HuggingFaceUser/adapter-mini-medmobile-no_LoRA-UltraMedical-V3
Browse files- README.md +194 -0
- added_tokens.json +13 -0
- config.json +36 -0
- generation_config.json +11 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +202 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +131 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: microsoft/Phi-3-mini-4k-instruct
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: phi-3-mini-UltraMedical-NoLoRA
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# phi-3-mini-UltraMedical-NoLoRA
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.7358
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 0.0001
|
40 |
+
- train_batch_size: 8
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 4
|
44 |
+
- total_train_batch_size: 32
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
48 |
+
- num_epochs: 3
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
54 |
+
| 0.8656 | 0.0225 | 200 | 0.7711 |
|
55 |
+
| 0.7615 | 0.0451 | 400 | 0.7521 |
|
56 |
+
| 0.748 | 0.0676 | 600 | 0.7457 |
|
57 |
+
| 0.7465 | 0.0902 | 800 | 0.7428 |
|
58 |
+
| 0.7468 | 0.1127 | 1000 | 0.7419 |
|
59 |
+
| 0.7434 | 0.1352 | 1200 | 0.7429 |
|
60 |
+
| 0.7467 | 0.1578 | 1400 | 0.7451 |
|
61 |
+
| 0.7508 | 0.1803 | 1600 | 0.7469 |
|
62 |
+
| 0.7505 | 0.2029 | 1800 | 0.7503 |
|
63 |
+
| 0.7541 | 0.2254 | 2000 | 0.7531 |
|
64 |
+
| 0.7559 | 0.2479 | 2200 | 0.7576 |
|
65 |
+
| 0.7592 | 0.2705 | 2400 | 0.7599 |
|
66 |
+
| 0.7729 | 0.2930 | 2600 | 0.7635 |
|
67 |
+
| 0.772 | 0.3156 | 2800 | 0.7645 |
|
68 |
+
| 0.7707 | 0.3381 | 3000 | 0.7628 |
|
69 |
+
| 0.7616 | 0.3606 | 3200 | 0.7614 |
|
70 |
+
| 0.7632 | 0.3832 | 3400 | 0.7590 |
|
71 |
+
| 0.7613 | 0.4057 | 3600 | 0.7574 |
|
72 |
+
| 0.7581 | 0.4283 | 3800 | 0.7558 |
|
73 |
+
| 0.7583 | 0.4508 | 4000 | 0.7539 |
|
74 |
+
| 0.7509 | 0.4733 | 4200 | 0.7518 |
|
75 |
+
| 0.7559 | 0.4959 | 4400 | 0.7506 |
|
76 |
+
| 0.7523 | 0.5184 | 4600 | 0.7491 |
|
77 |
+
| 0.7461 | 0.5410 | 4800 | 0.7469 |
|
78 |
+
| 0.7504 | 0.5635 | 5000 | 0.7464 |
|
79 |
+
| 0.7486 | 0.5860 | 5200 | 0.7449 |
|
80 |
+
| 0.7454 | 0.6086 | 5400 | 0.7436 |
|
81 |
+
| 0.7451 | 0.6311 | 5600 | 0.7427 |
|
82 |
+
| 0.7431 | 0.6537 | 5800 | 0.7412 |
|
83 |
+
| 0.7438 | 0.6762 | 6000 | 0.7402 |
|
84 |
+
| 0.7471 | 0.6987 | 6200 | 0.7390 |
|
85 |
+
| 0.7416 | 0.7213 | 6400 | 0.7378 |
|
86 |
+
| 0.7345 | 0.7438 | 6600 | 0.7364 |
|
87 |
+
| 0.7437 | 0.7663 | 6800 | 0.7349 |
|
88 |
+
| 0.7431 | 0.7889 | 7000 | 0.7349 |
|
89 |
+
| 0.737 | 0.8114 | 7200 | 0.7339 |
|
90 |
+
| 0.7358 | 0.8340 | 7400 | 0.7333 |
|
91 |
+
| 0.7336 | 0.8565 | 7600 | 0.7320 |
|
92 |
+
| 0.7327 | 0.8790 | 7800 | 0.7310 |
|
93 |
+
| 0.7288 | 0.9016 | 8000 | 0.7303 |
|
94 |
+
| 0.7326 | 0.9241 | 8200 | 0.7295 |
|
95 |
+
| 0.7354 | 0.9467 | 8400 | 0.7287 |
|
96 |
+
| 0.731 | 0.9692 | 8600 | 0.7278 |
|
97 |
+
| 0.7317 | 0.9917 | 8800 | 0.7272 |
|
98 |
+
| 0.6809 | 1.0143 | 9000 | 0.7359 |
|
99 |
+
| 0.6548 | 1.0368 | 9200 | 0.7341 |
|
100 |
+
| 0.6463 | 1.0594 | 9400 | 0.7353 |
|
101 |
+
| 0.6516 | 1.0819 | 9600 | 0.7357 |
|
102 |
+
| 0.6544 | 1.1044 | 9800 | 0.7345 |
|
103 |
+
| 0.6558 | 1.1270 | 10000 | 0.7342 |
|
104 |
+
| 0.6532 | 1.1495 | 10200 | 0.7331 |
|
105 |
+
| 0.653 | 1.1721 | 10400 | 0.7328 |
|
106 |
+
| 0.6583 | 1.1946 | 10600 | 0.7323 |
|
107 |
+
| 0.6537 | 1.2171 | 10800 | 0.7326 |
|
108 |
+
| 0.6622 | 1.2397 | 11000 | 0.7318 |
|
109 |
+
| 0.6596 | 1.2622 | 11200 | 0.7315 |
|
110 |
+
| 0.6522 | 1.2848 | 11400 | 0.7304 |
|
111 |
+
| 0.6517 | 1.3073 | 11600 | 0.7300 |
|
112 |
+
| 0.657 | 1.3298 | 11800 | 0.7296 |
|
113 |
+
| 0.6554 | 1.3524 | 12000 | 0.7286 |
|
114 |
+
| 0.6545 | 1.3749 | 12200 | 0.7287 |
|
115 |
+
| 0.6556 | 1.3975 | 12400 | 0.7283 |
|
116 |
+
| 0.655 | 1.4200 | 12600 | 0.7294 |
|
117 |
+
| 0.6489 | 1.4425 | 12800 | 0.7285 |
|
118 |
+
| 0.6539 | 1.4651 | 13000 | 0.7269 |
|
119 |
+
| 0.654 | 1.4876 | 13200 | 0.7273 |
|
120 |
+
| 0.6556 | 1.5102 | 13400 | 0.7273 |
|
121 |
+
| 0.6529 | 1.5327 | 13600 | 0.7271 |
|
122 |
+
| 0.6504 | 1.5552 | 13800 | 0.7264 |
|
123 |
+
| 0.6498 | 1.5778 | 14000 | 0.7256 |
|
124 |
+
| 0.6517 | 1.6003 | 14200 | 0.7255 |
|
125 |
+
| 0.656 | 1.6229 | 14400 | 0.7252 |
|
126 |
+
| 0.6471 | 1.6454 | 14600 | 0.7242 |
|
127 |
+
| 0.6485 | 1.6679 | 14800 | 0.7243 |
|
128 |
+
| 0.6545 | 1.6905 | 15000 | 0.7242 |
|
129 |
+
| 0.6527 | 1.7130 | 15200 | 0.7238 |
|
130 |
+
| 0.6504 | 1.7356 | 15400 | 0.7236 |
|
131 |
+
| 0.6492 | 1.7581 | 15600 | 0.7229 |
|
132 |
+
| 0.6529 | 1.7806 | 15800 | 0.7232 |
|
133 |
+
| 0.6507 | 1.8032 | 16000 | 0.7226 |
|
134 |
+
| 0.653 | 1.8257 | 16200 | 0.7229 |
|
135 |
+
| 0.6461 | 1.8483 | 16400 | 0.7223 |
|
136 |
+
| 0.6453 | 1.8708 | 16600 | 0.7221 |
|
137 |
+
| 0.6534 | 1.8933 | 16800 | 0.7219 |
|
138 |
+
| 0.6455 | 1.9159 | 17000 | 0.7220 |
|
139 |
+
| 0.6485 | 1.9384 | 17200 | 0.7212 |
|
140 |
+
| 0.6536 | 1.9610 | 17400 | 0.7214 |
|
141 |
+
| 0.6444 | 1.9835 | 17600 | 0.7211 |
|
142 |
+
| 0.6346 | 2.0060 | 17800 | 0.7356 |
|
143 |
+
| 0.5929 | 2.0286 | 18000 | 0.7368 |
|
144 |
+
| 0.5951 | 2.0511 | 18200 | 0.7371 |
|
145 |
+
| 0.6013 | 2.0736 | 18400 | 0.7374 |
|
146 |
+
| 0.6004 | 2.0962 | 18600 | 0.7375 |
|
147 |
+
| 0.5991 | 2.1187 | 18800 | 0.7375 |
|
148 |
+
| 0.5971 | 2.1413 | 19000 | 0.7369 |
|
149 |
+
| 0.597 | 2.1638 | 19200 | 0.7380 |
|
150 |
+
| 0.5951 | 2.1863 | 19400 | 0.7370 |
|
151 |
+
| 0.5916 | 2.2089 | 19600 | 0.7370 |
|
152 |
+
| 0.5992 | 2.2314 | 19800 | 0.7372 |
|
153 |
+
| 0.6011 | 2.2540 | 20000 | 0.7364 |
|
154 |
+
| 0.6003 | 2.2765 | 20200 | 0.7370 |
|
155 |
+
| 0.6003 | 2.2990 | 20400 | 0.7370 |
|
156 |
+
| 0.5985 | 2.3216 | 20600 | 0.7370 |
|
157 |
+
| 0.5988 | 2.3441 | 20800 | 0.7367 |
|
158 |
+
| 0.5959 | 2.3667 | 21000 | 0.7370 |
|
159 |
+
| 0.6019 | 2.3892 | 21200 | 0.7370 |
|
160 |
+
| 0.5977 | 2.4117 | 21400 | 0.7367 |
|
161 |
+
| 0.602 | 2.4343 | 21600 | 0.7368 |
|
162 |
+
| 0.5958 | 2.4568 | 21800 | 0.7368 |
|
163 |
+
| 0.5969 | 2.4794 | 22000 | 0.7360 |
|
164 |
+
| 0.6025 | 2.5019 | 22200 | 0.7362 |
|
165 |
+
| 0.5942 | 2.5244 | 22400 | 0.7361 |
|
166 |
+
| 0.6006 | 2.5470 | 22600 | 0.7361 |
|
167 |
+
| 0.5952 | 2.5695 | 22800 | 0.7366 |
|
168 |
+
| 0.6007 | 2.5921 | 23000 | 0.7363 |
|
169 |
+
| 0.6003 | 2.6146 | 23200 | 0.7363 |
|
170 |
+
| 0.6006 | 2.6371 | 23400 | 0.7359 |
|
171 |
+
| 0.6014 | 2.6597 | 23600 | 0.7360 |
|
172 |
+
| 0.6008 | 2.6822 | 23800 | 0.7356 |
|
173 |
+
| 0.6005 | 2.7048 | 24000 | 0.7357 |
|
174 |
+
| 0.5958 | 2.7273 | 24200 | 0.7356 |
|
175 |
+
| 0.5977 | 2.7498 | 24400 | 0.7358 |
|
176 |
+
| 0.6 | 2.7724 | 24600 | 0.7358 |
|
177 |
+
| 0.5978 | 2.7949 | 24800 | 0.7362 |
|
178 |
+
| 0.6018 | 2.8175 | 25000 | 0.7359 |
|
179 |
+
| 0.6079 | 2.8400 | 25200 | 0.7359 |
|
180 |
+
| 0.6036 | 2.8625 | 25400 | 0.7359 |
|
181 |
+
| 0.5985 | 2.8851 | 25600 | 0.7359 |
|
182 |
+
| 0.6019 | 2.9076 | 25800 | 0.7359 |
|
183 |
+
| 0.5994 | 2.9302 | 26000 | 0.7358 |
|
184 |
+
| 0.6027 | 2.9527 | 26200 | 0.7358 |
|
185 |
+
| 0.6014 | 2.9752 | 26400 | 0.7358 |
|
186 |
+
| 0.5957 | 2.9978 | 26600 | 0.7358 |
|
187 |
+
|
188 |
+
|
189 |
+
### Framework versions
|
190 |
+
|
191 |
+
- Transformers 4.43.3
|
192 |
+
- Pytorch 2.3.1+cu121
|
193 |
+
- Datasets 2.20.0
|
194 |
+
- Tokenizers 0.19.1
|
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 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Phi3ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
|
10 |
+
"AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
|
11 |
+
},
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"embd_pdrop": 0.0,
|
14 |
+
"eos_token_id": 32000,
|
15 |
+
"hidden_act": "silu",
|
16 |
+
"hidden_size": 3072,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 8192,
|
19 |
+
"max_position_embeddings": 4096,
|
20 |
+
"model_type": "phi3",
|
21 |
+
"num_attention_heads": 32,
|
22 |
+
"num_hidden_layers": 32,
|
23 |
+
"num_key_value_heads": 32,
|
24 |
+
"original_max_position_embeddings": 4096,
|
25 |
+
"pad_token_id": 32000,
|
26 |
+
"resid_pdrop": 0.0,
|
27 |
+
"rms_norm_eps": 1e-05,
|
28 |
+
"rope_scaling": null,
|
29 |
+
"rope_theta": 10000.0,
|
30 |
+
"sliding_window": 2047,
|
31 |
+
"tie_word_embeddings": false,
|
32 |
+
"torch_dtype": "bfloat16",
|
33 |
+
"transformers_version": "4.43.3",
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 32064
|
36 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": [
|
5 |
+
32000,
|
6 |
+
32001,
|
7 |
+
32007
|
8 |
+
],
|
9 |
+
"pad_token_id": 32000,
|
10 |
+
"transformers_version": "4.43.3"
|
11 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1ad6fb18e056cf1bd94ddf49fc83cdc5260d919d112217c0de1234f22ce5039
|
3 |
+
size 4972489328
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:388d4546ba937f1f5923c62c7280c8d9d231edd582e0013046d4aae10608d2f8
|
3 |
+
size 2669692552
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 7642159104
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
12 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
13 |
+
"model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
14 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
15 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
16 |
+
"model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
17 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
18 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
19 |
+
"model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
20 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
21 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
22 |
+
"model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
23 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
24 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
25 |
+
"model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
26 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
27 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
28 |
+
"model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
29 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
30 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
31 |
+
"model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
32 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
33 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
34 |
+
"model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
35 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
36 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
37 |
+
"model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
38 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
39 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
40 |
+
"model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
41 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
42 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
43 |
+
"model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
44 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
45 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
46 |
+
"model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
47 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
48 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
49 |
+
"model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
50 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
51 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
52 |
+
"model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
53 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
54 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
55 |
+
"model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
56 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
57 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
58 |
+
"model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
59 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
60 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
61 |
+
"model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
62 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
63 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
64 |
+
"model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
65 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
66 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
67 |
+
"model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
68 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
69 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
70 |
+
"model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
71 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
72 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
73 |
+
"model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
74 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
75 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
76 |
+
"model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
77 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
78 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
79 |
+
"model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
80 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
81 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
82 |
+
"model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
83 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
84 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
85 |
+
"model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
86 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
87 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
88 |
+
"model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
89 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
90 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
91 |
+
"model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
92 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
93 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
94 |
+
"model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
95 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
96 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
97 |
+
"model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
98 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
99 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
100 |
+
"model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
101 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
102 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
103 |
+
"model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
104 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
105 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
106 |
+
"model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
107 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
108 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
109 |
+
"model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
110 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
111 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
112 |
+
"model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
113 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
114 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
115 |
+
"model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
116 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
117 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
118 |
+
"model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
119 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
120 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
121 |
+
"model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
122 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
123 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
124 |
+
"model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
125 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
126 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
127 |
+
"model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
128 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
129 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
130 |
+
"model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
131 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
132 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
133 |
+
"model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
134 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
135 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
136 |
+
"model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
137 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
138 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
139 |
+
"model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
140 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
141 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
142 |
+
"model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
143 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
144 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
145 |
+
"model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
146 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
147 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
148 |
+
"model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
149 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
150 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
151 |
+
"model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
152 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
153 |
+
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
154 |
+
"model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
155 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
156 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
157 |
+
"model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
158 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
159 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
160 |
+
"model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
161 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
162 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
163 |
+
"model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
|
164 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
165 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
166 |
+
"model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
167 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
168 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
169 |
+
"model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
170 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
171 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
172 |
+
"model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
173 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
174 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
175 |
+
"model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
176 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
177 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
178 |
+
"model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
179 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
180 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
181 |
+
"model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
182 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
183 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
184 |
+
"model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
185 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
186 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
187 |
+
"model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
188 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
189 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
190 |
+
"model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
191 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
192 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
193 |
+
"model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
194 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
195 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
196 |
+
"model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
197 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
198 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
199 |
+
"model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
200 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
201 |
+
}
|
202 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
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 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": true,
|
4 |
+
"add_prefix_space": null,
|
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": true,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<|endoftext|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<|assistant|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": true,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"32002": {
|
47 |
+
"content": "<|placeholder1|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": true,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"32003": {
|
55 |
+
"content": "<|placeholder2|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": true,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"32004": {
|
63 |
+
"content": "<|placeholder3|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": true,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"32005": {
|
71 |
+
"content": "<|placeholder4|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": true,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"32006": {
|
79 |
+
"content": "<|system|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": true,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"32007": {
|
87 |
+
"content": "<|end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": true,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"32008": {
|
95 |
+
"content": "<|placeholder5|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": true,
|
99 |
+
"single_word": false,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"32009": {
|
103 |
+
"content": "<|placeholder6|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": true,
|
107 |
+
"single_word": false,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"32010": {
|
111 |
+
"content": "<|user|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": true,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
}
|
118 |
+
},
|
119 |
+
"bos_token": "<s>",
|
120 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
121 |
+
"clean_up_tokenization_spaces": false,
|
122 |
+
"eos_token": "<|endoftext|>",
|
123 |
+
"legacy": false,
|
124 |
+
"model_max_length": 4096,
|
125 |
+
"pad_token": "<unk>",
|
126 |
+
"padding_side": "left",
|
127 |
+
"sp_model_kwargs": {},
|
128 |
+
"tokenizer_class": "LlamaTokenizer",
|
129 |
+
"unk_token": "<unk>",
|
130 |
+
"use_default_system_prompt": false
|
131 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6549f63cb4049449dd78a7cca3dfe4ad4a1a6318cde27e8410bfaeec0a956244
|
3 |
+
size 5432
|