Hugging Face's logo

teowu
/
mplug_owl2_7b_448_qinstruct_preview_v0.1

Transformers
PyTorch
English
mplug_owl2
Inference Endpoints
Model card Files Community
teowu commited on
Commit
909ac64
•
1 Parent(s): d6d3025

Upload folder using huggingface_hub

Browse files
Files changed (39) hide show
  1. .ipynb_checkpoints/config-checkpoint.json +176 -0
  2. config.json +176 -0
  3. preprocessor_config.json +20 -0
  4. pytorch_model-1-of-33.bin +3 -0
  5. pytorch_model-10-of-33.bin +3 -0
  6. pytorch_model-11-of-33.bin +3 -0
  7. pytorch_model-12-of-33.bin +3 -0
  8. pytorch_model-13-of-33.bin +3 -0
  9. pytorch_model-14-of-33.bin +3 -0
  10. pytorch_model-15-of-33.bin +3 -0
  11. pytorch_model-16-of-33.bin +3 -0
  12. pytorch_model-17-of-33.bin +3 -0
  13. pytorch_model-18-of-33.bin +3 -0
  14. pytorch_model-19-of-33.bin +3 -0
  15. pytorch_model-2-of-33.bin +3 -0
  16. pytorch_model-20-of-33.bin +3 -0
  17. pytorch_model-21-of-33.bin +3 -0
  18. pytorch_model-22-of-33.bin +3 -0
  19. pytorch_model-23-of-33.bin +3 -0
  20. pytorch_model-24-of-33.bin +3 -0
  21. pytorch_model-25-of-33.bin +3 -0
  22. pytorch_model-26-of-33.bin +3 -0
  23. pytorch_model-27-of-33.bin +3 -0
  24. pytorch_model-28-of-33.bin +3 -0
  25. pytorch_model-29-of-33.bin +3 -0
  26. pytorch_model-3-of-33.bin +3 -0
  27. pytorch_model-30-of-33.bin +3 -0
  28. pytorch_model-31-of-33.bin +3 -0
  29. pytorch_model-32-of-33.bin +3 -0
  30. pytorch_model-33-of-33.bin +3 -0
  31. pytorch_model-4-of-33.bin +3 -0
  32. pytorch_model-5-of-33.bin +3 -0
  33. pytorch_model-6-of-33.bin +3 -0
  34. pytorch_model-7-of-33.bin +3 -0
  35. pytorch_model-8-of-33.bin +3 -0
  36. pytorch_model-9-of-33.bin +3 -0
  37. pytorch_model.bin.index.json +1 -0
  38. tokenizer.model +3 -0
  39. tokenizer_config.json +35 -0
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_bias": false,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "hidden_act": "silu",
6
+ "hidden_size": 4096,
7
+ "initializer_range": 0.02,
8
+ "intermediate_size": 11008,
9
+ "max_position_embeddings": 2048,
10
+ "model_type": "mplug_owl2",
11
+ "num_attention_heads": 32,
12
+ "num_hidden_layers": 32,
13
+ "num_key_value_heads": 32,
14
+ "pretraining_tp": 1,
15
+ "rms_norm_eps": 1e-06,
16
+ "rope_scaling": null,
17
+ "rope_theta": 10000.0,
18
+ "tie_word_embeddings": false,
19
+ "transformers_version": "4.28.1",
20
+ "use_cache": true,
21
+ "visual_config": {
22
+ "visual_abstractor": {
23
+ "_name_or_path": "",
24
+ "add_cross_attention": false,
25
+ "architectures": null,
26
+ "attention_probs_dropout_prob": 0.0,
27
+ "bad_words_ids": null,
28
+ "begin_suppress_tokens": null,
29
+ "bos_token_id": null,
30
+ "chunk_size_feed_forward": 0,
31
+ "cross_attention_hidden_size": null,
32
+ "decoder_start_token_id": null,
33
+ "diversity_penalty": 0.0,
34
+ "do_sample": false,
35
+ "early_stopping": false,
36
+ "encoder_hidden_size": 1024,
37
+ "encoder_no_repeat_ngram_size": 0,
38
+ "eos_token_id": null,
39
+ "exponential_decay_length_penalty": null,
40
+ "finetuning_task": null,
41
+ "forced_bos_token_id": null,
42
+ "forced_eos_token_id": null,
43
+ "grid_size": 32,
44
+ "hidden_size": 1024,
45
+ "id2label": {
46
+ "0": "LABEL_0",
47
+ "1": "LABEL_1"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": 2816,
51
+ "is_decoder": false,
52
+ "is_encoder_decoder": false,
53
+ "label2id": {
54
+ "LABEL_0": 0,
55
+ "LABEL_1": 1
56
+ },
57
+ "layer_norm_eps": 1e-06,
58
+ "length_penalty": 1.0,
59
+ "max_length": 20,
60
+ "min_length": 0,
61
+ "model_type": "mplug_owl_visual_abstract",
62
+ "no_repeat_ngram_size": 0,
63
+ "num_attention_heads": 16,
64
+ "num_beam_groups": 1,
65
+ "num_beams": 1,
66
+ "num_hidden_layers": 6,
67
+ "num_learnable_queries": 64,
68
+ "num_return_sequences": 1,
69
+ "output_attentions": false,
70
+ "output_hidden_states": false,
71
+ "output_scores": false,
72
+ "pad_token_id": null,
73
+ "prefix": null,
74
+ "problem_type": null,
75
+ "pruned_heads": {},
76
+ "remove_invalid_values": false,
77
+ "repetition_penalty": 1.0,
78
+ "return_dict": true,
79
+ "return_dict_in_generate": false,
80
+ "sep_token_id": null,
81
+ "suppress_tokens": null,
82
+ "task_specific_params": null,
83
+ "temperature": 1.0,
84
+ "tf_legacy_loss": false,
85
+ "tie_encoder_decoder": false,
86
+ "tie_word_embeddings": true,
87
+ "tokenizer_class": null,
88
+ "top_k": 50,
89
+ "top_p": 1.0,
90
+ "torch_dtype": null,
91
+ "torchscript": false,
92
+ "transformers_version": "4.28.1",
93
+ "typical_p": 1.0,
94
+ "use_bfloat16": false
95
+ },
96
+ "visual_model": {
97
+ "_name_or_path": "",
98
+ "add_cross_attention": false,
99
+ "architectures": null,
100
+ "attention_dropout": 0.0,
101
+ "bad_words_ids": null,
102
+ "begin_suppress_tokens": null,
103
+ "bos_token_id": null,
104
+ "chunk_size_feed_forward": 0,
105
+ "cross_attention_hidden_size": null,
106
+ "decoder_start_token_id": null,
107
+ "diversity_penalty": 0.0,
108
+ "do_sample": false,
109
+ "early_stopping": false,
110
+ "encoder_no_repeat_ngram_size": 0,
111
+ "eos_token_id": null,
112
+ "exponential_decay_length_penalty": null,
113
+ "finetuning_task": null,
114
+ "forced_bos_token_id": null,
115
+ "forced_eos_token_id": null,
116
+ "hidden_act": "quick_gelu",
117
+ "hidden_size": 1024,
118
+ "id2label": {
119
+ "0": "LABEL_0",
120
+ "1": "LABEL_1"
121
+ },
122
+ "image_size": 448,
123
+ "initializer_factor": 1.0,
124
+ "initializer_range": 0.02,
125
+ "intermediate_size": 4096,
126
+ "is_decoder": false,
127
+ "is_encoder_decoder": false,
128
+ "label2id": {
129
+ "LABEL_0": 0,
130
+ "LABEL_1": 1
131
+ },
132
+ "layer_norm_eps": 1e-06,
133
+ "length_penalty": 1.0,
134
+ "max_length": 20,
135
+ "min_length": 0,
136
+ "model_type": "mplug_owl_vision_model",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 16,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_channels": 3,
142
+ "num_hidden_layers": 24,
143
+ "num_return_sequences": 1,
144
+ "output_attentions": false,
145
+ "output_hidden_states": false,
146
+ "output_scores": false,
147
+ "pad_token_id": null,
148
+ "patch_size": 14,
149
+ "prefix": null,
150
+ "problem_type": null,
151
+ "projection_dim": 768,
152
+ "pruned_heads": {},
153
+ "remove_invalid_values": false,
154
+ "repetition_penalty": 1.0,
155
+ "return_dict": true,
156
+ "return_dict_in_generate": false,
157
+ "sep_token_id": null,
158
+ "suppress_tokens": null,
159
+ "task_specific_params": null,
160
+ "temperature": 1.0,
161
+ "tf_legacy_loss": false,
162
+ "tie_encoder_decoder": false,
163
+ "tie_word_embeddings": true,
164
+ "tokenizer_class": null,
165
+ "top_k": 50,
166
+ "top_p": 1.0,
167
+ "torch_dtype": null,
168
+ "torchscript": false,
169
+ "transformers_version": "4.28.1",
170
+ "typical_p": 1.0,
171
+ "use_bfloat16": false,
172
+ "use_flash_attn": false
173
+ }
174
+ },
175
+ "vocab_size": 32000
176
+ }
config.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_bias": false,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "hidden_act": "silu",
6
+ "hidden_size": 4096,
7
+ "initializer_range": 0.02,
8
+ "intermediate_size": 11008,
9
+ "max_position_embeddings": 2048,
10
+ "model_type": "mplug_owl2",
11
+ "num_attention_heads": 32,
12
+ "num_hidden_layers": 32,
13
+ "num_key_value_heads": 32,
14
+ "pretraining_tp": 1,
15
+ "rms_norm_eps": 1e-06,
16
+ "rope_scaling": null,
17
+ "rope_theta": 10000.0,
18
+ "tie_word_embeddings": false,
19
+ "transformers_version": "4.28.1",
20
+ "use_cache": true,
21
+ "visual_config": {
22
+ "visual_abstractor": {
23
+ "_name_or_path": "",
24
+ "add_cross_attention": false,
25
+ "architectures": null,
26
+ "attention_probs_dropout_prob": 0.0,
27
+ "bad_words_ids": null,
28
+ "begin_suppress_tokens": null,
29
+ "bos_token_id": null,
30
+ "chunk_size_feed_forward": 0,
31
+ "cross_attention_hidden_size": null,
32
+ "decoder_start_token_id": null,
33
+ "diversity_penalty": 0.0,
34
+ "do_sample": false,
35
+ "early_stopping": false,
36
+ "encoder_hidden_size": 1024,
37
+ "encoder_no_repeat_ngram_size": 0,
38
+ "eos_token_id": null,
39
+ "exponential_decay_length_penalty": null,
40
+ "finetuning_task": null,
41
+ "forced_bos_token_id": null,
42
+ "forced_eos_token_id": null,
43
+ "grid_size": 32,
44
+ "hidden_size": 1024,
45
+ "id2label": {
46
+ "0": "LABEL_0",
47
+ "1": "LABEL_1"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": 2816,
51
+ "is_decoder": false,
52
+ "is_encoder_decoder": false,
53
+ "label2id": {
54
+ "LABEL_0": 0,
55
+ "LABEL_1": 1
56
+ },
57
+ "layer_norm_eps": 1e-06,
58
+ "length_penalty": 1.0,
59
+ "max_length": 20,
60
+ "min_length": 0,
61
+ "model_type": "mplug_owl_visual_abstract",
62
+ "no_repeat_ngram_size": 0,
63
+ "num_attention_heads": 16,
64
+ "num_beam_groups": 1,
65
+ "num_beams": 1,
66
+ "num_hidden_layers": 6,
67
+ "num_learnable_queries": 64,
68
+ "num_return_sequences": 1,
69
+ "output_attentions": false,
70
+ "output_hidden_states": false,
71
+ "output_scores": false,
72
+ "pad_token_id": null,
73
+ "prefix": null,
74
+ "problem_type": null,
75
+ "pruned_heads": {},
76
+ "remove_invalid_values": false,
77
+ "repetition_penalty": 1.0,
78
+ "return_dict": true,
79
+ "return_dict_in_generate": false,
80
+ "sep_token_id": null,
81
+ "suppress_tokens": null,
82
+ "task_specific_params": null,
83
+ "temperature": 1.0,
84
+ "tf_legacy_loss": false,
85
+ "tie_encoder_decoder": false,
86
+ "tie_word_embeddings": true,
87
+ "tokenizer_class": null,
88
+ "top_k": 50,
89
+ "top_p": 1.0,
90
+ "torch_dtype": null,
91
+ "torchscript": false,
92
+ "transformers_version": "4.28.1",
93
+ "typical_p": 1.0,
94
+ "use_bfloat16": false
95
+ },
96
+ "visual_model": {
97
+ "_name_or_path": "",
98
+ "add_cross_attention": false,
99
+ "architectures": null,
100
+ "attention_dropout": 0.0,
101
+ "bad_words_ids": null,
102
+ "begin_suppress_tokens": null,
103
+ "bos_token_id": null,
104
+ "chunk_size_feed_forward": 0,
105
+ "cross_attention_hidden_size": null,
106
+ "decoder_start_token_id": null,
107
+ "diversity_penalty": 0.0,
108
+ "do_sample": false,
109
+ "early_stopping": false,
110
+ "encoder_no_repeat_ngram_size": 0,
111
+ "eos_token_id": null,
112
+ "exponential_decay_length_penalty": null,
113
+ "finetuning_task": null,
114
+ "forced_bos_token_id": null,
115
+ "forced_eos_token_id": null,
116
+ "hidden_act": "quick_gelu",
117
+ "hidden_size": 1024,
118
+ "id2label": {
119
+ "0": "LABEL_0",
120
+ "1": "LABEL_1"
121
+ },
122
+ "image_size": 448,
123
+ "initializer_factor": 1.0,
124
+ "initializer_range": 0.02,
125
+ "intermediate_size": 4096,
126
+ "is_decoder": false,
127
+ "is_encoder_decoder": false,
128
+ "label2id": {
129
+ "LABEL_0": 0,
130
+ "LABEL_1": 1
131
+ },
132
+ "layer_norm_eps": 1e-06,
133
+ "length_penalty": 1.0,
134
+ "max_length": 20,
135
+ "min_length": 0,
136
+ "model_type": "mplug_owl_vision_model",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 16,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_channels": 3,
142
+ "num_hidden_layers": 24,
143
+ "num_return_sequences": 1,
144
+ "output_attentions": false,
145
+ "output_hidden_states": false,
146
+ "output_scores": false,
147
+ "pad_token_id": null,
148
+ "patch_size": 14,
149
+ "prefix": null,
150
+ "problem_type": null,
151
+ "projection_dim": 768,
152
+ "pruned_heads": {},
153
+ "remove_invalid_values": false,
154
+ "repetition_penalty": 1.0,
155
+ "return_dict": true,
156
+ "return_dict_in_generate": false,
157
+ "sep_token_id": null,
158
+ "suppress_tokens": null,
159
+ "task_specific_params": null,
160
+ "temperature": 1.0,
161
+ "tf_legacy_loss": false,
162
+ "tie_encoder_decoder": false,
163
+ "tie_word_embeddings": true,
164
+ "tokenizer_class": null,
165
+ "top_k": 50,
166
+ "top_p": 1.0,
167
+ "torch_dtype": null,
168
+ "torchscript": false,
169
+ "transformers_version": "4.28.1",
170
+ "typical_p": 1.0,
171
+ "use_bfloat16": false,
172
+ "use_flash_attn": false
173
+ }
174
+ },
175
+ "vocab_size": 32000
176
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": 448,
3
+ "do_center_crop": true,
4
+ "do_normalize": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "CLIPFeatureExtractor",
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "resample": 3,
18
+ "size": 448
19
+ }
20
+
pytorch_model-1-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:887c855ee722a97b38941cf66b9c5fee4c17842d5aca63b52d4715d7a30284eb
3
+ size 471896315
pytorch_model-10-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d0db3dcebac1f80585eeb7300fc2b7cd3494eb4633f8f71da340d98912e65e
3
+ size 471896315
pytorch_model-11-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76676e9bc758d39b4f5597bb863ddbb76bd938ff7d13ef52dc8b95f00dae1e45
3
+ size 471896315
pytorch_model-12-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c591177a1e1d674be846d592f0170ee47dde4be5b89bbd3902c74ba710927f09
3
+ size 471896315
pytorch_model-13-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94f0ad8f6083a3d57169ccc20e9510cc8fa22b45c6b386052fb49b1374fa7b46
3
+ size 471896315
pytorch_model-14-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d7f6d38740bb47c820b613c9fc9943d403d53ab0395c86f7a4a4096eb45f75
3
+ size 471896315
pytorch_model-15-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b34b0baba0c03881b28d5b330004cde2b1296cd5ad2edff37dbded5c6000cec6
3
+ size 471896315
pytorch_model-16-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4647377f83a3dac2e6849cb66ad4e3ea6bd905437a8794c08181d0b51a2d3e7b
3
+ size 471896315
pytorch_model-17-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e115f65ec0c06e4510882e14b5d132d4cc1fa22091b8608527959753aab224de
3
+ size 471896315
pytorch_model-18-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:706544cdfc9a5ff5539fa1b119bfb58a454c44b49426de6b85a4837ac1457599
3
+ size 471896315
pytorch_model-19-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0bbf13965fe4db01dd3bf38ec647860af3718c472f7aebf57e9bd46f5c61d71
3
+ size 471896315
pytorch_model-2-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:880f73c4610afc99dde0a0841dd4a19771705a264753d769368f8e40ad506a52
3
+ size 471896315
pytorch_model-20-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d4ce184f7ac6c076b37ff276dd4f39ed71e26a61e7adeadba0b6bf4bdd0724
3
+ size 471896315
pytorch_model-21-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af0e44baba21d0c475c7f80b480dae3b1b18782e8f8d371f913e49b839fab141
3
+ size 471896315
pytorch_model-22-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24fc15879ad76d0d9b8112fd47e0b5971db06216edc904df9d7f6c25fadbb8d8
3
+ size 471896315
pytorch_model-23-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df38a96f9a644ae160f298119668548cf6739ee689d1325b0edb76bdafc4bf0e
3
+ size 471896315
pytorch_model-24-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fea6af46881427311647c36214c5a028c3a6b0ab4bc6a726c01ec24bc8a77385
3
+ size 471896315
pytorch_model-25-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:427ce5936cb5b7190d0134c4ee96a4d8b88d4dfb4e07cf1dd10326b159b55164
3
+ size 471896315
pytorch_model-26-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07aec68ff9da0231442e30848644ecb64c5421e7161021c6b8d9eb74ba867b76
3
+ size 471896315
pytorch_model-27-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3972398cc61d09b89ab2cd973eb0a2ccc3e98c6333dbd7119622fbb90da5895e
3
+ size 471896315
pytorch_model-28-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c463416aa1dc4791bf1f43871f4138b394014ef78ed7626b4b70550a719b1a76
3
+ size 471896315
pytorch_model-29-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db54d0d7fd41fb11f9eda0190e4a0c2fb9c7c41b232b78a6ca048a76727c973a
3
+ size 471896315
pytorch_model-3-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afffba63c018c89cb3498908baf2fd1e6060be80cf11e604d98408d0c1e923df
3
+ size 471896315
pytorch_model-30-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bf275391292bc5902ffd92983337b828229ec51ebb9c1fc99a41a507a36f2fa
3
+ size 471896315
pytorch_model-31-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f501f58f7833cac5cc288d4d6b1594a437d635d19cf46cda76b38d1edaa9f7c0
3
+ size 471896315
pytorch_model-32-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dfa2240bcae89d0589143b88f1a4ce6c278b5d8a365ad9b22917d1d38fc7d70
3
+ size 471896315
pytorch_model-33-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83fb5330a7fcbf4f43f8199f2753c04830367167a4e6e8878f4df31a944a719e
3
+ size 1295321821
pytorch_model-4-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84e6553b89d7394ced06b87bde477976dd85ac6d5006273caadd9fb5dfa8843e
3
+ size 471896315
pytorch_model-5-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:126a3d31e8f3eade2111b1bfdb864ced4c6a4fc53b7beeedb5afe1085c88eec8
3
+ size 471896315
pytorch_model-6-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9501757104ce87557d972e68b615f6de1540642f2eb996a38af1600267d6e52
3
+ size 471896315
pytorch_model-7-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:283bfcea71a533c23e1c9d5878a62ffb0fe5550c4d4997e295dd5926694a7208
3
+ size 471896315
pytorch_model-8-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13d66fe72eba5f92e82c39ae6de6ae445be8947e81923f5647c8a330006c0a9f
3
+ size 471896315
pytorch_model-9-of-33.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97c642f592d944c34d72840a2ef5cf4096e6688c0e5cb7cc4ad0df0df36659eb
3
+ size 471896315
pytorch_model.bin.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"weight_map": {"model.layers.0.self_attn.q_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.k_proj.multiway.0.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.v_proj.multiway.0.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.k_proj.multiway.1.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.v_proj.multiway.1.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.o_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.mlp.gate_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.mlp.down_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.mlp.up_proj.weight": "pytorch_model-1-of-33.bin", "model.layers.0.input_layernorm.multiway.0.weight": "pytorch_model-1-of-33.bin", "model.layers.0.post_attention_layernorm.multiway.0.weight": "pytorch_model-1-of-33.bin", "model.layers.0.input_layernorm.multiway.1.weight": "pytorch_model-1-of-33.bin", "model.layers.0.post_attention_layernorm.multiway.1.weight": "pytorch_model-1-of-33.bin", "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-1-of-33.bin", "model.layers.1.self_attn.q_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.k_proj.multiway.0.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.v_proj.multiway.0.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.k_proj.multiway.1.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.v_proj.multiway.1.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.o_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.mlp.gate_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.mlp.down_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.mlp.up_proj.weight": "pytorch_model-2-of-33.bin", "model.layers.1.input_layernorm.multiway.0.weight": "pytorch_model-2-of-33.bin", "model.layers.1.post_attention_layernorm.multiway.0.weight": "pytorch_model-2-of-33.bin", "model.layers.1.input_layernorm.multiway.1.weight": "pytorch_model-2-of-33.bin", "model.layers.1.post_attention_layernorm.multiway.1.weight": "pytorch_model-2-of-33.bin", "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-2-of-33.bin", "model.layers.2.self_attn.q_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.k_proj.multiway.0.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.v_proj.multiway.0.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.k_proj.multiway.1.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.v_proj.multiway.1.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.o_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.mlp.gate_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.mlp.down_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.mlp.up_proj.weight": "pytorch_model-3-of-33.bin", "model.layers.2.input_layernorm.multiway.0.weight": "pytorch_model-3-of-33.bin", "model.layers.2.post_attention_layernorm.multiway.0.weight": "pytorch_model-3-of-33.bin", "model.layers.2.input_layernorm.multiway.1.weight": "pytorch_model-3-of-33.bin", "model.layers.2.post_attention_layernorm.multiway.1.weight": "pytorch_model-3-of-33.bin", "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-3-of-33.bin", "model.layers.3.self_attn.q_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.k_proj.multiway.0.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.v_proj.multiway.0.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.k_proj.multiway.1.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.v_proj.multiway.1.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.o_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.mlp.gate_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.mlp.down_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.mlp.up_proj.weight": "pytorch_model-4-of-33.bin", "model.layers.3.input_layernorm.multiway.0.weight": "pytorch_model-4-of-33.bin", "model.layers.3.post_attention_layernorm.multiway.0.weight": "pytorch_model-4-of-33.bin", "model.layers.3.input_layernorm.multiway.1.weight": "pytorch_model-4-of-33.bin", "model.layers.3.post_attention_layernorm.multiway.1.weight": "pytorch_model-4-of-33.bin", "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-4-of-33.bin", "model.layers.4.self_attn.q_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.k_proj.multiway.0.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.v_proj.multiway.0.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.k_proj.multiway.1.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.v_proj.multiway.1.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.o_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.mlp.gate_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.mlp.down_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.mlp.up_proj.weight": "pytorch_model-5-of-33.bin", "model.layers.4.input_layernorm.multiway.0.weight": "pytorch_model-5-of-33.bin", "model.layers.4.post_attention_layernorm.multiway.0.weight": "pytorch_model-5-of-33.bin", "model.layers.4.input_layernorm.multiway.1.weight": "pytorch_model-5-of-33.bin", "model.layers.4.post_attention_layernorm.multiway.1.weight": "pytorch_model-5-of-33.bin", "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-5-of-33.bin", "model.layers.5.self_attn.q_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.k_proj.multiway.0.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.v_proj.multiway.0.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.k_proj.multiway.1.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.v_proj.multiway.1.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.o_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.mlp.gate_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.mlp.down_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.mlp.up_proj.weight": "pytorch_model-6-of-33.bin", "model.layers.5.input_layernorm.multiway.0.weight": "pytorch_model-6-of-33.bin", "model.layers.5.post_attention_layernorm.multiway.0.weight": "pytorch_model-6-of-33.bin", "model.layers.5.input_layernorm.multiway.1.weight": "pytorch_model-6-of-33.bin", "model.layers.5.post_attention_layernorm.multiway.1.weight": "pytorch_model-6-of-33.bin", "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-6-of-33.bin", "model.layers.6.self_attn.q_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.k_proj.multiway.0.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.v_proj.multiway.0.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.k_proj.multiway.1.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.v_proj.multiway.1.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.o_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.mlp.gate_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.mlp.down_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.mlp.up_proj.weight": "pytorch_model-7-of-33.bin", "model.layers.6.input_layernorm.multiway.0.weight": "pytorch_model-7-of-33.bin", "model.layers.6.post_attention_layernorm.multiway.0.weight": "pytorch_model-7-of-33.bin", "model.layers.6.input_layernorm.multiway.1.weight": "pytorch_model-7-of-33.bin", "model.layers.6.post_attention_layernorm.multiway.1.weight": "pytorch_model-7-of-33.bin", "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-7-of-33.bin", "model.layers.7.self_attn.q_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.k_proj.multiway.0.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.v_proj.multiway.0.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.k_proj.multiway.1.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.v_proj.multiway.1.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.o_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.mlp.gate_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.mlp.down_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.mlp.up_proj.weight": "pytorch_model-8-of-33.bin", "model.layers.7.input_layernorm.multiway.0.weight": "pytorch_model-8-of-33.bin", "model.layers.7.post_attention_layernorm.multiway.0.weight": "pytorch_model-8-of-33.bin", "model.layers.7.input_layernorm.multiway.1.weight": "pytorch_model-8-of-33.bin", "model.layers.7.post_attention_layernorm.multiway.1.weight": "pytorch_model-8-of-33.bin", "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-8-of-33.bin", "model.layers.8.self_attn.q_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.k_proj.multiway.0.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.v_proj.multiway.0.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.k_proj.multiway.1.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.v_proj.multiway.1.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.o_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.mlp.gate_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.mlp.down_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.mlp.up_proj.weight": "pytorch_model-9-of-33.bin", "model.layers.8.input_layernorm.multiway.0.weight": "pytorch_model-9-of-33.bin", "model.layers.8.post_attention_layernorm.multiway.0.weight": "pytorch_model-9-of-33.bin", "model.layers.8.input_layernorm.multiway.1.weight": "pytorch_model-9-of-33.bin", "model.layers.8.post_attention_layernorm.multiway.1.weight": "pytorch_model-9-of-33.bin", "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-9-of-33.bin", "model.layers.9.self_attn.q_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.k_proj.multiway.0.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.v_proj.multiway.0.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.k_proj.multiway.1.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.v_proj.multiway.1.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.o_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.mlp.gate_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.mlp.down_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.mlp.up_proj.weight": "pytorch_model-10-of-33.bin", "model.layers.9.input_layernorm.multiway.0.weight": "pytorch_model-10-of-33.bin", "model.layers.9.post_attention_layernorm.multiway.0.weight": "pytorch_model-10-of-33.bin", "model.layers.9.input_layernorm.multiway.1.weight": "pytorch_model-10-of-33.bin", "model.layers.9.post_attention_layernorm.multiway.1.weight": "pytorch_model-10-of-33.bin", "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-10-of-33.bin", "model.layers.10.self_attn.q_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.k_proj.multiway.0.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.v_proj.multiway.0.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.k_proj.multiway.1.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.v_proj.multiway.1.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.o_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.mlp.gate_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.mlp.down_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.mlp.up_proj.weight": "pytorch_model-11-of-33.bin", "model.layers.10.input_layernorm.multiway.0.weight": "pytorch_model-11-of-33.bin", "model.layers.10.post_attention_layernorm.multiway.0.weight": "pytorch_model-11-of-33.bin", "model.layers.10.input_layernorm.multiway.1.weight": "pytorch_model-11-of-33.bin", "model.layers.10.post_attention_layernorm.multiway.1.weight": "pytorch_model-11-of-33.bin", "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-11-of-33.bin", "model.layers.11.self_attn.q_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.k_proj.multiway.0.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.v_proj.multiway.0.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.k_proj.multiway.1.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.v_proj.multiway.1.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.o_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.mlp.gate_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.mlp.down_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.mlp.up_proj.weight": "pytorch_model-12-of-33.bin", "model.layers.11.input_layernorm.multiway.0.weight": "pytorch_model-12-of-33.bin", "model.layers.11.post_attention_layernorm.multiway.0.weight": "pytorch_model-12-of-33.bin", "model.layers.11.input_layernorm.multiway.1.weight": "pytorch_model-12-of-33.bin", "model.layers.11.post_attention_layernorm.multiway.1.weight": "pytorch_model-12-of-33.bin", "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-12-of-33.bin", "model.layers.12.self_attn.q_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.k_proj.multiway.0.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.v_proj.multiway.0.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.k_proj.multiway.1.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.v_proj.multiway.1.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.o_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.mlp.gate_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.mlp.down_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.mlp.up_proj.weight": "pytorch_model-13-of-33.bin", "model.layers.12.input_layernorm.multiway.0.weight": "pytorch_model-13-of-33.bin", "model.layers.12.post_attention_layernorm.multiway.0.weight": "pytorch_model-13-of-33.bin", "model.layers.12.input_layernorm.multiway.1.weight": "pytorch_model-13-of-33.bin", "model.layers.12.post_attention_layernorm.multiway.1.weight": "pytorch_model-13-of-33.bin", "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-13-of-33.bin", "model.layers.13.self_attn.q_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.k_proj.multiway.0.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.v_proj.multiway.0.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.k_proj.multiway.1.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.v_proj.multiway.1.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.o_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.mlp.gate_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.mlp.down_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.mlp.up_proj.weight": "pytorch_model-14-of-33.bin", "model.layers.13.input_layernorm.multiway.0.weight": "pytorch_model-14-of-33.bin", "model.layers.13.post_attention_layernorm.multiway.0.weight": "pytorch_model-14-of-33.bin", "model.layers.13.input_layernorm.multiway.1.weight": "pytorch_model-14-of-33.bin", "model.layers.13.post_attention_layernorm.multiway.1.weight": "pytorch_model-14-of-33.bin", "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-14-of-33.bin", "model.layers.14.self_attn.q_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.k_proj.multiway.0.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.v_proj.multiway.0.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.k_proj.multiway.1.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.v_proj.multiway.1.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.o_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.mlp.gate_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.mlp.down_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.mlp.up_proj.weight": "pytorch_model-15-of-33.bin", "model.layers.14.input_layernorm.multiway.0.weight": "pytorch_model-15-of-33.bin", "model.layers.14.post_attention_layernorm.multiway.0.weight": "pytorch_model-15-of-33.bin", "model.layers.14.input_layernorm.multiway.1.weight": "pytorch_model-15-of-33.bin", "model.layers.14.post_attention_layernorm.multiway.1.weight": "pytorch_model-15-of-33.bin", "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-15-of-33.bin", "model.layers.15.self_attn.q_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.k_proj.multiway.0.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.v_proj.multiway.0.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.k_proj.multiway.1.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.v_proj.multiway.1.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.o_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.mlp.gate_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.mlp.down_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.mlp.up_proj.weight": "pytorch_model-16-of-33.bin", "model.layers.15.input_layernorm.multiway.0.weight": "pytorch_model-16-of-33.bin", "model.layers.15.post_attention_layernorm.multiway.0.weight": "pytorch_model-16-of-33.bin", "model.layers.15.input_layernorm.multiway.1.weight": "pytorch_model-16-of-33.bin", "model.layers.15.post_attention_layernorm.multiway.1.weight": "pytorch_model-16-of-33.bin", "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-16-of-33.bin", "model.layers.16.self_attn.q_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.k_proj.multiway.0.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.v_proj.multiway.0.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.k_proj.multiway.1.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.v_proj.multiway.1.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.o_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.mlp.gate_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.mlp.down_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.mlp.up_proj.weight": "pytorch_model-17-of-33.bin", "model.layers.16.input_layernorm.multiway.0.weight": "pytorch_model-17-of-33.bin", "model.layers.16.post_attention_layernorm.multiway.0.weight": "pytorch_model-17-of-33.bin", "model.layers.16.input_layernorm.multiway.1.weight": "pytorch_model-17-of-33.bin", "model.layers.16.post_attention_layernorm.multiway.1.weight": "pytorch_model-17-of-33.bin", "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-17-of-33.bin", "model.layers.17.self_attn.q_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.k_proj.multiway.0.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.v_proj.multiway.0.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.k_proj.multiway.1.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.v_proj.multiway.1.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.o_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.mlp.gate_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.mlp.down_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.mlp.up_proj.weight": "pytorch_model-18-of-33.bin", "model.layers.17.input_layernorm.multiway.0.weight": "pytorch_model-18-of-33.bin", "model.layers.17.post_attention_layernorm.multiway.0.weight": "pytorch_model-18-of-33.bin", "model.layers.17.input_layernorm.multiway.1.weight": "pytorch_model-18-of-33.bin", "model.layers.17.post_attention_layernorm.multiway.1.weight": "pytorch_model-18-of-33.bin", "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-18-of-33.bin", "model.layers.18.self_attn.q_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.k_proj.multiway.0.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.v_proj.multiway.0.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.k_proj.multiway.1.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.v_proj.multiway.1.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.o_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.mlp.gate_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.mlp.down_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.mlp.up_proj.weight": "pytorch_model-19-of-33.bin", "model.layers.18.input_layernorm.multiway.0.weight": "pytorch_model-19-of-33.bin", "model.layers.18.post_attention_layernorm.multiway.0.weight": "pytorch_model-19-of-33.bin", "model.layers.18.input_layernorm.multiway.1.weight": "pytorch_model-19-of-33.bin", "model.layers.18.post_attention_layernorm.multiway.1.weight": "pytorch_model-19-of-33.bin", "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-19-of-33.bin", "model.layers.19.self_attn.q_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.k_proj.multiway.0.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.v_proj.multiway.0.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.k_proj.multiway.1.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.v_proj.multiway.1.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.o_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.mlp.gate_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.mlp.down_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.mlp.up_proj.weight": "pytorch_model-20-of-33.bin", "model.layers.19.input_layernorm.multiway.0.weight": "pytorch_model-20-of-33.bin", "model.layers.19.post_attention_layernorm.multiway.0.weight": "pytorch_model-20-of-33.bin", "model.layers.19.input_layernorm.multiway.1.weight": "pytorch_model-20-of-33.bin", "model.layers.19.post_attention_layernorm.multiway.1.weight": "pytorch_model-20-of-33.bin", "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-20-of-33.bin", "model.layers.20.self_attn.q_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.k_proj.multiway.0.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.v_proj.multiway.0.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.k_proj.multiway.1.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.v_proj.multiway.1.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.o_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.mlp.gate_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.mlp.down_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.mlp.up_proj.weight": "pytorch_model-21-of-33.bin", "model.layers.20.input_layernorm.multiway.0.weight": "pytorch_model-21-of-33.bin", "model.layers.20.post_attention_layernorm.multiway.0.weight": "pytorch_model-21-of-33.bin", "model.layers.20.input_layernorm.multiway.1.weight": "pytorch_model-21-of-33.bin", "model.layers.20.post_attention_layernorm.multiway.1.weight": "pytorch_model-21-of-33.bin", "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-21-of-33.bin", "model.layers.21.self_attn.q_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.k_proj.multiway.0.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.v_proj.multiway.0.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.k_proj.multiway.1.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.v_proj.multiway.1.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.o_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.mlp.gate_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.mlp.down_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.mlp.up_proj.weight": "pytorch_model-22-of-33.bin", "model.layers.21.input_layernorm.multiway.0.weight": "pytorch_model-22-of-33.bin", "model.layers.21.post_attention_layernorm.multiway.0.weight": "pytorch_model-22-of-33.bin", "model.layers.21.input_layernorm.multiway.1.weight": "pytorch_model-22-of-33.bin", "model.layers.21.post_attention_layernorm.multiway.1.weight": "pytorch_model-22-of-33.bin", "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-22-of-33.bin", "model.layers.22.self_attn.q_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.k_proj.multiway.0.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.v_proj.multiway.0.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.k_proj.multiway.1.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.v_proj.multiway.1.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.o_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.mlp.gate_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.mlp.down_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.mlp.up_proj.weight": "pytorch_model-23-of-33.bin", "model.layers.22.input_layernorm.multiway.0.weight": "pytorch_model-23-of-33.bin", "model.layers.22.post_attention_layernorm.multiway.0.weight": "pytorch_model-23-of-33.bin", "model.layers.22.input_layernorm.multiway.1.weight": "pytorch_model-23-of-33.bin", "model.layers.22.post_attention_layernorm.multiway.1.weight": "pytorch_model-23-of-33.bin", "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-23-of-33.bin", "model.layers.23.self_attn.q_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.k_proj.multiway.0.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.v_proj.multiway.0.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.k_proj.multiway.1.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.v_proj.multiway.1.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.o_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.mlp.gate_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.mlp.down_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.mlp.up_proj.weight": "pytorch_model-24-of-33.bin", "model.layers.23.input_layernorm.multiway.0.weight": "pytorch_model-24-of-33.bin", "model.layers.23.post_attention_layernorm.multiway.0.weight": "pytorch_model-24-of-33.bin", "model.layers.23.input_layernorm.multiway.1.weight": "pytorch_model-24-of-33.bin", "model.layers.23.post_attention_layernorm.multiway.1.weight": "pytorch_model-24-of-33.bin", "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-24-of-33.bin", "model.layers.24.self_attn.q_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.k_proj.multiway.0.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.v_proj.multiway.0.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.k_proj.multiway.1.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.v_proj.multiway.1.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.o_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.mlp.gate_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.mlp.down_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.mlp.up_proj.weight": "pytorch_model-25-of-33.bin", "model.layers.24.input_layernorm.multiway.0.weight": "pytorch_model-25-of-33.bin", "model.layers.24.post_attention_layernorm.multiway.0.weight": "pytorch_model-25-of-33.bin", "model.layers.24.input_layernorm.multiway.1.weight": "pytorch_model-25-of-33.bin", "model.layers.24.post_attention_layernorm.multiway.1.weight": "pytorch_model-25-of-33.bin", "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-25-of-33.bin", "model.layers.25.self_attn.q_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.k_proj.multiway.0.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.v_proj.multiway.0.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.k_proj.multiway.1.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.v_proj.multiway.1.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.o_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.mlp.gate_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.mlp.down_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.mlp.up_proj.weight": "pytorch_model-26-of-33.bin", "model.layers.25.input_layernorm.multiway.0.weight": "pytorch_model-26-of-33.bin", "model.layers.25.post_attention_layernorm.multiway.0.weight": "pytorch_model-26-of-33.bin", "model.layers.25.input_layernorm.multiway.1.weight": "pytorch_model-26-of-33.bin", "model.layers.25.post_attention_layernorm.multiway.1.weight": "pytorch_model-26-of-33.bin", "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-26-of-33.bin", "model.layers.26.self_attn.q_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.k_proj.multiway.0.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.v_proj.multiway.0.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.k_proj.multiway.1.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.v_proj.multiway.1.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.o_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.mlp.gate_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.mlp.down_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.mlp.up_proj.weight": "pytorch_model-27-of-33.bin", "model.layers.26.input_layernorm.multiway.0.weight": "pytorch_model-27-of-33.bin", "model.layers.26.post_attention_layernorm.multiway.0.weight": "pytorch_model-27-of-33.bin", "model.layers.26.input_layernorm.multiway.1.weight": "pytorch_model-27-of-33.bin", "model.layers.26.post_attention_layernorm.multiway.1.weight": "pytorch_model-27-of-33.bin", "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-27-of-33.bin", "model.layers.27.self_attn.q_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.k_proj.multiway.0.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.v_proj.multiway.0.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.k_proj.multiway.1.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.v_proj.multiway.1.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.o_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.mlp.gate_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.mlp.down_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.mlp.up_proj.weight": "pytorch_model-28-of-33.bin", "model.layers.27.input_layernorm.multiway.0.weight": "pytorch_model-28-of-33.bin", "model.layers.27.post_attention_layernorm.multiway.0.weight": "pytorch_model-28-of-33.bin", "model.layers.27.input_layernorm.multiway.1.weight": "pytorch_model-28-of-33.bin", "model.layers.27.post_attention_layernorm.multiway.1.weight": "pytorch_model-28-of-33.bin", "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-28-of-33.bin", "model.layers.28.self_attn.q_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.k_proj.multiway.0.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.v_proj.multiway.0.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.k_proj.multiway.1.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.v_proj.multiway.1.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.o_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.mlp.gate_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.mlp.down_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.mlp.up_proj.weight": "pytorch_model-29-of-33.bin", "model.layers.28.input_layernorm.multiway.0.weight": "pytorch_model-29-of-33.bin", "model.layers.28.post_attention_layernorm.multiway.0.weight": "pytorch_model-29-of-33.bin", "model.layers.28.input_layernorm.multiway.1.weight": "pytorch_model-29-of-33.bin", "model.layers.28.post_attention_layernorm.multiway.1.weight": "pytorch_model-29-of-33.bin", "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-29-of-33.bin", "model.layers.29.self_attn.q_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.k_proj.multiway.0.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.v_proj.multiway.0.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.k_proj.multiway.1.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.v_proj.multiway.1.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.o_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.mlp.gate_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.mlp.down_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.mlp.up_proj.weight": "pytorch_model-30-of-33.bin", "model.layers.29.input_layernorm.multiway.0.weight": "pytorch_model-30-of-33.bin", "model.layers.29.post_attention_layernorm.multiway.0.weight": "pytorch_model-30-of-33.bin", "model.layers.29.input_layernorm.multiway.1.weight": "pytorch_model-30-of-33.bin", "model.layers.29.post_attention_layernorm.multiway.1.weight": "pytorch_model-30-of-33.bin", "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-30-of-33.bin", "model.layers.30.self_attn.q_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.k_proj.multiway.0.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.v_proj.multiway.0.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.k_proj.multiway.1.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.v_proj.multiway.1.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.o_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.mlp.gate_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.mlp.down_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.mlp.up_proj.weight": "pytorch_model-31-of-33.bin", "model.layers.30.input_layernorm.multiway.0.weight": "pytorch_model-31-of-33.bin", "model.layers.30.post_attention_layernorm.multiway.0.weight": "pytorch_model-31-of-33.bin", "model.layers.30.input_layernorm.multiway.1.weight": "pytorch_model-31-of-33.bin", "model.layers.30.post_attention_layernorm.multiway.1.weight": "pytorch_model-31-of-33.bin", "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-31-of-33.bin", "model.layers.31.self_attn.q_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.k_proj.multiway.0.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.v_proj.multiway.0.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.k_proj.multiway.1.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.v_proj.multiway.1.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.o_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.mlp.gate_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.mlp.down_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.mlp.up_proj.weight": "pytorch_model-32-of-33.bin", "model.layers.31.input_layernorm.multiway.0.weight": "pytorch_model-32-of-33.bin", "model.layers.31.post_attention_layernorm.multiway.0.weight": "pytorch_model-32-of-33.bin", "model.layers.31.input_layernorm.multiway.1.weight": "pytorch_model-32-of-33.bin", "model.layers.31.post_attention_layernorm.multiway.1.weight": "pytorch_model-32-of-33.bin", "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-32-of-33.bin", "model.embed_tokens.weight": "pytorch_model-33-of-33.bin", "model.norm.weight": "pytorch_model-33-of-33.bin", "lm_head.weight": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.cls_token": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.patch_embed.weight": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.position_embedding": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.pre_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.embeddings.pre_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.post_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.post_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.0.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.1.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.2.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.3.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.4.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.5.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.6.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.7.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.8.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.9.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.10.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.11.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.12.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.13.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.14.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.15.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.16.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.17.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.18.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.19.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.20.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.21.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.22.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.input_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.input_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.post_attention_layernorm.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.self_attn.dense.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.self_attn.dense.weight": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.self_attn.query_key_value.bias": "pytorch_model-33-of-33.bin", "model.vision_model.encoder.layers.23.self_attn.query_key_value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.query_embeds": "pytorch_model-33-of-33.bin", "model.visual_abstractor.visual_fc.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.visual_fc.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.vit_eos": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.0.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.1.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.2.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.3.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.4.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.key.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.key.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.query.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.query.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.value.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.attention.value.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.norm1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.norm1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.normk.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.normk.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w1.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w1.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w3.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w3.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.norm2.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.norm2.weight": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.out_proj.bias": "pytorch_model-33-of-33.bin", "model.visual_abstractor.encoder.layers.5.crossattention.output.out_proj.weight": "pytorch_model-33-of-33.bin"}, "metadata": {"total_size": 16395722752}}
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 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
22
+ "model_max_length": 4096,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }