Hugging Face's logo

pavan01729
/
aria-finetuned_2

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
pavan01729 commited on
Commit
17bf274
•
1 Parent(s): cdc203e

Training in progress, epoch 0

Browse files
Files changed (8) hide show
  1. README.md +59 -0
  2. adapter_config.json +280 -0
  3. adapter_model.safetensors +3 -0
  4. preprocessor_config.json +21 -0
  5. special_tokens_map.json +10 -0
  6. tokenizer.model +3 -0
  7. tokenizer_config.json +27 -0
  8. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: rhymes-ai/Aria
3
+ library_name: peft
4
+ license: apache-2.0
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: aria-finetuned
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # aria-finetuned
18
+
19
+ This model is a fine-tuned version of [rhymes-ai/Aria](https://huggingface.co/rhymes-ai/Aria) on an unknown dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 16
44
+ - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.01
47
+ - training_steps: 10
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - PEFT 0.12.0
56
+ - Transformers 4.45.0
57
+ - Pytorch 2.4.0+cu121
58
+ - Datasets 2.18.0
59
+ - Tokenizers 0.20.1
adapter_config.json ADDED
@@ -0,0 +1,280 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "rhymes-ai/Aria",
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
+ "language_model.model.layers.7.self_attn.q_proj",
24
+ "language_model.model.layers.12.mlp.experts.fc2",
25
+ "language_model.model.layers.11.self_attn.o_proj",
26
+ "language_model.model.layers.1.mlp.shared_experts.gate_proj",
27
+ "language_model.model.layers.19.self_attn.v_proj",
28
+ "language_model.model.layers.8.mlp.shared_experts.gate_proj",
29
+ "language_model.model.layers.8.self_attn.q_proj",
30
+ "language_model.model.layers.11.self_attn.v_proj",
31
+ "language_model.model.layers.21.self_attn.o_proj",
32
+ "language_model.model.layers.22.mlp.experts.fc1",
33
+ "language_model.model.layers.24.mlp.experts.fc2",
34
+ "language_model.model.layers.18.mlp.shared_experts.gate_proj",
35
+ "language_model.model.layers.27.self_attn.v_proj",
36
+ "language_model.model.layers.25.self_attn.v_proj",
37
+ "language_model.model.layers.7.mlp.experts.fc2",
38
+ "language_model.model.layers.24.mlp.shared_experts.gate_proj",
39
+ "language_model.model.layers.27.mlp.experts.fc1",
40
+ "language_model.model.layers.27.mlp.shared_experts.down_proj",
41
+ "language_model.model.layers.6.mlp.experts.fc2",
42
+ "language_model.model.layers.18.self_attn.v_proj",
43
+ "language_model.model.layers.23.mlp.experts.fc2",
44
+ "language_model.model.layers.19.mlp.experts.fc2",
45
+ "language_model.model.layers.13.self_attn.k_proj",
46
+ "language_model.model.layers.21.mlp.shared_experts.down_proj",
47
+ "language_model.model.layers.4.mlp.shared_experts.gate_proj",
48
+ "language_model.model.layers.15.mlp.shared_experts.up_proj",
49
+ "language_model.model.layers.26.self_attn.k_proj",
50
+ "language_model.model.layers.19.self_attn.o_proj",
51
+ "language_model.model.layers.25.mlp.shared_experts.gate_proj",
52
+ "language_model.model.layers.15.mlp.shared_experts.gate_proj",
53
+ "language_model.model.layers.22.mlp.shared_experts.up_proj",
54
+ "language_model.model.layers.15.mlp.experts.fc1",
55
+ "language_model.model.layers.25.self_attn.q_proj",
56
+ "language_model.model.layers.11.self_attn.q_proj",
57
+ "language_model.model.layers.6.mlp.shared_experts.up_proj",
58
+ "language_model.model.layers.14.mlp.shared_experts.gate_proj",
59
+ "language_model.model.layers.5.mlp.shared_experts.down_proj",
60
+ "language_model.model.layers.13.mlp.experts.fc2",
61
+ "language_model.model.layers.14.self_attn.q_proj",
62
+ "language_model.model.layers.26.mlp.shared_experts.down_proj",
63
+ "language_model.model.layers.26.mlp.shared_experts.up_proj",
64
+ "language_model.model.layers.8.mlp.experts.fc1",
65
+ "language_model.model.layers.23.mlp.shared_experts.gate_proj",
66
+ "language_model.model.layers.8.mlp.shared_experts.down_proj",
67
+ "language_model.model.layers.27.mlp.shared_experts.up_proj",
68
+ "language_model.model.layers.20.mlp.shared_experts.up_proj",
69
+ "language_model.model.layers.24.self_attn.q_proj",
70
+ "language_model.model.layers.26.mlp.shared_experts.gate_proj",
71
+ "language_model.model.layers.20.mlp.shared_experts.down_proj",
72
+ "language_model.model.layers.20.mlp.experts.fc1",
73
+ "language_model.model.layers.17.mlp.shared_experts.up_proj",
74
+ "language_model.model.layers.22.self_attn.v_proj",
75
+ "language_model.model.layers.6.mlp.shared_experts.gate_proj",
76
+ "language_model.model.layers.23.self_attn.o_proj",
77
+ "language_model.model.layers.5.mlp.shared_experts.gate_proj",
78
+ "language_model.model.layers.11.mlp.shared_experts.down_proj",
79
+ "language_model.model.layers.7.self_attn.o_proj",
80
+ "language_model.model.layers.17.self_attn.v_proj",
81
+ "language_model.model.layers.9.self_attn.k_proj",
82
+ "language_model.model.layers.21.mlp.experts.fc2",
83
+ "language_model.model.layers.22.mlp.shared_experts.gate_proj",
84
+ "language_model.model.layers.16.self_attn.o_proj",
85
+ "language_model.model.layers.10.self_attn.q_proj",
86
+ "language_model.model.layers.14.self_attn.o_proj",
87
+ "language_model.model.layers.24.self_attn.k_proj",
88
+ "language_model.lm_head",
89
+ "language_model.model.layers.4.self_attn.q_proj",
90
+ "language_model.model.layers.3.mlp.experts.fc1",
91
+ "language_model.model.layers.23.mlp.shared_experts.down_proj",
92
+ "language_model.model.layers.15.self_attn.k_proj",
93
+ "language_model.model.layers.24.mlp.shared_experts.down_proj",
94
+ "language_model.model.layers.0.self_attn.k_proj",
95
+ "language_model.model.layers.3.mlp.shared_experts.gate_proj",
96
+ "language_model.model.layers.14.mlp.experts.fc1",
97
+ "language_model.model.layers.11.mlp.shared_experts.gate_proj",
98
+ "language_model.model.layers.12.mlp.shared_experts.down_proj",
99
+ "language_model.model.layers.7.mlp.experts.fc1",
100
+ "language_model.model.layers.24.self_attn.o_proj",
101
+ "language_model.model.layers.15.mlp.experts.fc2",
102
+ "language_model.model.layers.8.self_attn.v_proj",
103
+ "language_model.model.layers.5.self_attn.q_proj",
104
+ "language_model.model.layers.17.mlp.shared_experts.down_proj",
105
+ "language_model.model.layers.24.self_attn.v_proj",
106
+ "language_model.model.layers.1.mlp.experts.fc2",
107
+ "language_model.model.layers.4.mlp.shared_experts.down_proj",
108
+ "language_model.model.layers.5.mlp.experts.fc1",
109
+ "language_model.model.layers.8.mlp.shared_experts.up_proj",
110
+ "language_model.model.layers.6.self_attn.v_proj",
111
+ "language_model.model.layers.11.mlp.experts.fc1",
112
+ "language_model.model.layers.17.mlp.experts.fc1",
113
+ "language_model.model.layers.24.mlp.experts.fc1",
114
+ "language_model.model.layers.26.self_attn.o_proj",
115
+ "language_model.model.layers.16.mlp.experts.fc1",
116
+ "language_model.model.layers.18.self_attn.o_proj",
117
+ "language_model.model.layers.11.mlp.shared_experts.up_proj",
118
+ "language_model.model.layers.9.mlp.experts.fc2",
119
+ "language_model.model.layers.14.self_attn.v_proj",
120
+ "language_model.model.layers.1.self_attn.k_proj",
121
+ "language_model.model.layers.2.mlp.shared_experts.gate_proj",
122
+ "language_model.model.layers.27.self_attn.q_proj",
123
+ "language_model.model.layers.7.mlp.shared_experts.down_proj",
124
+ "language_model.model.layers.10.mlp.shared_experts.gate_proj",
125
+ "language_model.model.layers.4.mlp.shared_experts.up_proj",
126
+ "language_model.model.layers.10.self_attn.v_proj",
127
+ "language_model.model.layers.25.mlp.experts.fc1",
128
+ "language_model.model.layers.27.mlp.experts.fc2",
129
+ "language_model.model.layers.3.mlp.experts.fc2",
130
+ "language_model.model.layers.17.mlp.shared_experts.gate_proj",
131
+ "language_model.model.layers.23.mlp.shared_experts.up_proj",
132
+ "language_model.model.layers.9.self_attn.v_proj",
133
+ "language_model.model.layers.17.self_attn.o_proj",
134
+ "language_model.model.layers.23.self_attn.q_proj",
135
+ "language_model.model.layers.10.mlp.shared_experts.down_proj",
136
+ "language_model.model.layers.12.mlp.shared_experts.up_proj",
137
+ "language_model.model.layers.7.self_attn.v_proj",
138
+ "language_model.model.layers.18.mlp.experts.fc2",
139
+ "language_model.model.layers.22.mlp.experts.fc2",
140
+ "language_model.model.layers.12.mlp.experts.fc1",
141
+ "language_model.model.layers.19.mlp.shared_experts.up_proj",
142
+ "language_model.model.layers.18.self_attn.q_proj",
143
+ "language_model.model.layers.14.mlp.shared_experts.up_proj",
144
+ "language_model.model.layers.8.mlp.experts.fc2",
145
+ "language_model.model.layers.1.self_attn.o_proj",
146
+ "language_model.model.layers.2.mlp.experts.fc1",
147
+ "language_model.model.layers.17.self_attn.k_proj",
148
+ "language_model.model.layers.1.mlp.experts.fc1",
149
+ "language_model.model.layers.19.mlp.experts.fc1",
150
+ "language_model.model.layers.15.self_attn.o_proj",
151
+ "language_model.model.layers.25.self_attn.k_proj",
152
+ "language_model.model.layers.25.mlp.shared_experts.down_proj",
153
+ "language_model.model.layers.0.mlp.shared_experts.up_proj",
154
+ "language_model.model.layers.3.self_attn.k_proj",
155
+ "language_model.model.layers.0.self_attn.v_proj",
156
+ "language_model.model.layers.7.mlp.shared_experts.up_proj",
157
+ "language_model.model.layers.26.self_attn.v_proj",
158
+ "language_model.model.layers.2.mlp.shared_experts.up_proj",
159
+ "language_model.model.layers.0.mlp.shared_experts.down_proj",
160
+ "language_model.model.layers.19.mlp.shared_experts.down_proj",
161
+ "language_model.model.layers.10.mlp.shared_experts.up_proj",
162
+ "language_model.model.layers.27.self_attn.o_proj",
163
+ "language_model.model.layers.25.mlp.shared_experts.up_proj",
164
+ "language_model.model.layers.18.mlp.experts.fc1",
165
+ "language_model.model.layers.14.mlp.shared_experts.down_proj",
166
+ "language_model.model.layers.16.self_attn.v_proj",
167
+ "language_model.model.layers.2.self_attn.k_proj",
168
+ "language_model.model.layers.22.self_attn.k_proj",
169
+ "language_model.model.layers.21.mlp.experts.fc1",
170
+ "language_model.model.layers.11.mlp.experts.fc2",
171
+ "language_model.model.layers.12.self_attn.o_proj",
172
+ "language_model.model.layers.2.self_attn.o_proj",
173
+ "language_model.model.layers.14.mlp.experts.fc2",
174
+ "language_model.model.layers.21.self_attn.q_proj",
175
+ "language_model.model.layers.19.self_attn.q_proj",
176
+ "language_model.model.layers.7.self_attn.k_proj",
177
+ "language_model.model.layers.9.mlp.shared_experts.gate_proj",
178
+ "language_model.model.layers.13.self_attn.v_proj",
179
+ "language_model.model.layers.13.mlp.shared_experts.gate_proj",
180
+ "language_model.model.layers.13.self_attn.q_proj",
181
+ "language_model.model.layers.16.mlp.shared_experts.gate_proj",
182
+ "language_model.model.layers.1.mlp.shared_experts.up_proj",
183
+ "language_model.model.layers.20.self_attn.k_proj",
184
+ "language_model.model.layers.2.mlp.experts.fc2",
185
+ "language_model.model.layers.5.self_attn.v_proj",
186
+ "language_model.model.layers.18.mlp.shared_experts.up_proj",
187
+ "language_model.model.layers.1.self_attn.v_proj",
188
+ "language_model.model.layers.10.mlp.experts.fc2",
189
+ "language_model.model.layers.13.self_attn.o_proj",
190
+ "language_model.model.layers.2.self_attn.q_proj",
191
+ "language_model.model.layers.4.self_attn.k_proj",
192
+ "language_model.model.layers.12.self_attn.q_proj",
193
+ "language_model.model.layers.19.mlp.shared_experts.gate_proj",
194
+ "language_model.model.layers.18.self_attn.k_proj",
195
+ "language_model.model.layers.11.self_attn.k_proj",
196
+ "language_model.model.layers.27.mlp.shared_experts.gate_proj",
197
+ "language_model.model.layers.1.self_attn.q_proj",
198
+ "language_model.model.layers.16.self_attn.k_proj",
199
+ "language_model.model.layers.13.mlp.experts.fc1",
200
+ "language_model.model.layers.26.mlp.experts.fc2",
201
+ "language_model.model.layers.23.self_attn.k_proj",
202
+ "language_model.model.layers.0.mlp.experts.fc1",
203
+ "language_model.model.layers.3.self_attn.o_proj",
204
+ "language_model.model.layers.2.self_attn.v_proj",
205
+ "language_model.model.layers.14.self_attn.k_proj",
206
+ "language_model.model.layers.16.mlp.shared_experts.up_proj",
207
+ "language_model.model.layers.22.mlp.shared_experts.down_proj",
208
+ "language_model.model.layers.4.mlp.experts.fc2",
209
+ "language_model.model.layers.23.self_attn.v_proj",
210
+ "language_model.model.layers.19.self_attn.k_proj",
211
+ "language_model.model.layers.23.mlp.experts.fc1",
212
+ "language_model.model.layers.13.mlp.shared_experts.down_proj",
213
+ "language_model.model.layers.0.self_attn.q_proj",
214
+ "language_model.model.layers.12.mlp.shared_experts.gate_proj",
215
+ "language_model.model.layers.25.self_attn.o_proj",
216
+ "language_model.model.layers.9.mlp.shared_experts.up_proj",
217
+ "language_model.model.layers.21.mlp.shared_experts.gate_proj",
218
+ "language_model.model.layers.6.self_attn.o_proj",
219
+ "language_model.model.layers.25.mlp.experts.fc2",
220
+ "language_model.model.layers.4.self_attn.o_proj",
221
+ "language_model.model.layers.8.self_attn.o_proj",
222
+ "language_model.model.layers.13.mlp.shared_experts.up_proj",
223
+ "language_model.model.layers.2.mlp.shared_experts.down_proj",
224
+ "language_model.model.layers.4.self_attn.v_proj",
225
+ "language_model.model.layers.6.self_attn.k_proj",
226
+ "language_model.model.layers.10.self_attn.k_proj",
227
+ "language_model.model.layers.3.self_attn.v_proj",
228
+ "language_model.model.layers.20.self_attn.v_proj",
229
+ "language_model.model.layers.8.self_attn.k_proj",
230
+ "language_model.model.layers.9.mlp.experts.fc1",
231
+ "language_model.model.layers.5.mlp.shared_experts.up_proj",
232
+ "language_model.model.layers.26.mlp.experts.fc1",
233
+ "language_model.model.layers.16.mlp.shared_experts.down_proj",
234
+ "language_model.model.layers.17.mlp.experts.fc2",
235
+ "language_model.model.layers.15.mlp.shared_experts.down_proj",
236
+ "language_model.model.layers.3.mlp.shared_experts.down_proj",
237
+ "language_model.model.layers.10.mlp.experts.fc1",
238
+ "language_model.model.layers.22.self_attn.q_proj",
239
+ "language_model.model.layers.20.self_attn.o_proj",
240
+ "language_model.model.layers.9.mlp.shared_experts.down_proj",
241
+ "language_model.model.layers.17.self_attn.q_proj",
242
+ "language_model.model.layers.21.self_attn.v_proj",
243
+ "language_model.model.layers.22.self_attn.o_proj",
244
+ "language_model.model.layers.15.self_attn.v_proj",
245
+ "language_model.model.layers.10.self_attn.o_proj",
246
+ "language_model.model.layers.4.mlp.experts.fc1",
247
+ "language_model.model.layers.5.mlp.experts.fc2",
248
+ "language_model.model.layers.5.self_attn.o_proj",
249
+ "language_model.model.layers.26.self_attn.q_proj",
250
+ "language_model.model.layers.20.mlp.shared_experts.gate_proj",
251
+ "language_model.model.layers.0.mlp.experts.fc2",
252
+ "language_model.model.layers.1.mlp.shared_experts.down_proj",
253
+ "language_model.model.layers.6.mlp.shared_experts.down_proj",
254
+ "language_model.model.layers.20.self_attn.q_proj",
255
+ "language_model.model.layers.21.self_attn.k_proj",
256
+ "language_model.model.layers.3.mlp.shared_experts.up_proj",
257
+ "language_model.model.layers.7.mlp.shared_experts.gate_proj",
258
+ "language_model.model.layers.5.self_attn.k_proj",
259
+ "language_model.model.layers.15.self_attn.q_proj",
260
+ "language_model.model.layers.6.self_attn.q_proj",
261
+ "language_model.model.layers.0.mlp.shared_experts.gate_proj",
262
+ "language_model.model.layers.6.mlp.experts.fc1",
263
+ "language_model.model.layers.16.self_attn.q_proj",
264
+ "language_model.model.layers.24.mlp.shared_experts.up_proj",
265
+ "language_model.model.layers.9.self_attn.o_proj",
266
+ "language_model.model.layers.21.mlp.shared_experts.up_proj",
267
+ "language_model.model.layers.12.self_attn.k_proj",
268
+ "language_model.model.layers.9.self_attn.q_proj",
269
+ "language_model.model.layers.3.self_attn.q_proj",
270
+ "language_model.model.layers.18.mlp.shared_experts.down_proj",
271
+ "language_model.model.layers.20.mlp.experts.fc2",
272
+ "language_model.model.layers.12.self_attn.v_proj",
273
+ "language_model.model.layers.16.mlp.experts.fc2",
274
+ "language_model.model.layers.0.self_attn.o_proj",
275
+ "language_model.model.layers.27.self_attn.k_proj"
276
+ ],
277
+ "task_type": "CAUSAL_LM",
278
+ "use_dora": false,
279
+ "use_rslora": false
280
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00924994f45fa56beaeb029a1cf9491971c5790c304c7b148b1eacf8903b2b74
3
+ size 308744888
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_transform": null,
3
+ "auto_map": {
4
+ "AutoImageProcessor": "vision_processor.AriaVisionProcessor",
5
+ "AutoProcessor": "processing_aria.AriaProcessor"
6
+ },
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "AriaVisionProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "max_image_size": 980,
19
+ "min_image_size": 336,
20
+ "processor_class": "AriaProcessor"
21
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": "<unk>",
3
+ "unk_token": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e429a008ed1045d14464933311e0b3258575980efc9db4e61f368e399c719d2a
3
+ size 1696299
tokenizer_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
15
+ "bos_token": null,
16
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<fim_prefix><|img|><fim_suffix>{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
17
+ "clean_up_tokenization_spaces": false,
18
+ "eos_token": null,
19
+ "legacy": true,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": "<unk>",
22
+ "sp_model_kwargs": {},
23
+ "spaces_between_special_tokens": false,
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": "<unk>",
26
+ "use_default_system_prompt": false
27
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fda310cdf5b2939332ae414fd3d78fe11ae93884acac44b128266675865540df
3
+ size 5496