commit files to HF hub
Browse files- added_tokens.json +13 -0
- config.json +233 -0
- model.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +130 -0
added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32001,
|
3 |
+
"<|endoftext|>": 32000,
|
4 |
+
"<|end|>": 32007,
|
5 |
+
"<|placeholder1|>": 32002,
|
6 |
+
"<|placeholder2|>": 32003,
|
7 |
+
"<|placeholder3|>": 32004,
|
8 |
+
"<|placeholder4|>": 32005,
|
9 |
+
"<|placeholder5|>": 32008,
|
10 |
+
"<|placeholder6|>": 32009,
|
11 |
+
"<|system|>": 32006,
|
12 |
+
"<|user|>": 32010
|
13 |
+
}
|
config.json
ADDED
@@ -0,0 +1,233 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"vocab_size": 32064,
|
3 |
+
"hidden_size": 3072,
|
4 |
+
"intermediate_size": 8192,
|
5 |
+
"num_hidden_layers": 32,
|
6 |
+
"num_attention_heads": 32,
|
7 |
+
"num_key_value_heads": 32,
|
8 |
+
"resid_pdrop": 0.0,
|
9 |
+
"embd_pdrop": 0.0,
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"max_position_embeddings": 131072,
|
13 |
+
"original_max_position_embeddings": 4096,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"rms_norm_eps": 1e-05,
|
16 |
+
"use_cache": true,
|
17 |
+
"rope_theta": 10000.0,
|
18 |
+
"rope_scaling": {
|
19 |
+
"long_factor": [
|
20 |
+
1.0299999713897705,
|
21 |
+
1.0499999523162842,
|
22 |
+
1.0499999523162842,
|
23 |
+
1.0799999237060547,
|
24 |
+
1.2299998998641968,
|
25 |
+
1.2299998998641968,
|
26 |
+
1.2999999523162842,
|
27 |
+
1.4499999284744263,
|
28 |
+
1.5999999046325684,
|
29 |
+
1.6499998569488525,
|
30 |
+
1.8999998569488525,
|
31 |
+
2.859999895095825,
|
32 |
+
3.68999981880188,
|
33 |
+
5.419999599456787,
|
34 |
+
5.489999771118164,
|
35 |
+
5.489999771118164,
|
36 |
+
9.09000015258789,
|
37 |
+
11.579999923706055,
|
38 |
+
15.65999984741211,
|
39 |
+
15.769999504089355,
|
40 |
+
15.789999961853027,
|
41 |
+
18.360000610351562,
|
42 |
+
21.989999771118164,
|
43 |
+
23.079999923706055,
|
44 |
+
30.009998321533203,
|
45 |
+
32.35000228881836,
|
46 |
+
32.590003967285156,
|
47 |
+
35.56000518798828,
|
48 |
+
39.95000457763672,
|
49 |
+
53.840003967285156,
|
50 |
+
56.20000457763672,
|
51 |
+
57.95000457763672,
|
52 |
+
59.29000473022461,
|
53 |
+
59.77000427246094,
|
54 |
+
59.920005798339844,
|
55 |
+
61.190006256103516,
|
56 |
+
61.96000671386719,
|
57 |
+
62.50000762939453,
|
58 |
+
63.3700065612793,
|
59 |
+
63.48000717163086,
|
60 |
+
63.48000717163086,
|
61 |
+
63.66000747680664,
|
62 |
+
63.850006103515625,
|
63 |
+
64.08000946044922,
|
64 |
+
64.760009765625,
|
65 |
+
64.80001068115234,
|
66 |
+
64.81001281738281,
|
67 |
+
64.81001281738281
|
68 |
+
],
|
69 |
+
"short_factor": [
|
70 |
+
1.05,
|
71 |
+
1.05,
|
72 |
+
1.05,
|
73 |
+
1.1,
|
74 |
+
1.1,
|
75 |
+
1.1500000000000001,
|
76 |
+
1.2000000000000002,
|
77 |
+
1.2500000000000002,
|
78 |
+
1.3000000000000003,
|
79 |
+
1.3500000000000003,
|
80 |
+
1.5000000000000004,
|
81 |
+
2.000000000000001,
|
82 |
+
2.000000000000001,
|
83 |
+
2.000000000000001,
|
84 |
+
2.000000000000001,
|
85 |
+
2.000000000000001,
|
86 |
+
2.000000000000001,
|
87 |
+
2.000000000000001,
|
88 |
+
2.000000000000001,
|
89 |
+
2.000000000000001,
|
90 |
+
2.000000000000001,
|
91 |
+
2.000000000000001,
|
92 |
+
2.000000000000001,
|
93 |
+
2.000000000000001,
|
94 |
+
2.000000000000001,
|
95 |
+
2.000000000000001,
|
96 |
+
2.000000000000001,
|
97 |
+
2.000000000000001,
|
98 |
+
2.000000000000001,
|
99 |
+
2.000000000000001,
|
100 |
+
2.000000000000001,
|
101 |
+
2.000000000000001,
|
102 |
+
2.0500000000000007,
|
103 |
+
2.0500000000000007,
|
104 |
+
2.0500000000000007,
|
105 |
+
2.1000000000000005,
|
106 |
+
2.1000000000000005,
|
107 |
+
2.1000000000000005,
|
108 |
+
2.1500000000000004,
|
109 |
+
2.1500000000000004,
|
110 |
+
2.3499999999999996,
|
111 |
+
2.549999999999999,
|
112 |
+
2.5999999999999988,
|
113 |
+
2.5999999999999988,
|
114 |
+
2.7499999999999982,
|
115 |
+
2.849999999999998,
|
116 |
+
2.849999999999998,
|
117 |
+
2.9499999999999975
|
118 |
+
],
|
119 |
+
"type": "su"
|
120 |
+
},
|
121 |
+
"sliding_window": 262144,
|
122 |
+
"return_dict": true,
|
123 |
+
"output_hidden_states": false,
|
124 |
+
"output_attentions": false,
|
125 |
+
"torchscript": false,
|
126 |
+
"torch_dtype": "float16",
|
127 |
+
"use_bfloat16": false,
|
128 |
+
"tf_legacy_loss": false,
|
129 |
+
"pruned_heads": {},
|
130 |
+
"tie_word_embeddings": false,
|
131 |
+
"chunk_size_feed_forward": 0,
|
132 |
+
"is_encoder_decoder": false,
|
133 |
+
"is_decoder": false,
|
134 |
+
"cross_attention_hidden_size": null,
|
135 |
+
"add_cross_attention": false,
|
136 |
+
"tie_encoder_decoder": false,
|
137 |
+
"max_length": 20,
|
138 |
+
"min_length": 0,
|
139 |
+
"do_sample": false,
|
140 |
+
"early_stopping": false,
|
141 |
+
"num_beams": 1,
|
142 |
+
"num_beam_groups": 1,
|
143 |
+
"diversity_penalty": 0.0,
|
144 |
+
"temperature": 1.0,
|
145 |
+
"top_k": 50,
|
146 |
+
"top_p": 1.0,
|
147 |
+
"typical_p": 1.0,
|
148 |
+
"repetition_penalty": 1.0,
|
149 |
+
"length_penalty": 1.0,
|
150 |
+
"no_repeat_ngram_size": 0,
|
151 |
+
"encoder_no_repeat_ngram_size": 0,
|
152 |
+
"bad_words_ids": null,
|
153 |
+
"num_return_sequences": 1,
|
154 |
+
"output_scores": false,
|
155 |
+
"return_dict_in_generate": false,
|
156 |
+
"forced_bos_token_id": null,
|
157 |
+
"forced_eos_token_id": null,
|
158 |
+
"remove_invalid_values": false,
|
159 |
+
"exponential_decay_length_penalty": null,
|
160 |
+
"suppress_tokens": null,
|
161 |
+
"begin_suppress_tokens": null,
|
162 |
+
"architectures": [
|
163 |
+
"Phi3ForCausalLM"
|
164 |
+
],
|
165 |
+
"finetuning_task": null,
|
166 |
+
"id2label": {
|
167 |
+
"0": "LABEL_0",
|
168 |
+
"1": "LABEL_1"
|
169 |
+
},
|
170 |
+
"label2id": {
|
171 |
+
"LABEL_0": 0,
|
172 |
+
"LABEL_1": 1
|
173 |
+
},
|
174 |
+
"tokenizer_class": null,
|
175 |
+
"prefix": null,
|
176 |
+
"bos_token_id": 1,
|
177 |
+
"pad_token_id": 32000,
|
178 |
+
"eos_token_id": 32000,
|
179 |
+
"sep_token_id": null,
|
180 |
+
"decoder_start_token_id": null,
|
181 |
+
"task_specific_params": null,
|
182 |
+
"problem_type": null,
|
183 |
+
"_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
|
184 |
+
"transformers_version": "4.41.2",
|
185 |
+
"auto_map": {
|
186 |
+
"AutoConfig": "microsoft/Phi-3-mini-128k-instruct--configuration_phi3.Phi3Config",
|
187 |
+
"AutoModelForCausalLM": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForCausalLM",
|
188 |
+
"AutoModelForSequenceClassification": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForSequenceClassification",
|
189 |
+
"AutoModelForTokenClassification": "microsoft/Phi-3-mini-128k-instruct--modeling_phi3.Phi3ForTokenClassification"
|
190 |
+
},
|
191 |
+
"model_type": "phi3",
|
192 |
+
"attention_bias": false,
|
193 |
+
"num_experts": 2,
|
194 |
+
"num_experts_per_tok": 2,
|
195 |
+
"router_layers": [
|
196 |
+
"gate_up_proj",
|
197 |
+
"down_proj"
|
198 |
+
],
|
199 |
+
"router_layers_index": [
|
200 |
+
0,
|
201 |
+
1,
|
202 |
+
2,
|
203 |
+
3,
|
204 |
+
4,
|
205 |
+
5,
|
206 |
+
6,
|
207 |
+
7,
|
208 |
+
8,
|
209 |
+
9,
|
210 |
+
10,
|
211 |
+
11,
|
212 |
+
12,
|
213 |
+
13,
|
214 |
+
14,
|
215 |
+
15,
|
216 |
+
16,
|
217 |
+
17,
|
218 |
+
18,
|
219 |
+
19,
|
220 |
+
20,
|
221 |
+
21,
|
222 |
+
22,
|
223 |
+
23,
|
224 |
+
24,
|
225 |
+
25,
|
226 |
+
26,
|
227 |
+
27,
|
228 |
+
28,
|
229 |
+
29,
|
230 |
+
30,
|
231 |
+
31
|
232 |
+
]
|
233 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a3b2cd5fae6482bc401a75e9ae5eb4b127907b510a8bb83e93bd86b105fa517
|
3 |
+
size 7642181696
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
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": false,
|
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 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": true,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|endoftext|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|assistant|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "<|placeholder1|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "<|placeholder2|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": true,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "<|placeholder3|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": true,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "<|placeholder4|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": true,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "<|system|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": true,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "<|end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": true,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"32008": {
|
94 |
+
"content": "<|placeholder5|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": true,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"32009": {
|
102 |
+
"content": "<|placeholder6|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": true,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"32010": {
|
110 |
+
"content": "<|user|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": true,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
}
|
117 |
+
},
|
118 |
+
"bos_token": "<s>",
|
119 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
120 |
+
"clean_up_tokenization_spaces": false,
|
121 |
+
"eos_token": "<|endoftext|>",
|
122 |
+
"legacy": false,
|
123 |
+
"model_max_length": 131072,
|
124 |
+
"pad_token": "<|endoftext|>",
|
125 |
+
"padding_side": "left",
|
126 |
+
"sp_model_kwargs": {},
|
127 |
+
"tokenizer_class": "LlamaTokenizer",
|
128 |
+
"unk_token": "<unk>",
|
129 |
+
"use_default_system_prompt": false
|
130 |
+
}
|