Hugging Face's logo

lluvecwonv
/
WikiMIA_QA_256_10_10

PEFT
Safetensors
Generated from Trainer
Model card Files Community
lluvecwonv commited on
Commit
c028735
•
1 Parent(s): 0a40a16

wikimia_unlearned

Browse files
Files changed (8) hide show
  1. README.md +60 -0
  2. adapter_config.json +219 -0
  3. adapter_model.safetensors +3 -0
  4. config.yaml +46 -0
  5. special_tokens_map.json +30 -0
  6. tokenizer.model +3 -0
  7. tokenizer_config.json +42 -0
  8. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: openlm-research/open_llama_7b
7
+ model-index:
8
+ - name: WikiMIA_QA_256_10_10
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # WikiMIA_QA_256_10_10
16
+
17
+ This model is a fine-tuned version of [openlm-research/open_llama_7b](https://huggingface.co/openlm-research/open_llama_7b) on an unknown dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 2e-05
37
+ - train_batch_size: 4
38
+ - eval_batch_size: 4
39
+ - seed: 42
40
+ - distributed_type: multi-GPU
41
+ - num_devices: 2
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 32
44
+ - total_eval_batch_size: 8
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 26
48
+ - training_steps: 267
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - PEFT 0.10.0
57
+ - Transformers 4.41.0.dev0
58
+ - Pytorch 2.2.1+cu121
59
+ - Datasets 2.19.0
60
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": null,
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "base_model.model.model.layers.7.self_attn.v_proj.base_layer",
24
+ "base_model.model.model.layers.17.self_attn.v_proj.base_layer",
25
+ "base_model.model.model.layers.16.self_attn.q_proj.lora_B.default",
26
+ "base_model.model.model.layers.24.self_attn.v_proj.lora_A.default",
27
+ "base_model.model.model.layers.1.self_attn.q_proj.lora_A.default",
28
+ "base_model.model.model.layers.11.self_attn.q_proj.lora_B.default",
29
+ "base_model.model.model.layers.18.self_attn.q_proj.lora_A.default",
30
+ "base_model.model.model.layers.24.self_attn.q_proj.lora_A.default",
31
+ "base_model.model.model.layers.29.self_attn.q_proj.lora_A.default",
32
+ "base_model.model.model.layers.21.self_attn.q_proj.base_layer",
33
+ "base_model.model.model.layers.7.self_attn.q_proj.lora_A.default",
34
+ "base_model.model.model.layers.0.self_attn.q_proj.lora_B.default",
35
+ "base_model.model.model.layers.21.self_attn.q_proj.lora_B.default",
36
+ "base_model.model.model.layers.5.self_attn.v_proj.lora_A.default",
37
+ "base_model.model.model.layers.25.self_attn.q_proj.base_layer",
38
+ "base_model.model.model.layers.10.self_attn.q_proj.lora_A.default",
39
+ "base_model.model.model.layers.24.self_attn.q_proj.base_layer",
40
+ "base_model.model.model.layers.9.self_attn.v_proj.lora_A.default",
41
+ "base_model.model.model.layers.25.self_attn.v_proj.lora_B.default",
42
+ "base_model.model.model.layers.26.self_attn.v_proj.base_layer",
43
+ "base_model.model.model.layers.8.self_attn.q_proj.base_layer",
44
+ "base_model.model.model.layers.5.self_attn.q_proj.base_layer",
45
+ "base_model.model.model.layers.15.self_attn.v_proj.lora_B.default",
46
+ "base_model.model.model.layers.16.self_attn.q_proj.base_layer",
47
+ "base_model.model.model.layers.29.self_attn.q_proj.lora_B.default",
48
+ "base_model.model.model.layers.22.self_attn.v_proj.lora_A.default",
49
+ "base_model.model.model.layers.17.self_attn.v_proj.lora_B.default",
50
+ "base_model.model.model.layers.9.self_attn.q_proj.lora_A.default",
51
+ "base_model.model.model.layers.28.self_attn.q_proj.lora_B.default",
52
+ "base_model.model.model.layers.15.self_attn.v_proj.base_layer",
53
+ "base_model.model.model.layers.1.self_attn.q_proj.base_layer",
54
+ "base_model.model.model.layers.17.self_attn.q_proj.lora_B.default",
55
+ "base_model.model.model.layers.27.self_attn.q_proj.lora_A.default",
56
+ "base_model.model.model.layers.31.self_attn.v_proj.lora_B.default",
57
+ "base_model.model.model.layers.18.self_attn.v_proj.lora_B.default",
58
+ "base_model.model.model.layers.26.self_attn.q_proj.base_layer",
59
+ "base_model.model.model.layers.11.self_attn.v_proj.lora_B.default",
60
+ "base_model.model.model.layers.31.self_attn.v_proj.lora_A.default",
61
+ "base_model.model.model.layers.25.self_attn.v_proj.lora_A.default",
62
+ "base_model.model.model.layers.3.self_attn.q_proj.lora_B.default",
63
+ "base_model.model.model.layers.20.self_attn.v_proj.lora_B.default",
64
+ "base_model.model.model.layers.31.self_attn.q_proj.lora_B.default",
65
+ "base_model.model.model.layers.8.self_attn.v_proj.lora_B.default",
66
+ "base_model.model.model.layers.21.self_attn.v_proj.base_layer",
67
+ "base_model.model.model.layers.19.self_attn.v_proj.lora_B.default",
68
+ "base_model.model.model.layers.12.self_attn.v_proj.lora_B.default",
69
+ "base_model.model.model.layers.11.self_attn.v_proj.lora_A.default",
70
+ "base_model.model.model.layers.11.self_attn.v_proj.base_layer",
71
+ "base_model.model.model.layers.28.self_attn.v_proj.lora_B.default",
72
+ "base_model.model.model.layers.8.self_attn.v_proj.lora_A.default",
73
+ "base_model.model.model.layers.14.self_attn.q_proj.lora_B.default",
74
+ "base_model.model.model.layers.26.self_attn.q_proj.lora_A.default",
75
+ "base_model.model.model.layers.27.self_attn.q_proj.base_layer",
76
+ "base_model.model.model.layers.13.self_attn.v_proj.lora_A.default",
77
+ "base_model.model.model.layers.24.self_attn.q_proj.lora_B.default",
78
+ "base_model.model.model.layers.6.self_attn.q_proj.lora_A.default",
79
+ "base_model.model.model.layers.18.self_attn.q_proj.lora_B.default",
80
+ "base_model.model.model.layers.19.self_attn.q_proj.base_layer",
81
+ "base_model.model.model.layers.25.self_attn.q_proj.lora_B.default",
82
+ "base_model.model.model.layers.18.self_attn.v_proj.base_layer",
83
+ "base_model.model.model.layers.31.self_attn.q_proj.lora_A.default",
84
+ "base_model.model.model.layers.0.self_attn.q_proj.base_layer",
85
+ "base_model.model.model.layers.2.self_attn.q_proj.lora_A.default",
86
+ "base_model.model.model.layers.30.self_attn.v_proj.base_layer",
87
+ "base_model.model.model.layers.10.self_attn.q_proj.lora_B.default",
88
+ "base_model.model.model.layers.7.self_attn.v_proj.lora_A.default",
89
+ "base_model.model.model.layers.2.self_attn.v_proj.base_layer",
90
+ "base_model.model.model.layers.3.self_attn.q_proj.lora_A.default",
91
+ "base_model.model.model.layers.3.self_attn.v_proj.lora_A.default",
92
+ "base_model.model.model.layers.3.self_attn.v_proj.lora_B.default",
93
+ "base_model.model.model.layers.7.self_attn.q_proj.lora_B.default",
94
+ "base_model.model.model.layers.19.self_attn.v_proj.base_layer",
95
+ "base_model.model.model.layers.0.self_attn.v_proj.lora_B.default",
96
+ "base_model.model.model.layers.5.self_attn.q_proj.lora_A.default",
97
+ "base_model.model.model.layers.7.self_attn.q_proj.base_layer",
98
+ "base_model.model.model.layers.17.self_attn.q_proj.base_layer",
99
+ "base_model.model.model.layers.14.self_attn.v_proj.lora_B.default",
100
+ "base_model.model.model.layers.29.self_attn.v_proj.base_layer",
101
+ "base_model.model.model.layers.11.self_attn.q_proj.lora_A.default",
102
+ "base_model.model.model.layers.23.self_attn.q_proj.lora_A.default",
103
+ "base_model.model.model.layers.21.self_attn.v_proj.lora_B.default",
104
+ "base_model.model.model.layers.11.self_attn.q_proj.base_layer",
105
+ "base_model.model.model.layers.15.self_attn.v_proj.lora_A.default",
106
+ "base_model.model.model.layers.21.self_attn.q_proj.lora_A.default",
107
+ "base_model.model.model.layers.27.self_attn.v_proj.lora_B.default",
108
+ "base_model.model.model.layers.26.self_attn.q_proj.lora_B.default",
109
+ "base_model.model.model.layers.0.self_attn.q_proj.lora_A.default",
110
+ "base_model.model.model.layers.13.self_attn.v_proj.base_layer",
111
+ "base_model.model.model.layers.1.self_attn.v_proj.base_layer",
112
+ "base_model.model.model.layers.22.self_attn.v_proj.lora_B.default",
113
+ "base_model.model.model.layers.26.self_attn.v_proj.lora_A.default",
114
+ "base_model.model.model.layers.4.self_attn.q_proj.base_layer",
115
+ "base_model.model.model.layers.0.self_attn.v_proj.base_layer",
116
+ "base_model.model.model.layers.19.self_attn.v_proj.lora_A.default",
117
+ "base_model.model.model.layers.4.self_attn.v_proj.lora_A.default",
118
+ "base_model.model.model.layers.31.self_attn.q_proj.base_layer",
119
+ "base_model.model.model.layers.31.self_attn.v_proj.base_layer",
120
+ "base_model.model.model.layers.15.self_attn.q_proj.lora_B.default",
121
+ "base_model.model.model.layers.17.self_attn.q_proj.lora_A.default",
122
+ "base_model.model.model.layers.20.self_attn.v_proj.lora_A.default",
123
+ "base_model.model.model.layers.30.self_attn.q_proj.base_layer",
124
+ "base_model.model.model.layers.6.self_attn.q_proj.base_layer",
125
+ "base_model.model.model.layers.19.self_attn.q_proj.lora_A.default",
126
+ "base_model.model.model.layers.5.self_attn.v_proj.base_layer",
127
+ "base_model.model.model.layers.23.self_attn.v_proj.lora_A.default",
128
+ "base_model.model.model.layers.3.self_attn.v_proj.base_layer",
129
+ "base_model.model.model.layers.25.self_attn.q_proj.lora_A.default",
130
+ "base_model.model.model.layers.13.self_attn.q_proj.lora_B.default",
131
+ "base_model.model.model.layers.27.self_attn.v_proj.lora_A.default",
132
+ "base_model.model.model.layers.17.self_attn.v_proj.lora_A.default",
133
+ "base_model.model.model.layers.16.self_attn.v_proj.base_layer",
134
+ "base_model.model.model.layers.20.self_attn.q_proj.base_layer",
135
+ "base_model.model.model.layers.8.self_attn.q_proj.lora_A.default",
136
+ "base_model.model.model.layers.2.self_attn.v_proj.lora_A.default",
137
+ "base_model.model.model.layers.24.self_attn.v_proj.lora_B.default",
138
+ "base_model.model.model.layers.27.self_attn.q_proj.lora_B.default",
139
+ "base_model.model.model.layers.23.self_attn.v_proj.lora_B.default",
140
+ "base_model.model.model.layers.14.self_attn.q_proj.base_layer",
141
+ "base_model.model.model.layers.24.self_attn.v_proj.base_layer",
142
+ "base_model.model.model.layers.9.self_attn.q_proj.base_layer",
143
+ "base_model.model.model.layers.21.self_attn.v_proj.lora_A.default",
144
+ "base_model.model.model.layers.26.self_attn.v_proj.lora_B.default",
145
+ "base_model.model.model.layers.29.self_attn.v_proj.lora_A.default",
146
+ "base_model.model.model.layers.13.self_attn.q_proj.base_layer",
147
+ "base_model.model.model.layers.1.self_attn.v_proj.lora_B.default",
148
+ "base_model.model.model.layers.28.self_attn.q_proj.base_layer",
149
+ "base_model.model.model.layers.23.self_attn.q_proj.lora_B.default",
150
+ "base_model.model.model.layers.20.self_attn.q_proj.lora_A.default",
151
+ "base_model.model.model.layers.13.self_attn.q_proj.lora_A.default",
152
+ "base_model.model.model.layers.8.self_attn.v_proj.base_layer",
153
+ "base_model.model.model.layers.12.self_attn.q_proj.lora_A.default",
154
+ "base_model.model.model.layers.12.self_attn.q_proj.base_layer",
155
+ "base_model.model.model.layers.28.self_attn.v_proj.base_layer",
156
+ "base_model.model.model.layers.12.self_attn.v_proj.lora_A.default",
157
+ "base_model.model.model.layers.20.self_attn.v_proj.base_layer",
158
+ "base_model.model.model.layers.4.self_attn.q_proj.lora_A.default",
159
+ "base_model.model.model.layers.10.self_attn.v_proj.base_layer",
160
+ "base_model.model.model.layers.16.self_attn.v_proj.lora_B.default",
161
+ "base_model.model.model.layers.4.self_attn.v_proj.lora_B.default",
162
+ "base_model.model.model.layers.12.self_attn.q_proj.lora_B.default",
163
+ "base_model.model.model.layers.0.self_attn.v_proj.lora_A.default",
164
+ "base_model.model.model.layers.23.self_attn.q_proj.base_layer",
165
+ "base_model.model.model.layers.3.self_attn.q_proj.base_layer",
166
+ "base_model.model.model.layers.10.self_attn.q_proj.base_layer",
167
+ "base_model.model.model.layers.6.self_attn.q_proj.lora_B.default",
168
+ "base_model.model.model.layers.16.self_attn.v_proj.lora_A.default",
169
+ "base_model.model.model.layers.9.self_attn.v_proj.base_layer",
170
+ "base_model.model.model.layers.5.self_attn.v_proj.lora_B.default",
171
+ "base_model.model.model.layers.14.self_attn.q_proj.lora_A.default",
172
+ "base_model.model.model.layers.19.self_attn.q_proj.lora_B.default",
173
+ "base_model.model.model.layers.14.self_attn.v_proj.base_layer",
174
+ "base_model.model.model.layers.22.self_attn.v_proj.base_layer",
175
+ "base_model.model.model.layers.4.self_attn.q_proj.lora_B.default",
176
+ "base_model.model.model.layers.14.self_attn.v_proj.lora_A.default",
177
+ "base_model.model.model.layers.25.self_attn.v_proj.base_layer",
178
+ "base_model.model.model.layers.18.self_attn.v_proj.lora_A.default",
179
+ "base_model.model.model.layers.10.self_attn.v_proj.lora_B.default",
180
+ "base_model.model.model.layers.30.self_attn.v_proj.lora_B.default",
181
+ "base_model.model.model.layers.18.self_attn.q_proj.base_layer",
182
+ "base_model.model.model.layers.12.self_attn.v_proj.base_layer",
183
+ "base_model.model.model.layers.8.self_attn.q_proj.lora_B.default",
184
+ "base_model.model.model.layers.20.self_attn.q_proj.lora_B.default",
185
+ "base_model.model.model.layers.22.self_attn.q_proj.lora_A.default",
186
+ "base_model.model.model.layers.29.self_attn.q_proj.base_layer",
187
+ "base_model.model.model.layers.29.self_attn.v_proj.lora_B.default",
188
+ "base_model.model.model.layers.7.self_attn.v_proj.lora_B.default",
189
+ "base_model.model.model.layers.10.self_attn.v_proj.lora_A.default",
190
+ "base_model.model.model.layers.22.self_attn.q_proj.lora_B.default",
191
+ "base_model.model.model.layers.22.self_attn.q_proj.base_layer",
192
+ "base_model.model.model.layers.5.self_attn.q_proj.lora_B.default",
193
+ "base_model.model.model.layers.4.self_attn.v_proj.base_layer",
194
+ "base_model.model.model.layers.2.self_attn.v_proj.lora_B.default",
195
+ "base_model.model.model.layers.30.self_attn.v_proj.lora_A.default",
196
+ "base_model.model.model.layers.28.self_attn.q_proj.lora_A.default",
197
+ "base_model.model.model.layers.2.self_attn.q_proj.base_layer",
198
+ "base_model.model.model.layers.6.self_attn.v_proj.lora_B.default",
199
+ "base_model.model.model.layers.16.self_attn.q_proj.lora_A.default",
200
+ "base_model.model.model.layers.23.self_attn.v_proj.base_layer",
201
+ "base_model.model.model.layers.30.self_attn.q_proj.lora_A.default",
202
+ "base_model.model.model.layers.1.self_attn.q_proj.lora_B.default",
203
+ "base_model.model.model.layers.15.self_attn.q_proj.lora_A.default",
204
+ "base_model.model.model.layers.15.self_attn.q_proj.base_layer",
205
+ "base_model.model.model.layers.28.self_attn.v_proj.lora_A.default",
206
+ "base_model.model.model.layers.6.self_attn.v_proj.base_layer",
207
+ "base_model.model.model.layers.27.self_attn.v_proj.base_layer",
208
+ "base_model.model.model.layers.6.self_attn.v_proj.lora_A.default",
209
+ "base_model.model.model.layers.2.self_attn.q_proj.lora_B.default",
210
+ "base_model.model.model.layers.9.self_attn.q_proj.lora_B.default",
211
+ "base_model.model.model.layers.30.self_attn.q_proj.lora_B.default",
212
+ "base_model.model.model.layers.13.self_attn.v_proj.lora_B.default",
213
+ "base_model.model.model.layers.1.self_attn.v_proj.lora_A.default",
214
+ "base_model.model.model.layers.9.self_attn.v_proj.lora_B.default"
215
+ ],
216
+ "task_type": "CAUSAL_LM",
217
+ "use_dora": false,
218
+ "use_rslora": false
219
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a4b58e9628e1e7618cee6c6bbdc0e1644d650f81426586947f67689811c1514
3
+ size 25263688
config.yaml ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model_family: llama-7b
2
+ model_path: openlm-research/open_llama_7b
3
+ LoRA:
4
+ r: 8
5
+ alpha: 32
6
+ dropout: 0.05
7
+ lr: 2.0e-05
8
+ split: WikiMIA_QA_256
9
+ data_path: lluvecwonv/WikiMIA_QA
10
+ gradient_accumulation_steps: 4
11
+ num_epochs: 10
12
+ forget_loss: grad_ascent
13
+ file_path: /root/kdu/output/openlm-research/open_llama_7b_lluvecwonv_WikiMIA_QA_WikiMIA_QA_256_logit/
14
+ unlearned_model: lluvecwonv/WikiMIA_QA_256_10
15
+ save_dir: ${model_family}/${split}_${unlearned_model}_${num_epochs}
16
+ overwrite_dir: true
17
+ weight_decay: 0.01
18
+ save_model: true
19
+ eval_while_train: false
20
+ eval_only: false
21
+ seed: 42
22
+ master_port: 18765
23
+ eval:
24
+ model_path: ${..model_path}
25
+ model_family: ${..model_family}
26
+ save_dir: ${..save_dir}
27
+ data_path: luvecwonv/WikiMIA_QA
28
+ split: ${..split}
29
+ eval_task:
30
+ - eval_log
31
+ - eval_log_forget
32
+ question_key:
33
+ - Query
34
+ - Query
35
+ answer_key:
36
+ - Answer
37
+ - Answer
38
+ generation:
39
+ max_length: 200
40
+ max_new_tokens: null
41
+ save_generated_text: true
42
+ ds_size: 300
43
+ overwrite: true
44
+ use_pretrained: false
45
+ batch_size: 4
46
+ retain_result: null
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": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
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.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
3
+ size 534194
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6bd57ce816ea441a137134f702696c762a04d3b9c1d4432f821078b2aca400e
3
+ size 6712