": false,
465
+ "normalized": false,
466
+ "rstrip": false,
467
+ "single_word": false,
468
+ "special": true
469
+ },
470
+ "32055": {
471
+ "content": "<|control_56|>",
472
+ "lstrip": false,
473
+ "normalized": false,
474
+ "rstrip": false,
475
+ "single_word": false,
476
+ "special": true
477
+ },
478
+ "32056": {
479
+ "content": "<|control_57|>",
480
+ "lstrip": false,
481
+ "normalized": false,
482
+ "rstrip": false,
483
+ "single_word": false,
484
+ "special": true
485
+ },
486
+ "32057": {
487
+ "content": "<|control_58|>",
488
+ "lstrip": false,
489
+ "normalized": false,
490
+ "rstrip": false,
491
+ "single_word": false,
492
+ "special": true
493
+ },
494
+ "32058": {
495
+ "content": "<|control_59|>",
496
+ "lstrip": false,
497
+ "normalized": false,
498
+ "rstrip": false,
499
+ "single_word": false,
500
+ "special": true
501
+ },
502
+ "32059": {
503
+ "content": "<|control_60|>",
504
+ "lstrip": false,
505
+ "normalized": false,
506
+ "rstrip": false,
507
+ "single_word": false,
508
+ "special": true
509
+ },
510
+ "32060": {
511
+ "content": "<|control_61|>",
512
+ "lstrip": false,
513
+ "normalized": false,
514
+ "rstrip": false,
515
+ "single_word": false,
516
+ "special": true
517
+ },
518
+ "32061": {
519
+ "content": "<|control_62|>",
520
+ "lstrip": false,
521
+ "normalized": false,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": true
525
+ },
526
+ "32062": {
527
+ "content": "<|control_63|>",
528
+ "lstrip": false,
529
+ "normalized": false,
530
+ "rstrip": false,
531
+ "single_word": false,
532
+ "special": true
533
+ },
534
+ "32063": {
535
+ "content": "<|control_64|>",
536
+ "lstrip": false,
537
+ "normalized": false,
538
+ "rstrip": false,
539
+ "single_word": false,
540
+ "special": true
541
+ },
542
+ "32064": {
543
+ "content": "<|control_65|>",
544
+ "lstrip": false,
545
+ "normalized": false,
546
+ "rstrip": false,
547
+ "single_word": false,
548
+ "special": true
549
+ },
550
+ "32065": {
551
+ "content": "<|control_66|>",
552
+ "lstrip": false,
553
+ "normalized": false,
554
+ "rstrip": false,
555
+ "single_word": false,
556
+ "special": true
557
+ },
558
+ "32066": {
559
+ "content": "<|control_67|>",
560
+ "lstrip": false,
561
+ "normalized": false,
562
+ "rstrip": false,
563
+ "single_word": false,
564
+ "special": true
565
+ },
566
+ "32067": {
567
+ "content": "<|control_68|>",
568
+ "lstrip": false,
569
+ "normalized": false,
570
+ "rstrip": false,
571
+ "single_word": false,
572
+ "special": true
573
+ },
574
+ "32068": {
575
+ "content": "<|control_69|>",
576
+ "lstrip": false,
577
+ "normalized": false,
578
+ "rstrip": false,
579
+ "single_word": false,
580
+ "special": true
581
+ },
582
+ "32069": {
583
+ "content": "<|control_70|>",
584
+ "lstrip": false,
585
+ "normalized": false,
586
+ "rstrip": false,
587
+ "single_word": false,
588
+ "special": true
589
+ },
590
+ "32070": {
591
+ "content": "<|control_71|>",
592
+ "lstrip": false,
593
+ "normalized": false,
594
+ "rstrip": false,
595
+ "single_word": false,
596
+ "special": true
597
+ },
598
+ "32071": {
599
+ "content": "<|control_72|>",
600
+ "lstrip": false,
601
+ "normalized": false,
602
+ "rstrip": false,
603
+ "single_word": false,
604
+ "special": true
605
+ },
606
+ "32072": {
607
+ "content": "<|control_73|>",
608
+ "lstrip": false,
609
+ "normalized": false,
610
+ "rstrip": false,
611
+ "single_word": false,
612
+ "special": true
613
+ },
614
+ "32073": {
615
+ "content": "<|control_74|>",
616
+ "lstrip": false,
617
+ "normalized": false,
618
+ "rstrip": false,
619
+ "single_word": false,
620
+ "special": true
621
+ },
622
+ "32074": {
623
+ "content": "<|control_75|>",
624
+ "lstrip": false,
625
+ "normalized": false,
626
+ "rstrip": false,
627
+ "single_word": false,
628
+ "special": true
629
+ },
630
+ "32075": {
631
+ "content": "<|control_76|>",
632
+ "lstrip": false,
633
+ "normalized": false,
634
+ "rstrip": false,
635
+ "single_word": false,
636
+ "special": true
637
+ },
638
+ "32076": {
639
+ "content": "<|control_77|>",
640
+ "lstrip": false,
641
+ "normalized": false,
642
+ "rstrip": false,
643
+ "single_word": false,
644
+ "special": true
645
+ },
646
+ "32077": {
647
+ "content": "<|control_78|>",
648
+ "lstrip": false,
649
+ "normalized": false,
650
+ "rstrip": false,
651
+ "single_word": false,
652
+ "special": true
653
+ },
654
+ "32078": {
655
+ "content": "<|control_79|>",
656
+ "lstrip": false,
657
+ "normalized": false,
658
+ "rstrip": false,
659
+ "single_word": false,
660
+ "special": true
661
+ },
662
+ "32079": {
663
+ "content": "<|control_80|>",
664
+ "lstrip": false,
665
+ "normalized": false,
666
+ "rstrip": false,
667
+ "single_word": false,
668
+ "special": true
669
+ },
670
+ "32080": {
671
+ "content": "<|control_81|>",
672
+ "lstrip": false,
673
+ "normalized": false,
674
+ "rstrip": false,
675
+ "single_word": false,
676
+ "special": true
677
+ },
678
+ "32081": {
679
+ "content": "<|control_82|>",
680
+ "lstrip": false,
681
+ "normalized": false,
682
+ "rstrip": false,
683
+ "single_word": false,
684
+ "special": true
685
+ },
686
+ "32082": {
687
+ "content": "<|control_83|>",
688
+ "lstrip": false,
689
+ "normalized": false,
690
+ "rstrip": false,
691
+ "single_word": false,
692
+ "special": true
693
+ },
694
+ "32083": {
695
+ "content": "<|control_84|>",
696
+ "lstrip": false,
697
+ "normalized": false,
698
+ "rstrip": false,
699
+ "single_word": false,
700
+ "special": true
701
+ },
702
+ "32084": {
703
+ "content": "<|control_85|>",
704
+ "lstrip": false,
705
+ "normalized": false,
706
+ "rstrip": false,
707
+ "single_word": false,
708
+ "special": true
709
+ },
710
+ "32085": {
711
+ "content": "<|control_86|>",
712
+ "lstrip": false,
713
+ "normalized": false,
714
+ "rstrip": false,
715
+ "single_word": false,
716
+ "special": true
717
+ },
718
+ "32086": {
719
+ "content": "<|control_87|>",
720
+ "lstrip": false,
721
+ "normalized": false,
722
+ "rstrip": false,
723
+ "single_word": false,
724
+ "special": true
725
+ },
726
+ "32087": {
727
+ "content": "<|control_88|>",
728
+ "lstrip": false,
729
+ "normalized": false,
730
+ "rstrip": false,
731
+ "single_word": false,
732
+ "special": true
733
+ },
734
+ "32088": {
735
+ "content": "<|control_89|>",
736
+ "lstrip": false,
737
+ "normalized": false,
738
+ "rstrip": false,
739
+ "single_word": false,
740
+ "special": true
741
+ },
742
+ "32089": {
743
+ "content": "<|control_90|>",
744
+ "lstrip": false,
745
+ "normalized": false,
746
+ "rstrip": false,
747
+ "single_word": false,
748
+ "special": true
749
+ },
750
+ "32090": {
751
+ "content": "<|control_91|>",
752
+ "lstrip": false,
753
+ "normalized": false,
754
+ "rstrip": false,
755
+ "single_word": false,
756
+ "special": true
757
+ },
758
+ "32091": {
759
+ "content": "<|control_92|>",
760
+ "lstrip": false,
761
+ "normalized": false,
762
+ "rstrip": false,
763
+ "single_word": false,
764
+ "special": true
765
+ },
766
+ "32092": {
767
+ "content": "<|control_93|>",
768
+ "lstrip": false,
769
+ "normalized": false,
770
+ "rstrip": false,
771
+ "single_word": false,
772
+ "special": true
773
+ },
774
+ "32093": {
775
+ "content": "<|control_94|>",
776
+ "lstrip": false,
777
+ "normalized": false,
778
+ "rstrip": false,
779
+ "single_word": false,
780
+ "special": true
781
+ },
782
+ "32094": {
783
+ "content": "<|control_95|>",
784
+ "lstrip": false,
785
+ "normalized": false,
786
+ "rstrip": false,
787
+ "single_word": false,
788
+ "special": true
789
+ },
790
+ "32095": {
791
+ "content": "<|control_96|>",
792
+ "lstrip": false,
793
+ "normalized": false,
794
+ "rstrip": false,
795
+ "single_word": false,
796
+ "special": true
797
+ },
798
+ "32096": {
799
+ "content": "<|control_97|>",
800
+ "lstrip": false,
801
+ "normalized": false,
802
+ "rstrip": false,
803
+ "single_word": false,
804
+ "special": true
805
+ },
806
+ "32097": {
807
+ "content": "<|control_98|>",
808
+ "lstrip": false,
809
+ "normalized": false,
810
+ "rstrip": false,
811
+ "single_word": false,
812
+ "special": true
813
+ },
814
+ "32098": {
815
+ "content": "<|control_99|>",
816
+ "lstrip": false,
817
+ "normalized": false,
818
+ "rstrip": false,
819
+ "single_word": false,
820
+ "special": true
821
+ },
822
+ "32099": {
823
+ "content": "<|control_100|>",
824
+ "lstrip": false,
825
+ "normalized": false,
826
+ "rstrip": false,
827
+ "single_word": false,
828
+ "special": true
829
+ },
830
+ "32100": {
831
+ "content": "<|control_101|>",
832
+ "lstrip": false,
833
+ "normalized": false,
834
+ "rstrip": false,
835
+ "single_word": false,
836
+ "special": true
837
+ },
838
+ "32101": {
839
+ "content": "<|control_102|>",
840
+ "lstrip": false,
841
+ "normalized": false,
842
+ "rstrip": false,
843
+ "single_word": false,
844
+ "special": true
845
+ },
846
+ "32102": {
847
+ "content": "<|control_103|>",
848
+ "lstrip": false,
849
+ "normalized": false,
850
+ "rstrip": false,
851
+ "single_word": false,
852
+ "special": true
853
+ },
854
+ "32103": {
855
+ "content": "<|control_104|>",
856
+ "lstrip": false,
857
+ "normalized": false,
858
+ "rstrip": false,
859
+ "single_word": false,
860
+ "special": true
861
+ },
862
+ "32104": {
863
+ "content": "<|control_105|>",
864
+ "lstrip": false,
865
+ "normalized": false,
866
+ "rstrip": false,
867
+ "single_word": false,
868
+ "special": true
869
+ },
870
+ "32105": {
871
+ "content": "<|control_106|>",
872
+ "lstrip": false,
873
+ "normalized": false,
874
+ "rstrip": false,
875
+ "single_word": false,
876
+ "special": true
877
+ },
878
+ "32106": {
879
+ "content": "<|control_107|>",
880
+ "lstrip": false,
881
+ "normalized": false,
882
+ "rstrip": false,
883
+ "single_word": false,
884
+ "special": true
885
+ },
886
+ "32107": {
887
+ "content": "<|control_108|>",
888
+ "lstrip": false,
889
+ "normalized": false,
890
+ "rstrip": false,
891
+ "single_word": false,
892
+ "special": true
893
+ },
894
+ "32108": {
895
+ "content": "<|control_109|>",
896
+ "lstrip": false,
897
+ "normalized": false,
898
+ "rstrip": false,
899
+ "single_word": false,
900
+ "special": true
901
+ },
902
+ "32109": {
903
+ "content": "<|control_110|>",
904
+ "lstrip": false,
905
+ "normalized": false,
906
+ "rstrip": false,
907
+ "single_word": false,
908
+ "special": true
909
+ },
910
+ "32110": {
911
+ "content": "<|control_111|>",
912
+ "lstrip": false,
913
+ "normalized": false,
914
+ "rstrip": false,
915
+ "single_word": false,
916
+ "special": true
917
+ },
918
+ "32111": {
919
+ "content": "<|control_112|>",
920
+ "lstrip": false,
921
+ "normalized": false,
922
+ "rstrip": false,
923
+ "single_word": false,
924
+ "special": true
925
+ },
926
+ "32112": {
927
+ "content": "<|control_113|>",
928
+ "lstrip": false,
929
+ "normalized": false,
930
+ "rstrip": false,
931
+ "single_word": false,
932
+ "special": true
933
+ },
934
+ "32113": {
935
+ "content": "<|control_114|>",
936
+ "lstrip": false,
937
+ "normalized": false,
938
+ "rstrip": false,
939
+ "single_word": false,
940
+ "special": true
941
+ },
942
+ "32114": {
943
+ "content": "<|control_115|>",
944
+ "lstrip": false,
945
+ "normalized": false,
946
+ "rstrip": false,
947
+ "single_word": false,
948
+ "special": true
949
+ },
950
+ "32115": {
951
+ "content": "<|control_116|>",
952
+ "lstrip": false,
953
+ "normalized": false,
954
+ "rstrip": false,
955
+ "single_word": false,
956
+ "special": true
957
+ },
958
+ "32116": {
959
+ "content": "<|control_117|>",
960
+ "lstrip": false,
961
+ "normalized": false,
962
+ "rstrip": false,
963
+ "single_word": false,
964
+ "special": true
965
+ },
966
+ "32117": {
967
+ "content": "<|control_118|>",
968
+ "lstrip": false,
969
+ "normalized": false,
970
+ "rstrip": false,
971
+ "single_word": false,
972
+ "special": true
973
+ },
974
+ "32118": {
975
+ "content": "<|control_119|>",
976
+ "lstrip": false,
977
+ "normalized": false,
978
+ "rstrip": false,
979
+ "single_word": false,
980
+ "special": true
981
+ },
982
+ "32119": {
983
+ "content": "<|control_120|>",
984
+ "lstrip": false,
985
+ "normalized": false,
986
+ "rstrip": false,
987
+ "single_word": false,
988
+ "special": true
989
+ },
990
+ "32120": {
991
+ "content": "<|control_121|>",
992
+ "lstrip": false,
993
+ "normalized": false,
994
+ "rstrip": false,
995
+ "single_word": false,
996
+ "special": true
997
+ },
998
+ "32121": {
999
+ "content": "<|control_122|>",
1000
+ "lstrip": false,
1001
+ "normalized": false,
1002
+ "rstrip": false,
1003
+ "single_word": false,
1004
+ "special": true
1005
+ },
1006
+ "32122": {
1007
+ "content": "<|control_123|>",
1008
+ "lstrip": false,
1009
+ "normalized": false,
1010
+ "rstrip": false,
1011
+ "single_word": false,
1012
+ "special": true
1013
+ },
1014
+ "32123": {
1015
+ "content": "<|control_124|>",
1016
+ "lstrip": false,
1017
+ "normalized": false,
1018
+ "rstrip": false,
1019
+ "single_word": false,
1020
+ "special": true
1021
+ },
1022
+ "32124": {
1023
+ "content": "<|control_125|>",
1024
+ "lstrip": false,
1025
+ "normalized": false,
1026
+ "rstrip": false,
1027
+ "single_word": false,
1028
+ "special": true
1029
+ },
1030
+ "32125": {
1031
+ "content": "<|control_126|>",
1032
+ "lstrip": false,
1033
+ "normalized": false,
1034
+ "rstrip": false,
1035
+ "single_word": false,
1036
+ "special": true
1037
+ },
1038
+ "32126": {
1039
+ "content": "<|control_127|>",
1040
+ "lstrip": false,
1041
+ "normalized": false,
1042
+ "rstrip": false,
1043
+ "single_word": false,
1044
+ "special": true
1045
+ },
1046
+ "32127": {
1047
+ "content": "<|control_128|>",
1048
+ "lstrip": false,
1049
+ "normalized": false,
1050
+ "rstrip": false,
1051
+ "single_word": false,
1052
+ "special": true
1053
+ }
1054
+ },
1055
+ "additional_special_tokens": [
1056
+ "<|im_start|>",
1057
+ "<|im_end|>",
1058
+ "<|function_list|>",
1059
+ "<|function_output|>",
1060
+ "<|function_call|>",
1061
+ "<|control_6|>",
1062
+ "<|control_7|>",
1063
+ "<|control_8|>",
1064
+ "<|control_9|>",
1065
+ "<|control_10|>",
1066
+ "<|control_11|>",
1067
+ "<|control_12|>",
1068
+ "<|control_13|>",
1069
+ "<|control_14|>",
1070
+ "<|control_15|>",
1071
+ "<|control_16|>",
1072
+ "<|control_17|>",
1073
+ "<|control_18|>",
1074
+ "<|control_19|>",
1075
+ "<|control_20|>",
1076
+ "<|control_21|>",
1077
+ "<|control_22|>",
1078
+ "<|control_23|>",
1079
+ "<|control_24|>",
1080
+ "<|control_25|>",
1081
+ "<|control_26|>",
1082
+ "<|control_27|>",
1083
+ "<|control_28|>",
1084
+ "<|control_29|>",
1085
+ "<|control_30|>",
1086
+ "<|control_31|>",
1087
+ "<|control_32|>",
1088
+ "<|control_33|>",
1089
+ "<|control_34|>",
1090
+ "<|control_35|>",
1091
+ "<|control_36|>",
1092
+ "<|control_37|>",
1093
+ "<|control_38|>",
1094
+ "<|control_39|>",
1095
+ "<|control_40|>",
1096
+ "<|control_41|>",
1097
+ "<|control_42|>",
1098
+ "<|control_43|>",
1099
+ "<|control_44|>",
1100
+ "<|control_45|>",
1101
+ "<|control_46|>",
1102
+ "<|control_47|>",
1103
+ "<|control_48|>",
1104
+ "<|control_49|>",
1105
+ "<|control_50|>",
1106
+ "<|control_51|>",
1107
+ "<|control_52|>",
1108
+ "<|control_53|>",
1109
+ "<|control_54|>",
1110
+ "<|control_55|>",
1111
+ "<|control_56|>",
1112
+ "<|control_57|>",
1113
+ "<|control_58|>",
1114
+ "<|control_59|>",
1115
+ "<|control_60|>",
1116
+ "<|control_61|>",
1117
+ "<|control_62|>",
1118
+ "<|control_63|>",
1119
+ "<|control_64|>",
1120
+ "<|control_65|>",
1121
+ "<|control_66|>",
1122
+ "<|control_67|>",
1123
+ "<|control_68|>",
1124
+ "<|control_69|>",
1125
+ "<|control_70|>",
1126
+ "<|control_71|>",
1127
+ "<|control_72|>",
1128
+ "<|control_73|>",
1129
+ "<|control_74|>",
1130
+ "<|control_75|>",
1131
+ "<|control_76|>",
1132
+ "<|control_77|>",
1133
+ "<|control_78|>",
1134
+ "<|control_79|>",
1135
+ "<|control_80|>",
1136
+ "<|control_81|>",
1137
+ "<|control_82|>",
1138
+ "<|control_83|>",
1139
+ "<|control_84|>",
1140
+ "<|control_85|>",
1141
+ "<|control_86|>",
1142
+ "<|control_87|>",
1143
+ "<|control_88|>",
1144
+ "<|control_89|>",
1145
+ "<|control_90|>",
1146
+ "<|control_91|>",
1147
+ "<|control_92|>",
1148
+ "<|control_93|>",
1149
+ "<|control_94|>",
1150
+ "<|control_95|>",
1151
+ "<|control_96|>",
1152
+ "<|control_97|>",
1153
+ "<|control_98|>",
1154
+ "<|control_99|>",
1155
+ "<|control_100|>",
1156
+ "<|control_101|>",
1157
+ "<|control_102|>",
1158
+ "<|control_103|>",
1159
+ "<|control_104|>",
1160
+ "<|control_105|>",
1161
+ "<|control_106|>",
1162
+ "<|control_107|>",
1163
+ "<|control_108|>",
1164
+ "<|control_109|>",
1165
+ "<|control_110|>",
1166
+ "<|control_111|>",
1167
+ "<|control_112|>",
1168
+ "<|control_113|>",
1169
+ "<|control_114|>",
1170
+ "<|control_115|>",
1171
+ "<|control_116|>",
1172
+ "<|control_117|>",
1173
+ "<|control_118|>",
1174
+ "<|control_119|>",
1175
+ "<|control_120|>",
1176
+ "<|control_121|>",
1177
+ "<|control_122|>",
1178
+ "<|control_123|>",
1179
+ "<|control_124|>",
1180
+ "<|control_125|>",
1181
+ "<|control_126|>",
1182
+ "<|control_127|>",
1183
+ "<|control_128|>"
1184
+ ],
1185
+ "bos_token": "<s>",
1186
+ "chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
1187
+ "clean_up_tokenization_spaces": true,
1188
+ "eos_token": "</s>",
1189
+ "legacy": true,
1190
+ "model_max_length": 1000000000000000019884624838656,
1191
+ "pad_token": "</s>",
1192
+ "sp_model_kwargs": {},
1193
+ "spaces_between_special_tokens": false,
1194
+ "tokenizer_class": "LlamaTokenizer",
1195
+ "unk_token": "<unk>",
1196
+ "use_default_system_prompt": false
1197
+ }