Hugging Face's logo

amd
/
Llama-3.2-90B-Vision-Instruct-FP8-KV

Safetensors
mllama
fp8
Model card Files Community
10
bowenbaoamd commited on
Commit
22bcd0c
·
verified ·
1 Parent(s): 3e3f59e

Upload folder using huggingface_hub

Browse files
Files changed (26) hide show
  1. config.json +230 -52
  2. generation_config.json +2 -1
  3. model-00001-of-00019.safetensors +2 -2
  4. model-00002-of-00019.safetensors +2 -2
  5. model-00003-of-00019.safetensors +2 -2
  6. model-00004-of-00019.safetensors +2 -2
  7. model-00005-of-00019.safetensors +2 -2
  8. model-00006-of-00019.safetensors +2 -2
  9. model-00007-of-00019.safetensors +2 -2
  10. model-00008-of-00019.safetensors +2 -2
  11. model-00009-of-00019.safetensors +2 -2
  12. model-00010-of-00019.safetensors +2 -2
  13. model-00011-of-00019.safetensors +2 -2
  14. model-00012-of-00019.safetensors +2 -2
  15. model-00013-of-00019.safetensors +2 -2
  16. model-00014-of-00019.safetensors +2 -2
  17. model-00015-of-00019.safetensors +2 -2
  18. model-00016-of-00019.safetensors +2 -2
  19. model-00017-of-00019.safetensors +2 -2
  20. model-00018-of-00019.safetensors +2 -2
  21. model-00019-of-00019.safetensors +2 -2
  22. model.safetensors.index.json +0 -0
  23. preprocessor_config.json +25 -0
  24. special_tokens_map.json +1 -7
  25. tokenizer.json +2 -2
  26. tokenizer_config.json +3 -2
config.json CHANGED
@@ -1,46 +1,10 @@
1
  {
 
2
  "architectures": [
3
- "MllamaForCausalLM"
4
  ],
5
- "bos_token_id": 128000,
6
- "cross_attention_layers": [
7
- 3,
8
- 8,
9
- 13,
10
- 18,
11
- 23,
12
- 28,
13
- 33,
14
- 38,
15
- 43,
16
- 48,
17
- 53,
18
- 58,
19
- 63,
20
- 68,
21
- 73,
22
- 78,
23
- 83,
24
- 88,
25
- 93,
26
- 98
27
- ],
28
- "dropout": 0,
29
- "eos_token_id": [
30
- 128001,
31
- 128008,
32
- 128009
33
- ],
34
- "hidden_act": "silu",
35
- "hidden_size": 8192,
36
- "initializer_range": 0.02,
37
- "intermediate_size": 28672,
38
- "max_position_embeddings": 131072,
39
- "model_type": "mllama_text_model",
40
- "num_attention_heads": 64,
41
- "num_hidden_layers": 100,
42
- "num_key_value_heads": 8,
43
- "pad_token_id": 128004,
44
  "quantization_config": {
45
  "activation_scheme": "static",
46
  "ignored_layers": [
@@ -49,18 +13,232 @@
49
  "kv_cache_scheme": "static",
50
  "quant_method": "fp8"
51
  },
52
- "rms_norm_eps": 1e-05,
53
- "rope_scaling": {
54
- "factor": 8.0,
55
- "high_freq_factor": 4.0,
56
- "low_freq_factor": 1.0,
57
- "original_max_position_embeddings": 8192,
58
- "rope_type": "llama3"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
  },
60
- "rope_theta": 500000.0,
61
- "tie_word_embeddings": false,
62
  "torch_dtype": "bfloat16",
63
- "transformers_version": "4.45.1",
64
- "use_cache": true,
65
- "vocab_size": 128256
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
  }
 
1
  {
2
+ "_name_or_path": "/model_path/meta-llama/Llama-3.2-90B-Vision-Instruct/",
3
  "architectures": [
4
+ "MllamaForConditionalGeneration"
5
  ],
6
+ "image_token_index": 128256,
7
+ "model_type": "mllama",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "quantization_config": {
9
  "activation_scheme": "static",
10
  "ignored_layers": [
 
13
  "kv_cache_scheme": "static",
14
  "quant_method": "fp8"
15
  },
16
+ "text_config": {
17
+ "_name_or_path": "",
18
+ "add_cross_attention": false,
19
+ "architectures": null,
20
+ "bad_words_ids": null,
21
+ "begin_suppress_tokens": null,
22
+ "bos_token_id": 128000,
23
+ "chunk_size_feed_forward": 0,
24
+ "cross_attention_hidden_size": null,
25
+ "cross_attention_layers": [
26
+ 3,
27
+ 8,
28
+ 13,
29
+ 18,
30
+ 23,
31
+ 28,
32
+ 33,
33
+ 38,
34
+ 43,
35
+ 48,
36
+ 53,
37
+ 58,
38
+ 63,
39
+ 68,
40
+ 73,
41
+ 78,
42
+ 83,
43
+ 88,
44
+ 93,
45
+ 98
46
+ ],
47
+ "decoder_start_token_id": null,
48
+ "diversity_penalty": 0.0,
49
+ "do_sample": false,
50
+ "dropout": 0,
51
+ "early_stopping": false,
52
+ "encoder_no_repeat_ngram_size": 0,
53
+ "eos_token_id": [
54
+ 128001,
55
+ 128008,
56
+ 128009
57
+ ],
58
+ "exponential_decay_length_penalty": null,
59
+ "finetuning_task": null,
60
+ "forced_bos_token_id": null,
61
+ "forced_eos_token_id": null,
62
+ "hidden_act": "silu",
63
+ "hidden_size": 8192,
64
+ "id2label": {
65
+ "0": "LABEL_0",
66
+ "1": "LABEL_1"
67
+ },
68
+ "initializer_range": 0.02,
69
+ "intermediate_size": 28672,
70
+ "is_decoder": false,
71
+ "is_encoder_decoder": false,
72
+ "label2id": {
73
+ "LABEL_0": 0,
74
+ "LABEL_1": 1
75
+ },
76
+ "length_penalty": 1.0,
77
+ "max_length": 20,
78
+ "max_position_embeddings": 131072,
79
+ "min_length": 0,
80
+ "model_type": "mllama_text_model",
81
+ "no_repeat_ngram_size": 0,
82
+ "num_attention_heads": 64,
83
+ "num_beam_groups": 1,
84
+ "num_beams": 1,
85
+ "num_hidden_layers": 100,
86
+ "num_key_value_heads": 8,
87
+ "num_return_sequences": 1,
88
+ "output_attentions": false,
89
+ "output_hidden_states": false,
90
+ "output_scores": false,
91
+ "pad_token_id": 128004,
92
+ "prefix": null,
93
+ "problem_type": null,
94
+ "pruned_heads": {},
95
+ "remove_invalid_values": false,
96
+ "repetition_penalty": 1.0,
97
+ "return_dict": true,
98
+ "return_dict_in_generate": false,
99
+ "rms_norm_eps": 1e-05,
100
+ "rope_scaling": {
101
+ "factor": 8.0,
102
+ "high_freq_factor": 4.0,
103
+ "low_freq_factor": 1.0,
104
+ "original_max_position_embeddings": 8192,
105
+ "rope_type": "llama3"
106
+ },
107
+ "rope_theta": 500000.0,
108
+ "sep_token_id": null,
109
+ "suppress_tokens": null,
110
+ "task_specific_params": null,
111
+ "temperature": 1.0,
112
+ "tf_legacy_loss": false,
113
+ "tie_encoder_decoder": false,
114
+ "tie_word_embeddings": false,
115
+ "tokenizer_class": null,
116
+ "top_k": 50,
117
+ "top_p": 1.0,
118
+ "torch_dtype": "bfloat16",
119
+ "torchscript": false,
120
+ "typical_p": 1.0,
121
+ "use_bfloat16": false,
122
+ "use_cache": true,
123
+ "vocab_size": 128256
124
  },
 
 
125
  "torch_dtype": "bfloat16",
126
+ "transformers_version": "4.45.2",
127
+ "vision_config": {
128
+ "_name_or_path": "",
129
+ "add_cross_attention": false,
130
+ "architectures": null,
131
+ "attention_heads": 16,
132
+ "bad_words_ids": null,
133
+ "begin_suppress_tokens": null,
134
+ "bos_token_id": null,
135
+ "chunk_size_feed_forward": 0,
136
+ "cross_attention_hidden_size": null,
137
+ "decoder_start_token_id": null,
138
+ "diversity_penalty": 0.0,
139
+ "do_sample": false,
140
+ "early_stopping": false,
141
+ "encoder_no_repeat_ngram_size": 0,
142
+ "eos_token_id": null,
143
+ "exponential_decay_length_penalty": null,
144
+ "finetuning_task": null,
145
+ "forced_bos_token_id": null,
146
+ "forced_eos_token_id": null,
147
+ "hidden_act": "gelu",
148
+ "hidden_size": 1280,
149
+ "id2label": {
150
+ "0": "LABEL_0",
151
+ "1": "LABEL_1"
152
+ },
153
+ "image_size": 560,
154
+ "initializer_range": 0.02,
155
+ "intermediate_layers_indices": [
156
+ 3,
157
+ 7,
158
+ 15,
159
+ 23,
160
+ 30
161
+ ],
162
+ "intermediate_size": 5120,
163
+ "is_decoder": false,
164
+ "is_encoder_decoder": false,
165
+ "label2id": {
166
+ "LABEL_0": 0,
167
+ "LABEL_1": 1
168
+ },
169
+ "length_penalty": 1.0,
170
+ "max_length": 20,
171
+ "max_num_tiles": 4,
172
+ "min_length": 0,
173
+ "model_type": "mllama_vision_model",
174
+ "no_repeat_ngram_size": 0,
175
+ "norm_eps": 1e-05,
176
+ "num_beam_groups": 1,
177
+ "num_beams": 1,
178
+ "num_channels": 3,
179
+ "num_global_layers": 8,
180
+ "num_hidden_layers": 32,
181
+ "num_return_sequences": 1,
182
+ "output_attentions": false,
183
+ "output_hidden_states": false,
184
+ "output_scores": false,
185
+ "pad_token_id": null,
186
+ "patch_size": 14,
187
+ "prefix": null,
188
+ "problem_type": null,
189
+ "pruned_heads": {},
190
+ "remove_invalid_values": false,
191
+ "repetition_penalty": 1.0,
192
+ "return_dict": true,
193
+ "return_dict_in_generate": false,
194
+ "sep_token_id": null,
195
+ "supported_aspect_ratios": [
196
+ [
197
+ 1,
198
+ 1
199
+ ],
200
+ [
201
+ 1,
202
+ 2
203
+ ],
204
+ [
205
+ 1,
206
+ 3
207
+ ],
208
+ [
209
+ 1,
210
+ 4
211
+ ],
212
+ [
213
+ 2,
214
+ 1
215
+ ],
216
+ [
217
+ 2,
218
+ 2
219
+ ],
220
+ [
221
+ 3,
222
+ 1
223
+ ],
224
+ [
225
+ 4,
226
+ 1
227
+ ]
228
+ ],
229
+ "suppress_tokens": null,
230
+ "task_specific_params": null,
231
+ "temperature": 1.0,
232
+ "tf_legacy_loss": false,
233
+ "tie_encoder_decoder": false,
234
+ "tie_word_embeddings": true,
235
+ "tokenizer_class": null,
236
+ "top_k": 50,
237
+ "top_p": 1.0,
238
+ "torch_dtype": "bfloat16",
239
+ "torchscript": false,
240
+ "typical_p": 1.0,
241
+ "use_bfloat16": false,
242
+ "vision_output_dim": 7680
243
+ }
244
  }
generation_config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "bos_token_id": 128000,
3
  "do_sample": true,
4
  "eos_token_id": [
@@ -9,5 +10,5 @@
9
  "pad_token_id": 128004,
10
  "temperature": 0.6,
11
  "top_p": 0.9,
12
- "transformers_version": "4.45.1"
13
  }
 
1
  {
2
+ "attn_implementation": "eager",
3
  "bos_token_id": 128000,
4
  "do_sample": true,
5
  "eos_token_id": [
 
10
  "pad_token_id": 128004,
11
  "temperature": 0.6,
12
  "top_p": 0.9,
13
+ "transformers_version": "4.45.2"
14
  }
model-00001-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bd0a1fcc14896bb9b5c630e874e2df046065835bcdfbe557d9d8dff5dd85768
3
- size 4819511324
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5633ead602ca8cd3f5603a1b352f916379f37bf7c92a9454a73c91b3d425bc4
3
+ size 4835349758
model-00002-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:182efcf174d3e7f0c0aa573c1aebefc2c63a2f98760d89592298c80477ab2930
3
- size 4983028204
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c42c5c10a552ab129ffa92fc6a5a2b07a639920d9497f9d87ed52452a90e9d
3
+ size 4983046716
model-00003-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e95e09a2ba51f63651d40488135675f49492593e0e940d87fd8dc1ca69d870c5
3
- size 4899126616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8237d40f2800f714a402d70c2e4bcdeb783e774b0af83996e17abdf27adacd14
3
+ size 4899128696
model-00004-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d7a829e6b0b4ee3351485349a605608a1dba6103f83150c63e1e833cdb9e166
3
- size 4899159732
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81b197e264111aa05d4ffc5653659cc7bd0d0e35cf42da153d388225f6709844
3
+ size 4899179408
model-00005-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fada21ac6d0cc5850b8a2e4f567a7f0bd9786b383440204a97b8119c3b3e0bf
3
- size 4899159724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c7dfa55ab23d7b2137a76d9f869f72c2e57635eca9971099e2f32021ab86cb
3
+ size 4899145404
model-00006-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2aab0c845d1df5f5539cc24ab2bf3bd7123551a89daa3150a8780fbfb1df5772
3
- size 4983044812
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ae76eab5c8ec24d102280131ca0e5b08dfc5b13a1b365dfeb794e018f4d241e
3
+ size 4983046860
model-00007-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c69289f2379fa24b4fb90ef41979f58eec7f59a7eba9110710c60be67fd058b3
3
- size 4899126632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b75365ead7409e54bcdedb9796a50fcb99b206073e7f5dede2ff34761c4ff05
3
+ size 4899128768
model-00008-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8eb8aaa066f144dbd2de612b93e0e3a217dcbca6f7e8d3181ba8d47104a73707
3
- size 4899177160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5843387d5c61880345dcb96dab915373df5a32908f0a9638bbe934d26c6e2605
3
+ size 4899161900
model-00009-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67fee5c31901b59cf6017a11e3fb2c15b25c333b33dfec3fe90d65f61354e2a2
3
- size 4899143244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0cce284a3fc84b43351440fc4a09103469bf0bfbef10d6aa0c548acbbdaa5d7
3
+ size 4899161900
model-00010-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9980ef9ec00e1aa090e923da5c8947b9b902d71777e2610b0340613b8a6a4ee
3
- size 4983044820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9ac707f663b09db5853b037fba63e8e7163c3cbc914ef4c9857572dea636ee
3
+ size 4983047080
model-00011-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd28304dd794e6df10364c1048776e7af227d170bc86803985017b2b31ae62ab
3
- size 4899126640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7969b5046cd09601629a89b2264208a1f95ca0bba766331b68869a7d99d12f2
3
+ size 4899146040
model-00012-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:151dd6e67a528f542ebccca6a811c03bbc13b2079373729d08c2e0ac56035625
3
- size 4899159724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43786ea2bcb24de175b1c56ccb692f07d8759e616d1e66072be7b2be3d1789c7
3
+ size 4899145404
model-00013-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e741ab629c5a87d89122fde5b724bd2a110453df9a58ad2701f505c5925f1c8d
3
- size 4899159724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e06841c6be0dced0db1961b53c76619f53b5fee463525adc8427d67d1f85bc15
3
+ size 4899161908
model-00014-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63408a09613132b527a1f4292151080c5fbc9d46bd0a25ae4772a162cdfb3097
3
- size 4983045008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49c43d251ef8d3945971db6e0e06f4505c2e2fb18293c1803ac4f457fad588f
3
+ size 4983046852
model-00015-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec8872fdb2c24a07fb930f4eb0434647225e4ae432af373c8fdfedef4be6b9c6
3
- size 4899143864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e6f13ab0b56631f154111e2a11b875a8f6fb37d1c41f595bd330bd568f1ce40
3
+ size 4899128768
model-00016-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b593cd8b74dc66ed7eed45303164f8f9285d15caded44ce42b0b746cacf890a
3
- size 4899143244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da9a88b14df4918329ef19a89938a3a444477281af915101b483508391af5c5f
3
+ size 4899161900
model-00017-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a98024b3b3c5b5815babc4dbd03972fa105f60dac44e9cde9cc7ef4376e1a93
3
- size 4899159732
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e68b8b71dfb0dcf9222275e8db0f69d02ee21b03bc6e7e4fec6427ad8ca82b9
3
+ size 4899179400
model-00018-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52aa8f6213e3c18cd489dd723bfcf9a574a319d77317171644b4113fcaf253de
3
- size 4127387820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cde51ac7c61430a36ae18caac5f0b5491bb005f6f2af21807ec3ff1540454f8
3
+ size 4983030364
model-00019-of-00019.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c845d7ccba30e2e0eb8ab20aa313d5ed45dca6634e214a62ed323b70462fa828
3
- size 2101346432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f13ee3f4daeec8770d7996f5af786be664c899fdf6fc854ea89a00214bc9683
3
+ size 3082882248
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_processor_type": "MllamaImageProcessor",
13
+ "image_std": [
14
+ 0.26862954,
15
+ 0.26130258,
16
+ 0.27577711
17
+ ],
18
+ "max_image_tiles": 4,
19
+ "resample": 2,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 560,
23
+ "width": 560
24
+ }
25
+ }
special_tokens_map.json CHANGED
@@ -13,11 +13,5 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": {
17
- "content": "<|finetune_right_pad_id|>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
  }
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<|eot_id|>"
 
 
 
 
 
 
17
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47be6519609d58a5f29b3497045b8a2798d0d0978955ea90a893ad80e2ecdd4d
3
- size 17208880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2950f10d620c6db4032082fe810ee88b29d8cda2caabfbcbf30f40eec988741c
3
+ size 17210350
tokenizer_config.json CHANGED
@@ -2065,7 +2065,8 @@
2065
  "input_ids",
2066
  "attention_mask"
2067
  ],
2068
- "model_max_length": 131072,
2069
- "pad_token": "<|finetune_right_pad_id|>",
 
2070
  "tokenizer_class": "PreTrainedTokenizerFast"
2071
  }
 
2065
  "input_ids",
2066
  "attention_mask"
2067
  ],
2068
+ "model_max_length": 512,
2069
+ "pad_token": "<|eot_id|>",
2070
+ "padding_side": "left",
2071
  "tokenizer_class": "PreTrainedTokenizerFast"
2072
  }