v2
Browse files- config.json +218 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
config.json
ADDED
@@ -0,0 +1,218 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "checkpoints/mtgv/MobileLLaMA-1.4B-Chat",
|
3 |
+
"anyprec": {
|
4 |
+
"arch_config": {
|
5 |
+
"layers_name": "layers",
|
6 |
+
"model_name": "model",
|
7 |
+
"module_names": [
|
8 |
+
"self_attn.q_proj",
|
9 |
+
"self_attn.k_proj",
|
10 |
+
"self_attn.v_proj",
|
11 |
+
"self_attn.o_proj",
|
12 |
+
"mlp.gate_proj",
|
13 |
+
"mlp.up_proj",
|
14 |
+
"mlp.down_proj"
|
15 |
+
]
|
16 |
+
},
|
17 |
+
"group_count": 1,
|
18 |
+
"parent_precision": 4,
|
19 |
+
"seed_precision": 2,
|
20 |
+
"sparse_numvals": {
|
21 |
+
"model.layers.0.mlp.down_proj": 400523,
|
22 |
+
"model.layers.0.mlp.gate_proj": 396264,
|
23 |
+
"model.layers.0.mlp.up_proj": 385037,
|
24 |
+
"model.layers.0.self_attn.k_proj": 275407,
|
25 |
+
"model.layers.0.self_attn.o_proj": 150081,
|
26 |
+
"model.layers.0.self_attn.q_proj": 255588,
|
27 |
+
"model.layers.0.self_attn.v_proj": 160697,
|
28 |
+
"model.layers.1.mlp.down_proj": 386409,
|
29 |
+
"model.layers.1.mlp.gate_proj": 393215,
|
30 |
+
"model.layers.1.mlp.up_proj": 385587,
|
31 |
+
"model.layers.1.self_attn.k_proj": 475524,
|
32 |
+
"model.layers.1.self_attn.o_proj": 221750,
|
33 |
+
"model.layers.1.self_attn.q_proj": 476847,
|
34 |
+
"model.layers.1.self_attn.v_proj": 176783,
|
35 |
+
"model.layers.10.mlp.down_proj": 387140,
|
36 |
+
"model.layers.10.mlp.gate_proj": 425728,
|
37 |
+
"model.layers.10.mlp.up_proj": 401174,
|
38 |
+
"model.layers.10.self_attn.k_proj": 299367,
|
39 |
+
"model.layers.10.self_attn.o_proj": 165346,
|
40 |
+
"model.layers.10.self_attn.q_proj": 279251,
|
41 |
+
"model.layers.10.self_attn.v_proj": 171614,
|
42 |
+
"model.layers.11.mlp.down_proj": 387474,
|
43 |
+
"model.layers.11.mlp.gate_proj": 424181,
|
44 |
+
"model.layers.11.mlp.up_proj": 401896,
|
45 |
+
"model.layers.11.self_attn.k_proj": 285408,
|
46 |
+
"model.layers.11.self_attn.o_proj": 155248,
|
47 |
+
"model.layers.11.self_attn.q_proj": 278893,
|
48 |
+
"model.layers.11.self_attn.v_proj": 166240,
|
49 |
+
"model.layers.12.mlp.down_proj": 396426,
|
50 |
+
"model.layers.12.mlp.gate_proj": 443150,
|
51 |
+
"model.layers.12.mlp.up_proj": 414688,
|
52 |
+
"model.layers.12.self_attn.k_proj": 270116,
|
53 |
+
"model.layers.12.self_attn.o_proj": 148084,
|
54 |
+
"model.layers.12.self_attn.q_proj": 257984,
|
55 |
+
"model.layers.12.self_attn.v_proj": 166043,
|
56 |
+
"model.layers.13.mlp.down_proj": 409209,
|
57 |
+
"model.layers.13.mlp.gate_proj": 468928,
|
58 |
+
"model.layers.13.mlp.up_proj": 410030,
|
59 |
+
"model.layers.13.self_attn.k_proj": 277122,
|
60 |
+
"model.layers.13.self_attn.o_proj": 158213,
|
61 |
+
"model.layers.13.self_attn.q_proj": 264605,
|
62 |
+
"model.layers.13.self_attn.v_proj": 183753,
|
63 |
+
"model.layers.14.mlp.down_proj": 410006,
|
64 |
+
"model.layers.14.mlp.gate_proj": 481442,
|
65 |
+
"model.layers.14.mlp.up_proj": 427451,
|
66 |
+
"model.layers.14.self_attn.k_proj": 278867,
|
67 |
+
"model.layers.14.self_attn.o_proj": 155983,
|
68 |
+
"model.layers.14.self_attn.q_proj": 268760,
|
69 |
+
"model.layers.14.self_attn.v_proj": 176188,
|
70 |
+
"model.layers.15.mlp.down_proj": 411189,
|
71 |
+
"model.layers.15.mlp.gate_proj": 471248,
|
72 |
+
"model.layers.15.mlp.up_proj": 421665,
|
73 |
+
"model.layers.15.self_attn.k_proj": 281331,
|
74 |
+
"model.layers.15.self_attn.o_proj": 162574,
|
75 |
+
"model.layers.15.self_attn.q_proj": 284610,
|
76 |
+
"model.layers.15.self_attn.v_proj": 180714,
|
77 |
+
"model.layers.16.mlp.down_proj": 418971,
|
78 |
+
"model.layers.16.mlp.gate_proj": 464595,
|
79 |
+
"model.layers.16.mlp.up_proj": 423591,
|
80 |
+
"model.layers.16.self_attn.k_proj": 261045,
|
81 |
+
"model.layers.16.self_attn.o_proj": 160088,
|
82 |
+
"model.layers.16.self_attn.q_proj": 250977,
|
83 |
+
"model.layers.16.self_attn.v_proj": 177848,
|
84 |
+
"model.layers.17.mlp.down_proj": 409538,
|
85 |
+
"model.layers.17.mlp.gate_proj": 450034,
|
86 |
+
"model.layers.17.mlp.up_proj": 415172,
|
87 |
+
"model.layers.17.self_attn.k_proj": 276751,
|
88 |
+
"model.layers.17.self_attn.o_proj": 161674,
|
89 |
+
"model.layers.17.self_attn.q_proj": 266644,
|
90 |
+
"model.layers.17.self_attn.v_proj": 173601,
|
91 |
+
"model.layers.18.mlp.down_proj": 399252,
|
92 |
+
"model.layers.18.mlp.gate_proj": 427813,
|
93 |
+
"model.layers.18.mlp.up_proj": 422532,
|
94 |
+
"model.layers.18.self_attn.k_proj": 255264,
|
95 |
+
"model.layers.18.self_attn.o_proj": 162202,
|
96 |
+
"model.layers.18.self_attn.q_proj": 270035,
|
97 |
+
"model.layers.18.self_attn.v_proj": 173328,
|
98 |
+
"model.layers.19.mlp.down_proj": 393065,
|
99 |
+
"model.layers.19.mlp.gate_proj": 415779,
|
100 |
+
"model.layers.19.mlp.up_proj": 419838,
|
101 |
+
"model.layers.19.self_attn.k_proj": 254719,
|
102 |
+
"model.layers.19.self_attn.o_proj": 185780,
|
103 |
+
"model.layers.19.self_attn.q_proj": 250004,
|
104 |
+
"model.layers.19.self_attn.v_proj": 185533,
|
105 |
+
"model.layers.2.mlp.down_proj": 378193,
|
106 |
+
"model.layers.2.mlp.gate_proj": 376952,
|
107 |
+
"model.layers.2.mlp.up_proj": 381512,
|
108 |
+
"model.layers.2.self_attn.k_proj": 368064,
|
109 |
+
"model.layers.2.self_attn.o_proj": 167961,
|
110 |
+
"model.layers.2.self_attn.q_proj": 314862,
|
111 |
+
"model.layers.2.self_attn.v_proj": 158764,
|
112 |
+
"model.layers.20.mlp.down_proj": 400546,
|
113 |
+
"model.layers.20.mlp.gate_proj": 415086,
|
114 |
+
"model.layers.20.mlp.up_proj": 406972,
|
115 |
+
"model.layers.20.self_attn.k_proj": 233681,
|
116 |
+
"model.layers.20.self_attn.o_proj": 170441,
|
117 |
+
"model.layers.20.self_attn.q_proj": 229955,
|
118 |
+
"model.layers.20.self_attn.v_proj": 169777,
|
119 |
+
"model.layers.21.mlp.down_proj": 389671,
|
120 |
+
"model.layers.21.mlp.gate_proj": 405414,
|
121 |
+
"model.layers.21.mlp.up_proj": 397729,
|
122 |
+
"model.layers.21.self_attn.k_proj": 230648,
|
123 |
+
"model.layers.21.self_attn.o_proj": 204977,
|
124 |
+
"model.layers.21.self_attn.q_proj": 230574,
|
125 |
+
"model.layers.21.self_attn.v_proj": 199698,
|
126 |
+
"model.layers.22.mlp.down_proj": 414621,
|
127 |
+
"model.layers.22.mlp.gate_proj": 415759,
|
128 |
+
"model.layers.22.mlp.up_proj": 408002,
|
129 |
+
"model.layers.22.self_attn.k_proj": 251619,
|
130 |
+
"model.layers.22.self_attn.o_proj": 185353,
|
131 |
+
"model.layers.22.self_attn.q_proj": 246379,
|
132 |
+
"model.layers.22.self_attn.v_proj": 186204,
|
133 |
+
"model.layers.23.mlp.down_proj": 508914,
|
134 |
+
"model.layers.23.mlp.gate_proj": 468804,
|
135 |
+
"model.layers.23.mlp.up_proj": 480458,
|
136 |
+
"model.layers.23.self_attn.k_proj": 205880,
|
137 |
+
"model.layers.23.self_attn.o_proj": 208179,
|
138 |
+
"model.layers.23.self_attn.q_proj": 199025,
|
139 |
+
"model.layers.23.self_attn.v_proj": 194158,
|
140 |
+
"model.layers.3.mlp.down_proj": 378183,
|
141 |
+
"model.layers.3.mlp.gate_proj": 377659,
|
142 |
+
"model.layers.3.mlp.up_proj": 375109,
|
143 |
+
"model.layers.3.self_attn.k_proj": 294567,
|
144 |
+
"model.layers.3.self_attn.o_proj": 144791,
|
145 |
+
"model.layers.3.self_attn.q_proj": 248337,
|
146 |
+
"model.layers.3.self_attn.v_proj": 149933,
|
147 |
+
"model.layers.4.mlp.down_proj": 381223,
|
148 |
+
"model.layers.4.mlp.gate_proj": 380416,
|
149 |
+
"model.layers.4.mlp.up_proj": 387728,
|
150 |
+
"model.layers.4.self_attn.k_proj": 292882,
|
151 |
+
"model.layers.4.self_attn.o_proj": 143059,
|
152 |
+
"model.layers.4.self_attn.q_proj": 237856,
|
153 |
+
"model.layers.4.self_attn.v_proj": 148584,
|
154 |
+
"model.layers.5.mlp.down_proj": 390101,
|
155 |
+
"model.layers.5.mlp.gate_proj": 384475,
|
156 |
+
"model.layers.5.mlp.up_proj": 377591,
|
157 |
+
"model.layers.5.self_attn.k_proj": 284178,
|
158 |
+
"model.layers.5.self_attn.o_proj": 155071,
|
159 |
+
"model.layers.5.self_attn.q_proj": 256165,
|
160 |
+
"model.layers.5.self_attn.v_proj": 169034,
|
161 |
+
"model.layers.6.mlp.down_proj": 382083,
|
162 |
+
"model.layers.6.mlp.gate_proj": 390114,
|
163 |
+
"model.layers.6.mlp.up_proj": 387960,
|
164 |
+
"model.layers.6.self_attn.k_proj": 290834,
|
165 |
+
"model.layers.6.self_attn.o_proj": 170995,
|
166 |
+
"model.layers.6.self_attn.q_proj": 256834,
|
167 |
+
"model.layers.6.self_attn.v_proj": 183257,
|
168 |
+
"model.layers.7.mlp.down_proj": 385748,
|
169 |
+
"model.layers.7.mlp.gate_proj": 398626,
|
170 |
+
"model.layers.7.mlp.up_proj": 392283,
|
171 |
+
"model.layers.7.self_attn.k_proj": 253397,
|
172 |
+
"model.layers.7.self_attn.o_proj": 154212,
|
173 |
+
"model.layers.7.self_attn.q_proj": 221549,
|
174 |
+
"model.layers.7.self_attn.v_proj": 160685,
|
175 |
+
"model.layers.8.mlp.down_proj": 394012,
|
176 |
+
"model.layers.8.mlp.gate_proj": 413009,
|
177 |
+
"model.layers.8.mlp.up_proj": 397484,
|
178 |
+
"model.layers.8.self_attn.k_proj": 270590,
|
179 |
+
"model.layers.8.self_attn.o_proj": 171845,
|
180 |
+
"model.layers.8.self_attn.q_proj": 238918,
|
181 |
+
"model.layers.8.self_attn.v_proj": 193766,
|
182 |
+
"model.layers.9.mlp.down_proj": 393867,
|
183 |
+
"model.layers.9.mlp.gate_proj": 409331,
|
184 |
+
"model.layers.9.mlp.up_proj": 400690,
|
185 |
+
"model.layers.9.self_attn.k_proj": 285793,
|
186 |
+
"model.layers.9.self_attn.o_proj": 175292,
|
187 |
+
"model.layers.9.self_attn.q_proj": 271217,
|
188 |
+
"model.layers.9.self_attn.v_proj": 188112
|
189 |
+
}
|
190 |
+
},
|
191 |
+
"architectures": [
|
192 |
+
"LlamaForCausalLM"
|
193 |
+
],
|
194 |
+
"attention_bias": false,
|
195 |
+
"attention_dropout": 0.0,
|
196 |
+
"bos_token_id": 1,
|
197 |
+
"eos_token_id": 2,
|
198 |
+
"hidden_act": "silu",
|
199 |
+
"hidden_size": 2048,
|
200 |
+
"initializer_range": 0.02,
|
201 |
+
"intermediate_size": 5632,
|
202 |
+
"max_position_embeddings": 2048,
|
203 |
+
"max_sequence_length": 2048,
|
204 |
+
"model_type": "llama",
|
205 |
+
"num_attention_heads": 16,
|
206 |
+
"num_hidden_layers": 24,
|
207 |
+
"num_key_value_heads": 16,
|
208 |
+
"pad_token_id": 0,
|
209 |
+
"pretraining_tp": 1,
|
210 |
+
"rms_norm_eps": 1e-06,
|
211 |
+
"rope_scaling": null,
|
212 |
+
"rope_theta": 10000.0,
|
213 |
+
"tie_word_embeddings": false,
|
214 |
+
"torch_dtype": "float16",
|
215 |
+
"transformers_version": "4.39.3",
|
216 |
+
"use_cache": true,
|
217 |
+
"vocab_size": 32000
|
218 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68ca30d8fa2014d94dc99ce77942425f1acfc6f381accd966b248f9ee84a512d
|
3 |
+
size 1214896665
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
35 |
+
"model_max_length": 2048,
|
36 |
+
"pad_token": "<unk>",
|
37 |
+
"padding_side": "right",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|