Upload folder using huggingface_hub
Browse files- config.json +187 -0
- preprocessor_config.json +20 -0
- pytorch_model-00001-of-00004.bin +3 -0
- pytorch_model-00002-of-00004.bin +3 -0
- pytorch_model-00003-of-00004.bin +3 -0
- pytorch_model-00004-of-00004.bin +3 -0
- pytorch_model.bin.index.json +869 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
- trainer_state.json +606 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,187 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "MAGAer13/mplug-owl2-llama2-7b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MPLUGOwl2LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"freeze_vision_model": false,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"image_aspect_ratio": "pad",
|
| 14 |
+
"image_grid_pinpoints": null,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 11008,
|
| 17 |
+
"max_position_embeddings": 2048,
|
| 18 |
+
"model_type": "mplug_owl2",
|
| 19 |
+
"num_attention_heads": 32,
|
| 20 |
+
"num_hidden_layers": 32,
|
| 21 |
+
"num_key_value_heads": 32,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_scaling": null,
|
| 25 |
+
"rope_theta": 10000.0,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.36.1",
|
| 29 |
+
"tune_visual_abstractor": true,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"visual_abstractor_lr": null,
|
| 32 |
+
"visual_config": {
|
| 33 |
+
"visual_abstractor": {
|
| 34 |
+
"_name_or_path": "",
|
| 35 |
+
"add_cross_attention": false,
|
| 36 |
+
"architectures": null,
|
| 37 |
+
"attention_probs_dropout_prob": 0.0,
|
| 38 |
+
"bad_words_ids": null,
|
| 39 |
+
"begin_suppress_tokens": null,
|
| 40 |
+
"bos_token_id": null,
|
| 41 |
+
"chunk_size_feed_forward": 0,
|
| 42 |
+
"cross_attention_hidden_size": null,
|
| 43 |
+
"decoder_start_token_id": null,
|
| 44 |
+
"diversity_penalty": 0.0,
|
| 45 |
+
"do_sample": false,
|
| 46 |
+
"early_stopping": false,
|
| 47 |
+
"encoder_hidden_size": 1024,
|
| 48 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 49 |
+
"eos_token_id": null,
|
| 50 |
+
"exponential_decay_length_penalty": null,
|
| 51 |
+
"finetuning_task": null,
|
| 52 |
+
"forced_bos_token_id": null,
|
| 53 |
+
"forced_eos_token_id": null,
|
| 54 |
+
"grid_size": 32,
|
| 55 |
+
"hidden_size": 1024,
|
| 56 |
+
"id2label": {
|
| 57 |
+
"0": "LABEL_0",
|
| 58 |
+
"1": "LABEL_1"
|
| 59 |
+
},
|
| 60 |
+
"initializer_range": 0.02,
|
| 61 |
+
"intermediate_size": 2816,
|
| 62 |
+
"is_decoder": false,
|
| 63 |
+
"is_encoder_decoder": false,
|
| 64 |
+
"label2id": {
|
| 65 |
+
"LABEL_0": 0,
|
| 66 |
+
"LABEL_1": 1
|
| 67 |
+
},
|
| 68 |
+
"layer_norm_eps": 1e-06,
|
| 69 |
+
"length_penalty": 1.0,
|
| 70 |
+
"max_length": 20,
|
| 71 |
+
"min_length": 0,
|
| 72 |
+
"model_type": "mplug_owl_visual_abstract",
|
| 73 |
+
"no_repeat_ngram_size": 0,
|
| 74 |
+
"num_attention_heads": 16,
|
| 75 |
+
"num_beam_groups": 1,
|
| 76 |
+
"num_beams": 1,
|
| 77 |
+
"num_hidden_layers": 6,
|
| 78 |
+
"num_learnable_queries": 64,
|
| 79 |
+
"num_return_sequences": 1,
|
| 80 |
+
"output_attentions": false,
|
| 81 |
+
"output_hidden_states": false,
|
| 82 |
+
"output_scores": false,
|
| 83 |
+
"pad_token_id": null,
|
| 84 |
+
"prefix": null,
|
| 85 |
+
"problem_type": null,
|
| 86 |
+
"pruned_heads": {},
|
| 87 |
+
"remove_invalid_values": false,
|
| 88 |
+
"repetition_penalty": 1.0,
|
| 89 |
+
"return_dict": true,
|
| 90 |
+
"return_dict_in_generate": false,
|
| 91 |
+
"sep_token_id": null,
|
| 92 |
+
"suppress_tokens": null,
|
| 93 |
+
"task_specific_params": null,
|
| 94 |
+
"temperature": 1.0,
|
| 95 |
+
"tf_legacy_loss": false,
|
| 96 |
+
"tie_encoder_decoder": false,
|
| 97 |
+
"tie_word_embeddings": true,
|
| 98 |
+
"tokenizer_class": null,
|
| 99 |
+
"top_k": 50,
|
| 100 |
+
"top_p": 1.0,
|
| 101 |
+
"torch_dtype": null,
|
| 102 |
+
"torchscript": false,
|
| 103 |
+
"transformers_version": "4.28.1",
|
| 104 |
+
"typical_p": 1.0,
|
| 105 |
+
"use_bfloat16": false
|
| 106 |
+
},
|
| 107 |
+
"visual_model": {
|
| 108 |
+
"_name_or_path": "",
|
| 109 |
+
"add_cross_attention": false,
|
| 110 |
+
"architectures": null,
|
| 111 |
+
"attention_dropout": 0.0,
|
| 112 |
+
"bad_words_ids": null,
|
| 113 |
+
"begin_suppress_tokens": null,
|
| 114 |
+
"bos_token_id": null,
|
| 115 |
+
"chunk_size_feed_forward": 0,
|
| 116 |
+
"cross_attention_hidden_size": null,
|
| 117 |
+
"decoder_start_token_id": null,
|
| 118 |
+
"diversity_penalty": 0.0,
|
| 119 |
+
"do_sample": false,
|
| 120 |
+
"early_stopping": false,
|
| 121 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 122 |
+
"eos_token_id": null,
|
| 123 |
+
"exponential_decay_length_penalty": null,
|
| 124 |
+
"finetuning_task": null,
|
| 125 |
+
"forced_bos_token_id": null,
|
| 126 |
+
"forced_eos_token_id": null,
|
| 127 |
+
"hidden_act": "quick_gelu",
|
| 128 |
+
"hidden_size": 1024,
|
| 129 |
+
"id2label": {
|
| 130 |
+
"0": "LABEL_0",
|
| 131 |
+
"1": "LABEL_1"
|
| 132 |
+
},
|
| 133 |
+
"image_size": 448,
|
| 134 |
+
"initializer_factor": 1.0,
|
| 135 |
+
"initializer_range": 0.02,
|
| 136 |
+
"intermediate_size": 4096,
|
| 137 |
+
"is_decoder": false,
|
| 138 |
+
"is_encoder_decoder": false,
|
| 139 |
+
"label2id": {
|
| 140 |
+
"LABEL_0": 0,
|
| 141 |
+
"LABEL_1": 1
|
| 142 |
+
},
|
| 143 |
+
"layer_norm_eps": 1e-06,
|
| 144 |
+
"length_penalty": 1.0,
|
| 145 |
+
"max_length": 20,
|
| 146 |
+
"min_length": 0,
|
| 147 |
+
"model_type": "mplug_owl_vision_model",
|
| 148 |
+
"no_repeat_ngram_size": 0,
|
| 149 |
+
"num_attention_heads": 16,
|
| 150 |
+
"num_beam_groups": 1,
|
| 151 |
+
"num_beams": 1,
|
| 152 |
+
"num_channels": 3,
|
| 153 |
+
"num_hidden_layers": 24,
|
| 154 |
+
"num_return_sequences": 1,
|
| 155 |
+
"output_attentions": false,
|
| 156 |
+
"output_hidden_states": false,
|
| 157 |
+
"output_scores": false,
|
| 158 |
+
"pad_token_id": null,
|
| 159 |
+
"patch_size": 14,
|
| 160 |
+
"prefix": null,
|
| 161 |
+
"problem_type": null,
|
| 162 |
+
"projection_dim": 768,
|
| 163 |
+
"pruned_heads": {},
|
| 164 |
+
"remove_invalid_values": false,
|
| 165 |
+
"repetition_penalty": 1.0,
|
| 166 |
+
"return_dict": true,
|
| 167 |
+
"return_dict_in_generate": false,
|
| 168 |
+
"sep_token_id": null,
|
| 169 |
+
"suppress_tokens": null,
|
| 170 |
+
"task_specific_params": null,
|
| 171 |
+
"temperature": 1.0,
|
| 172 |
+
"tf_legacy_loss": false,
|
| 173 |
+
"tie_encoder_decoder": false,
|
| 174 |
+
"tie_word_embeddings": true,
|
| 175 |
+
"tokenizer_class": null,
|
| 176 |
+
"top_k": 50,
|
| 177 |
+
"top_p": 1.0,
|
| 178 |
+
"torch_dtype": null,
|
| 179 |
+
"torchscript": false,
|
| 180 |
+
"transformers_version": "4.28.1",
|
| 181 |
+
"typical_p": 1.0,
|
| 182 |
+
"use_bfloat16": false,
|
| 183 |
+
"use_flash_attn": false
|
| 184 |
+
}
|
| 185 |
+
},
|
| 186 |
+
"vocab_size": 32000
|
| 187 |
+
}
|
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-00001-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6340b556bfca09547de39f1a4bee6d09c2dec05d67653d583ad19c818a7103b
|
| 3 |
+
size 4981108780
|
pytorch_model-00002-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b44b169ef7232790f0954a0a6b7d0970f458ac5fb2c7e21f4052ff92ad4afac
|
| 3 |
+
size 4920293259
|
pytorch_model-00003-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac4fccd4bc28bf22351f4d7c076b64050d4c8db5e7fc2ed78de2f9809982d8b7
|
| 3 |
+
size 4989532454
|
pytorch_model-00004-of-00004.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e802d0c59c195aab6b86e08bd0c52af86fd2d8d2714014139e31aa49ca9f744d
|
| 3 |
+
size 1518469929
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,869 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16409100288
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00004-of-00004.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 9 |
+
"model.layers.0.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 14 |
+
"model.layers.0.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 16 |
+
"model.layers.0.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 17 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 21 |
+
"model.layers.1.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 22 |
+
"model.layers.1.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 23 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 24 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 25 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 26 |
+
"model.layers.1.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 27 |
+
"model.layers.1.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 28 |
+
"model.layers.1.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 29 |
+
"model.layers.1.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 30 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 31 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 33 |
+
"model.layers.1.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 34 |
+
"model.layers.10.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 35 |
+
"model.layers.10.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 36 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 37 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 38 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 39 |
+
"model.layers.10.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 40 |
+
"model.layers.10.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 41 |
+
"model.layers.10.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 42 |
+
"model.layers.10.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 43 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 44 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 45 |
+
"model.layers.10.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 46 |
+
"model.layers.10.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 47 |
+
"model.layers.11.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 48 |
+
"model.layers.11.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 49 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 50 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 51 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 52 |
+
"model.layers.11.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 53 |
+
"model.layers.11.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 54 |
+
"model.layers.11.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 55 |
+
"model.layers.11.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 56 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 57 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 58 |
+
"model.layers.11.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 59 |
+
"model.layers.11.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 60 |
+
"model.layers.12.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 61 |
+
"model.layers.12.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 62 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 63 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 64 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 65 |
+
"model.layers.12.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 66 |
+
"model.layers.12.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 67 |
+
"model.layers.12.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 68 |
+
"model.layers.12.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 69 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 70 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 71 |
+
"model.layers.12.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 72 |
+
"model.layers.12.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 73 |
+
"model.layers.13.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 74 |
+
"model.layers.13.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 75 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 76 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 77 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 78 |
+
"model.layers.13.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 79 |
+
"model.layers.13.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 80 |
+
"model.layers.13.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 81 |
+
"model.layers.13.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 82 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 83 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 84 |
+
"model.layers.13.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 85 |
+
"model.layers.13.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 86 |
+
"model.layers.14.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 87 |
+
"model.layers.14.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 88 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 89 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 90 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 91 |
+
"model.layers.14.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 92 |
+
"model.layers.14.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 93 |
+
"model.layers.14.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 94 |
+
"model.layers.14.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 95 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 96 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 97 |
+
"model.layers.14.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 98 |
+
"model.layers.14.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 99 |
+
"model.layers.15.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 100 |
+
"model.layers.15.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 101 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 102 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 103 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 104 |
+
"model.layers.15.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 105 |
+
"model.layers.15.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 106 |
+
"model.layers.15.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 107 |
+
"model.layers.15.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 108 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 109 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 110 |
+
"model.layers.15.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 111 |
+
"model.layers.15.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 112 |
+
"model.layers.16.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 113 |
+
"model.layers.16.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 114 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 115 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 116 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 117 |
+
"model.layers.16.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 118 |
+
"model.layers.16.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 119 |
+
"model.layers.16.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 120 |
+
"model.layers.16.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 121 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 122 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 123 |
+
"model.layers.16.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 124 |
+
"model.layers.16.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 125 |
+
"model.layers.17.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 126 |
+
"model.layers.17.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 127 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 128 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 129 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 130 |
+
"model.layers.17.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 131 |
+
"model.layers.17.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 132 |
+
"model.layers.17.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 133 |
+
"model.layers.17.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 134 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 135 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 136 |
+
"model.layers.17.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 137 |
+
"model.layers.17.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 138 |
+
"model.layers.18.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 139 |
+
"model.layers.18.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 140 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 141 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 142 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 143 |
+
"model.layers.18.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 144 |
+
"model.layers.18.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 145 |
+
"model.layers.18.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 146 |
+
"model.layers.18.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 147 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 148 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 149 |
+
"model.layers.18.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 150 |
+
"model.layers.18.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 151 |
+
"model.layers.19.input_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 152 |
+
"model.layers.19.input_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 153 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 154 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 155 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 156 |
+
"model.layers.19.post_attention_layernorm.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 157 |
+
"model.layers.19.post_attention_layernorm.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 158 |
+
"model.layers.19.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 159 |
+
"model.layers.19.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 160 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 161 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 162 |
+
"model.layers.19.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 163 |
+
"model.layers.19.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 164 |
+
"model.layers.2.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 165 |
+
"model.layers.2.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 166 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 167 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 168 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 169 |
+
"model.layers.2.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 170 |
+
"model.layers.2.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 171 |
+
"model.layers.2.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 172 |
+
"model.layers.2.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 173 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 174 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 175 |
+
"model.layers.2.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 176 |
+
"model.layers.2.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 177 |
+
"model.layers.20.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 178 |
+
"model.layers.20.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 179 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 180 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 181 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 182 |
+
"model.layers.20.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 183 |
+
"model.layers.20.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 184 |
+
"model.layers.20.self_attn.k_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 185 |
+
"model.layers.20.self_attn.k_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 186 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 187 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
|
| 188 |
+
"model.layers.20.self_attn.v_proj.multiway.0.weight": "pytorch_model-00002-of-00004.bin",
|
| 189 |
+
"model.layers.20.self_attn.v_proj.multiway.1.weight": "pytorch_model-00002-of-00004.bin",
|
| 190 |
+
"model.layers.21.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 191 |
+
"model.layers.21.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 192 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 193 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 194 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 195 |
+
"model.layers.21.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 196 |
+
"model.layers.21.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 197 |
+
"model.layers.21.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 198 |
+
"model.layers.21.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 199 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 200 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 201 |
+
"model.layers.21.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 202 |
+
"model.layers.21.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 203 |
+
"model.layers.22.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 204 |
+
"model.layers.22.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 205 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 206 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 207 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 208 |
+
"model.layers.22.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 209 |
+
"model.layers.22.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 210 |
+
"model.layers.22.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 211 |
+
"model.layers.22.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 212 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 213 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 214 |
+
"model.layers.22.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 215 |
+
"model.layers.22.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 216 |
+
"model.layers.23.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 217 |
+
"model.layers.23.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 218 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 219 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 220 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 221 |
+
"model.layers.23.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 222 |
+
"model.layers.23.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 223 |
+
"model.layers.23.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 224 |
+
"model.layers.23.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 225 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 226 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 227 |
+
"model.layers.23.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 228 |
+
"model.layers.23.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 229 |
+
"model.layers.24.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 230 |
+
"model.layers.24.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 231 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 232 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 233 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 234 |
+
"model.layers.24.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 235 |
+
"model.layers.24.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 236 |
+
"model.layers.24.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 237 |
+
"model.layers.24.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 238 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 239 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 240 |
+
"model.layers.24.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 241 |
+
"model.layers.24.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 242 |
+
"model.layers.25.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 243 |
+
"model.layers.25.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 244 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 245 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 246 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 247 |
+
"model.layers.25.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 248 |
+
"model.layers.25.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 249 |
+
"model.layers.25.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 250 |
+
"model.layers.25.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 251 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 252 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 253 |
+
"model.layers.25.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 254 |
+
"model.layers.25.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 255 |
+
"model.layers.26.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 256 |
+
"model.layers.26.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 257 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 258 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 259 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 260 |
+
"model.layers.26.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 261 |
+
"model.layers.26.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 262 |
+
"model.layers.26.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 263 |
+
"model.layers.26.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 264 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 265 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 266 |
+
"model.layers.26.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 267 |
+
"model.layers.26.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 268 |
+
"model.layers.27.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 269 |
+
"model.layers.27.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 270 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 271 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 272 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 273 |
+
"model.layers.27.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 274 |
+
"model.layers.27.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 275 |
+
"model.layers.27.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 276 |
+
"model.layers.27.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 277 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 278 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 279 |
+
"model.layers.27.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 280 |
+
"model.layers.27.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 281 |
+
"model.layers.28.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 282 |
+
"model.layers.28.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 283 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 284 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 285 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 286 |
+
"model.layers.28.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 287 |
+
"model.layers.28.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 288 |
+
"model.layers.28.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 289 |
+
"model.layers.28.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 290 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 291 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 292 |
+
"model.layers.28.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 293 |
+
"model.layers.28.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 294 |
+
"model.layers.29.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 295 |
+
"model.layers.29.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 296 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 297 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 298 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 299 |
+
"model.layers.29.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 300 |
+
"model.layers.29.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 301 |
+
"model.layers.29.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 302 |
+
"model.layers.29.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 303 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 304 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 305 |
+
"model.layers.29.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 306 |
+
"model.layers.29.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 307 |
+
"model.layers.3.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 308 |
+
"model.layers.3.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 309 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 310 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 311 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 312 |
+
"model.layers.3.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 313 |
+
"model.layers.3.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 314 |
+
"model.layers.3.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 315 |
+
"model.layers.3.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 316 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 317 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 318 |
+
"model.layers.3.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 319 |
+
"model.layers.3.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 320 |
+
"model.layers.30.input_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 321 |
+
"model.layers.30.input_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 322 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 323 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 324 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 325 |
+
"model.layers.30.post_attention_layernorm.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 326 |
+
"model.layers.30.post_attention_layernorm.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 327 |
+
"model.layers.30.self_attn.k_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 328 |
+
"model.layers.30.self_attn.k_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 329 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 330 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
|
| 331 |
+
"model.layers.30.self_attn.v_proj.multiway.0.weight": "pytorch_model-00003-of-00004.bin",
|
| 332 |
+
"model.layers.30.self_attn.v_proj.multiway.1.weight": "pytorch_model-00003-of-00004.bin",
|
| 333 |
+
"model.layers.31.input_layernorm.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
|
| 334 |
+
"model.layers.31.input_layernorm.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
|
| 335 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 336 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 337 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 338 |
+
"model.layers.31.post_attention_layernorm.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
|
| 339 |
+
"model.layers.31.post_attention_layernorm.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
|
| 340 |
+
"model.layers.31.self_attn.k_proj.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
|
| 341 |
+
"model.layers.31.self_attn.k_proj.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
|
| 342 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 343 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 344 |
+
"model.layers.31.self_attn.v_proj.multiway.0.weight": "pytorch_model-00004-of-00004.bin",
|
| 345 |
+
"model.layers.31.self_attn.v_proj.multiway.1.weight": "pytorch_model-00004-of-00004.bin",
|
| 346 |
+
"model.layers.4.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 347 |
+
"model.layers.4.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 348 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 349 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 350 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 351 |
+
"model.layers.4.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 352 |
+
"model.layers.4.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 353 |
+
"model.layers.4.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 354 |
+
"model.layers.4.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 355 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 356 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 357 |
+
"model.layers.4.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 358 |
+
"model.layers.4.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 359 |
+
"model.layers.5.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 360 |
+
"model.layers.5.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 361 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 362 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 363 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 364 |
+
"model.layers.5.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 365 |
+
"model.layers.5.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 366 |
+
"model.layers.5.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 367 |
+
"model.layers.5.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 368 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 369 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 370 |
+
"model.layers.5.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 371 |
+
"model.layers.5.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 372 |
+
"model.layers.6.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 373 |
+
"model.layers.6.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 374 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 375 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 376 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 377 |
+
"model.layers.6.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 378 |
+
"model.layers.6.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 379 |
+
"model.layers.6.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 380 |
+
"model.layers.6.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 381 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 382 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 383 |
+
"model.layers.6.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 384 |
+
"model.layers.6.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 385 |
+
"model.layers.7.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 386 |
+
"model.layers.7.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 387 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 388 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 389 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 390 |
+
"model.layers.7.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 391 |
+
"model.layers.7.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 392 |
+
"model.layers.7.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 393 |
+
"model.layers.7.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 394 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 395 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 396 |
+
"model.layers.7.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 397 |
+
"model.layers.7.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 398 |
+
"model.layers.8.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 399 |
+
"model.layers.8.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 400 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 401 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 402 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 403 |
+
"model.layers.8.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 404 |
+
"model.layers.8.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 405 |
+
"model.layers.8.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 406 |
+
"model.layers.8.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 407 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 408 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 409 |
+
"model.layers.8.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 410 |
+
"model.layers.8.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 411 |
+
"model.layers.9.input_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 412 |
+
"model.layers.9.input_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 413 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 414 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 415 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 416 |
+
"model.layers.9.post_attention_layernorm.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 417 |
+
"model.layers.9.post_attention_layernorm.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 418 |
+
"model.layers.9.self_attn.k_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 419 |
+
"model.layers.9.self_attn.k_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 420 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 421 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
|
| 422 |
+
"model.layers.9.self_attn.v_proj.multiway.0.weight": "pytorch_model-00001-of-00004.bin",
|
| 423 |
+
"model.layers.9.self_attn.v_proj.multiway.1.weight": "pytorch_model-00001-of-00004.bin",
|
| 424 |
+
"model.norm.weight": "pytorch_model-00004-of-00004.bin",
|
| 425 |
+
"model.vision_model.embeddings.cls_token": "pytorch_model-00004-of-00004.bin",
|
| 426 |
+
"model.vision_model.embeddings.patch_embed.weight": "pytorch_model-00004-of-00004.bin",
|
| 427 |
+
"model.vision_model.embeddings.position_embedding": "pytorch_model-00004-of-00004.bin",
|
| 428 |
+
"model.vision_model.embeddings.pre_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 429 |
+
"model.vision_model.embeddings.pre_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 430 |
+
"model.vision_model.encoder.layers.0.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 431 |
+
"model.vision_model.encoder.layers.0.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 432 |
+
"model.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 433 |
+
"model.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 434 |
+
"model.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 435 |
+
"model.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 436 |
+
"model.vision_model.encoder.layers.0.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 437 |
+
"model.vision_model.encoder.layers.0.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 438 |
+
"model.vision_model.encoder.layers.0.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 439 |
+
"model.vision_model.encoder.layers.0.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 440 |
+
"model.vision_model.encoder.layers.0.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 441 |
+
"model.vision_model.encoder.layers.0.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 442 |
+
"model.vision_model.encoder.layers.1.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 443 |
+
"model.vision_model.encoder.layers.1.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 444 |
+
"model.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 445 |
+
"model.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 446 |
+
"model.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 447 |
+
"model.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 448 |
+
"model.vision_model.encoder.layers.1.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 449 |
+
"model.vision_model.encoder.layers.1.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 450 |
+
"model.vision_model.encoder.layers.1.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 451 |
+
"model.vision_model.encoder.layers.1.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 452 |
+
"model.vision_model.encoder.layers.1.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 453 |
+
"model.vision_model.encoder.layers.1.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 454 |
+
"model.vision_model.encoder.layers.10.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 455 |
+
"model.vision_model.encoder.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 456 |
+
"model.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 457 |
+
"model.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 458 |
+
"model.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 459 |
+
"model.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 460 |
+
"model.vision_model.encoder.layers.10.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 461 |
+
"model.vision_model.encoder.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 462 |
+
"model.vision_model.encoder.layers.10.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 463 |
+
"model.vision_model.encoder.layers.10.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 464 |
+
"model.vision_model.encoder.layers.10.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 465 |
+
"model.vision_model.encoder.layers.10.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 466 |
+
"model.vision_model.encoder.layers.11.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 467 |
+
"model.vision_model.encoder.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 468 |
+
"model.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 469 |
+
"model.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 470 |
+
"model.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 471 |
+
"model.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 472 |
+
"model.vision_model.encoder.layers.11.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 473 |
+
"model.vision_model.encoder.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 474 |
+
"model.vision_model.encoder.layers.11.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 475 |
+
"model.vision_model.encoder.layers.11.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 476 |
+
"model.vision_model.encoder.layers.11.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 477 |
+
"model.vision_model.encoder.layers.11.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 478 |
+
"model.vision_model.encoder.layers.12.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 479 |
+
"model.vision_model.encoder.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 480 |
+
"model.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 481 |
+
"model.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 482 |
+
"model.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 483 |
+
"model.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 484 |
+
"model.vision_model.encoder.layers.12.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 485 |
+
"model.vision_model.encoder.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 486 |
+
"model.vision_model.encoder.layers.12.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 487 |
+
"model.vision_model.encoder.layers.12.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 488 |
+
"model.vision_model.encoder.layers.12.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 489 |
+
"model.vision_model.encoder.layers.12.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 490 |
+
"model.vision_model.encoder.layers.13.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 491 |
+
"model.vision_model.encoder.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 492 |
+
"model.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 493 |
+
"model.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 494 |
+
"model.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 495 |
+
"model.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 496 |
+
"model.vision_model.encoder.layers.13.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 497 |
+
"model.vision_model.encoder.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 498 |
+
"model.vision_model.encoder.layers.13.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 499 |
+
"model.vision_model.encoder.layers.13.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 500 |
+
"model.vision_model.encoder.layers.13.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 501 |
+
"model.vision_model.encoder.layers.13.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 502 |
+
"model.vision_model.encoder.layers.14.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 503 |
+
"model.vision_model.encoder.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 504 |
+
"model.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 505 |
+
"model.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 506 |
+
"model.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 507 |
+
"model.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 508 |
+
"model.vision_model.encoder.layers.14.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 509 |
+
"model.vision_model.encoder.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 510 |
+
"model.vision_model.encoder.layers.14.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 511 |
+
"model.vision_model.encoder.layers.14.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 512 |
+
"model.vision_model.encoder.layers.14.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 513 |
+
"model.vision_model.encoder.layers.14.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 514 |
+
"model.vision_model.encoder.layers.15.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 515 |
+
"model.vision_model.encoder.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 516 |
+
"model.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 517 |
+
"model.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 518 |
+
"model.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 519 |
+
"model.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 520 |
+
"model.vision_model.encoder.layers.15.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 521 |
+
"model.vision_model.encoder.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 522 |
+
"model.vision_model.encoder.layers.15.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 523 |
+
"model.vision_model.encoder.layers.15.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 524 |
+
"model.vision_model.encoder.layers.15.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 525 |
+
"model.vision_model.encoder.layers.15.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 526 |
+
"model.vision_model.encoder.layers.16.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 527 |
+
"model.vision_model.encoder.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 528 |
+
"model.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 529 |
+
"model.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 530 |
+
"model.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 531 |
+
"model.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 532 |
+
"model.vision_model.encoder.layers.16.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 533 |
+
"model.vision_model.encoder.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 534 |
+
"model.vision_model.encoder.layers.16.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 535 |
+
"model.vision_model.encoder.layers.16.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 536 |
+
"model.vision_model.encoder.layers.16.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 537 |
+
"model.vision_model.encoder.layers.16.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 538 |
+
"model.vision_model.encoder.layers.17.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 539 |
+
"model.vision_model.encoder.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 540 |
+
"model.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 541 |
+
"model.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 542 |
+
"model.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 543 |
+
"model.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 544 |
+
"model.vision_model.encoder.layers.17.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 545 |
+
"model.vision_model.encoder.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 546 |
+
"model.vision_model.encoder.layers.17.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 547 |
+
"model.vision_model.encoder.layers.17.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 548 |
+
"model.vision_model.encoder.layers.17.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 549 |
+
"model.vision_model.encoder.layers.17.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 550 |
+
"model.vision_model.encoder.layers.18.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 551 |
+
"model.vision_model.encoder.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 552 |
+
"model.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 553 |
+
"model.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 554 |
+
"model.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 555 |
+
"model.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 556 |
+
"model.vision_model.encoder.layers.18.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 557 |
+
"model.vision_model.encoder.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 558 |
+
"model.vision_model.encoder.layers.18.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 559 |
+
"model.vision_model.encoder.layers.18.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 560 |
+
"model.vision_model.encoder.layers.18.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 561 |
+
"model.vision_model.encoder.layers.18.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 562 |
+
"model.vision_model.encoder.layers.19.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 563 |
+
"model.vision_model.encoder.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 564 |
+
"model.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 565 |
+
"model.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 566 |
+
"model.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 567 |
+
"model.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 568 |
+
"model.vision_model.encoder.layers.19.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 569 |
+
"model.vision_model.encoder.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 570 |
+
"model.vision_model.encoder.layers.19.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 571 |
+
"model.vision_model.encoder.layers.19.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 572 |
+
"model.vision_model.encoder.layers.19.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 573 |
+
"model.vision_model.encoder.layers.19.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 574 |
+
"model.vision_model.encoder.layers.2.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 575 |
+
"model.vision_model.encoder.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 576 |
+
"model.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 577 |
+
"model.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 578 |
+
"model.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 579 |
+
"model.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 580 |
+
"model.vision_model.encoder.layers.2.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 581 |
+
"model.vision_model.encoder.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 582 |
+
"model.vision_model.encoder.layers.2.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 583 |
+
"model.vision_model.encoder.layers.2.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 584 |
+
"model.vision_model.encoder.layers.2.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 585 |
+
"model.vision_model.encoder.layers.2.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 586 |
+
"model.vision_model.encoder.layers.20.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 587 |
+
"model.vision_model.encoder.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 588 |
+
"model.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 589 |
+
"model.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 590 |
+
"model.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 591 |
+
"model.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 592 |
+
"model.vision_model.encoder.layers.20.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 593 |
+
"model.vision_model.encoder.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 594 |
+
"model.vision_model.encoder.layers.20.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 595 |
+
"model.vision_model.encoder.layers.20.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 596 |
+
"model.vision_model.encoder.layers.20.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 597 |
+
"model.vision_model.encoder.layers.20.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 598 |
+
"model.vision_model.encoder.layers.21.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 599 |
+
"model.vision_model.encoder.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 600 |
+
"model.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 601 |
+
"model.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 602 |
+
"model.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 603 |
+
"model.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 604 |
+
"model.vision_model.encoder.layers.21.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 605 |
+
"model.vision_model.encoder.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 606 |
+
"model.vision_model.encoder.layers.21.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 607 |
+
"model.vision_model.encoder.layers.21.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 608 |
+
"model.vision_model.encoder.layers.21.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 609 |
+
"model.vision_model.encoder.layers.21.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 610 |
+
"model.vision_model.encoder.layers.22.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 611 |
+
"model.vision_model.encoder.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 612 |
+
"model.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 613 |
+
"model.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 614 |
+
"model.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 615 |
+
"model.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 616 |
+
"model.vision_model.encoder.layers.22.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 617 |
+
"model.vision_model.encoder.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 618 |
+
"model.vision_model.encoder.layers.22.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 619 |
+
"model.vision_model.encoder.layers.22.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 620 |
+
"model.vision_model.encoder.layers.22.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 621 |
+
"model.vision_model.encoder.layers.22.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 622 |
+
"model.vision_model.encoder.layers.23.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 623 |
+
"model.vision_model.encoder.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 624 |
+
"model.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 625 |
+
"model.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 626 |
+
"model.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 627 |
+
"model.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 628 |
+
"model.vision_model.encoder.layers.23.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 629 |
+
"model.vision_model.encoder.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 630 |
+
"model.vision_model.encoder.layers.23.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 631 |
+
"model.vision_model.encoder.layers.23.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 632 |
+
"model.vision_model.encoder.layers.23.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 633 |
+
"model.vision_model.encoder.layers.23.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 634 |
+
"model.vision_model.encoder.layers.3.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 635 |
+
"model.vision_model.encoder.layers.3.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 636 |
+
"model.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 637 |
+
"model.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 638 |
+
"model.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 639 |
+
"model.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 640 |
+
"model.vision_model.encoder.layers.3.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 641 |
+
"model.vision_model.encoder.layers.3.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 642 |
+
"model.vision_model.encoder.layers.3.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 643 |
+
"model.vision_model.encoder.layers.3.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 644 |
+
"model.vision_model.encoder.layers.3.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 645 |
+
"model.vision_model.encoder.layers.3.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 646 |
+
"model.vision_model.encoder.layers.4.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 647 |
+
"model.vision_model.encoder.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 648 |
+
"model.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 649 |
+
"model.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 650 |
+
"model.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 651 |
+
"model.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 652 |
+
"model.vision_model.encoder.layers.4.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 653 |
+
"model.vision_model.encoder.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 654 |
+
"model.vision_model.encoder.layers.4.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 655 |
+
"model.vision_model.encoder.layers.4.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 656 |
+
"model.vision_model.encoder.layers.4.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 657 |
+
"model.vision_model.encoder.layers.4.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 658 |
+
"model.vision_model.encoder.layers.5.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 659 |
+
"model.vision_model.encoder.layers.5.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 660 |
+
"model.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 661 |
+
"model.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 662 |
+
"model.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 663 |
+
"model.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 664 |
+
"model.vision_model.encoder.layers.5.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 665 |
+
"model.vision_model.encoder.layers.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 666 |
+
"model.vision_model.encoder.layers.5.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 667 |
+
"model.vision_model.encoder.layers.5.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 668 |
+
"model.vision_model.encoder.layers.5.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 669 |
+
"model.vision_model.encoder.layers.5.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 670 |
+
"model.vision_model.encoder.layers.6.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 671 |
+
"model.vision_model.encoder.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 672 |
+
"model.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 673 |
+
"model.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 674 |
+
"model.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 675 |
+
"model.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 676 |
+
"model.vision_model.encoder.layers.6.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 677 |
+
"model.vision_model.encoder.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 678 |
+
"model.vision_model.encoder.layers.6.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 679 |
+
"model.vision_model.encoder.layers.6.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 680 |
+
"model.vision_model.encoder.layers.6.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 681 |
+
"model.vision_model.encoder.layers.6.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 682 |
+
"model.vision_model.encoder.layers.7.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 683 |
+
"model.vision_model.encoder.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 684 |
+
"model.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 685 |
+
"model.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 686 |
+
"model.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 687 |
+
"model.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 688 |
+
"model.vision_model.encoder.layers.7.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 689 |
+
"model.vision_model.encoder.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 690 |
+
"model.vision_model.encoder.layers.7.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 691 |
+
"model.vision_model.encoder.layers.7.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 692 |
+
"model.vision_model.encoder.layers.7.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 693 |
+
"model.vision_model.encoder.layers.7.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 694 |
+
"model.vision_model.encoder.layers.8.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 695 |
+
"model.vision_model.encoder.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 696 |
+
"model.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 697 |
+
"model.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 698 |
+
"model.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 699 |
+
"model.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 700 |
+
"model.vision_model.encoder.layers.8.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 701 |
+
"model.vision_model.encoder.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 702 |
+
"model.vision_model.encoder.layers.8.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 703 |
+
"model.vision_model.encoder.layers.8.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 704 |
+
"model.vision_model.encoder.layers.8.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 705 |
+
"model.vision_model.encoder.layers.8.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 706 |
+
"model.vision_model.encoder.layers.9.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 707 |
+
"model.vision_model.encoder.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 708 |
+
"model.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00004-of-00004.bin",
|
| 709 |
+
"model.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00004-of-00004.bin",
|
| 710 |
+
"model.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00004-of-00004.bin",
|
| 711 |
+
"model.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00004-of-00004.bin",
|
| 712 |
+
"model.vision_model.encoder.layers.9.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 713 |
+
"model.vision_model.encoder.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 714 |
+
"model.vision_model.encoder.layers.9.self_attn.dense.bias": "pytorch_model-00004-of-00004.bin",
|
| 715 |
+
"model.vision_model.encoder.layers.9.self_attn.dense.weight": "pytorch_model-00004-of-00004.bin",
|
| 716 |
+
"model.vision_model.encoder.layers.9.self_attn.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
|
| 717 |
+
"model.vision_model.encoder.layers.9.self_attn.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
|
| 718 |
+
"model.vision_model.post_layernorm.bias": "pytorch_model-00004-of-00004.bin",
|
| 719 |
+
"model.vision_model.post_layernorm.weight": "pytorch_model-00004-of-00004.bin",
|
| 720 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 721 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
|
| 722 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
|
| 723 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 724 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
|
| 725 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
|
| 726 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
|
| 727 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
|
| 728 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
|
| 729 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
|
| 730 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
|
| 731 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
|
| 732 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
|
| 733 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
|
| 734 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
|
| 735 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
|
| 736 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
|
| 737 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
|
| 738 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
|
| 739 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
|
| 740 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
|
| 741 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
|
| 742 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 743 |
+
"model.visual_abstractor.encoder.layers.0.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 744 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 745 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
|
| 746 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
|
| 747 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 748 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
|
| 749 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
|
| 750 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
|
| 751 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
|
| 752 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
|
| 753 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
|
| 754 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
|
| 755 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
|
| 756 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
|
| 757 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
|
| 758 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
|
| 759 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
|
| 760 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
|
| 761 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
|
| 762 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
|
| 763 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
|
| 764 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
|
| 765 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
|
| 766 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 767 |
+
"model.visual_abstractor.encoder.layers.1.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 768 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 769 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
|
| 770 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
|
| 771 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 772 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
|
| 773 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
|
| 774 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
|
| 775 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
|
| 776 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
|
| 777 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
|
| 778 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
|
| 779 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
|
| 780 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
|
| 781 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
|
| 782 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
|
| 783 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
|
| 784 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
|
| 785 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
|
| 786 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
|
| 787 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
|
| 788 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
|
| 789 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
|
| 790 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 791 |
+
"model.visual_abstractor.encoder.layers.2.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 792 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 793 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
|
| 794 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
|
| 795 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 796 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
|
| 797 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
|
| 798 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
|
| 799 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
|
| 800 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
|
| 801 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
|
| 802 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
|
| 803 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
|
| 804 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
|
| 805 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
|
| 806 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
|
| 807 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
|
| 808 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
|
| 809 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
|
| 810 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
|
| 811 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
|
| 812 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
|
| 813 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
|
| 814 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 815 |
+
"model.visual_abstractor.encoder.layers.3.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 816 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 817 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
|
| 818 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
|
| 819 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 820 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
|
| 821 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
|
| 822 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
|
| 823 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
|
| 824 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
|
| 825 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
|
| 826 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
|
| 827 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
|
| 828 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
|
| 829 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
|
| 830 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
|
| 831 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
|
| 832 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
|
| 833 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
|
| 834 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
|
| 835 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
|
| 836 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
|
| 837 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
|
| 838 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 839 |
+
"model.visual_abstractor.encoder.layers.4.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 840 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.k_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 841 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.key.bias": "pytorch_model-00004-of-00004.bin",
|
| 842 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.key.weight": "pytorch_model-00004-of-00004.bin",
|
| 843 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.q_pos_embed": "pytorch_model-00004-of-00004.bin",
|
| 844 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.query.bias": "pytorch_model-00004-of-00004.bin",
|
| 845 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.query.weight": "pytorch_model-00004-of-00004.bin",
|
| 846 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.value.bias": "pytorch_model-00004-of-00004.bin",
|
| 847 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.attention.value.weight": "pytorch_model-00004-of-00004.bin",
|
| 848 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.norm1.bias": "pytorch_model-00004-of-00004.bin",
|
| 849 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.norm1.weight": "pytorch_model-00004-of-00004.bin",
|
| 850 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.normk.bias": "pytorch_model-00004-of-00004.bin",
|
| 851 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.normk.weight": "pytorch_model-00004-of-00004.bin",
|
| 852 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.ffn_ln.bias": "pytorch_model-00004-of-00004.bin",
|
| 853 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.ffn_ln.weight": "pytorch_model-00004-of-00004.bin",
|
| 854 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w1.bias": "pytorch_model-00004-of-00004.bin",
|
| 855 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w1.weight": "pytorch_model-00004-of-00004.bin",
|
| 856 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w2.bias": "pytorch_model-00004-of-00004.bin",
|
| 857 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w2.weight": "pytorch_model-00004-of-00004.bin",
|
| 858 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w3.bias": "pytorch_model-00004-of-00004.bin",
|
| 859 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.mlp.w3.weight": "pytorch_model-00004-of-00004.bin",
|
| 860 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.norm2.bias": "pytorch_model-00004-of-00004.bin",
|
| 861 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.norm2.weight": "pytorch_model-00004-of-00004.bin",
|
| 862 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.out_proj.bias": "pytorch_model-00004-of-00004.bin",
|
| 863 |
+
"model.visual_abstractor.encoder.layers.5.crossattention.output.out_proj.weight": "pytorch_model-00004-of-00004.bin",
|
| 864 |
+
"model.visual_abstractor.query_embeds": "pytorch_model-00004-of-00004.bin",
|
| 865 |
+
"model.visual_abstractor.visual_fc.bias": "pytorch_model-00004-of-00004.bin",
|
| 866 |
+
"model.visual_abstractor.visual_fc.weight": "pytorch_model-00004-of-00004.bin",
|
| 867 |
+
"model.visual_abstractor.vit_eos": "pytorch_model-00004-of-00004.bin"
|
| 868 |
+
}
|
| 869 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.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 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"bos_token": "<s>",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"legacy": false,
|
| 34 |
+
"model_max_length": 2048,
|
| 35 |
+
"pad_token": "<unk>",
|
| 36 |
+
"padding_side": "right",
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"spaces_between_special_tokens": false,
|
| 39 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"unk_token": "<unk>",
|
| 41 |
+
"use_default_system_prompt": false
|
| 42 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,606 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 96,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 6.666666666666667e-06,
|
| 14 |
+
"loss": 0.9785,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.12,
|
| 19 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 20 |
+
"loss": 1.0381,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.19,
|
| 25 |
+
"learning_rate": 2e-05,
|
| 26 |
+
"loss": 0.5466,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.25,
|
| 31 |
+
"learning_rate": 1.999429490929718e-05,
|
| 32 |
+
"loss": 2.5332,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.31,
|
| 37 |
+
"learning_rate": 1.9977186146800707e-05,
|
| 38 |
+
"loss": 0.4666,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.38,
|
| 43 |
+
"learning_rate": 1.994869323391895e-05,
|
| 44 |
+
"loss": 0.2064,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.44,
|
| 49 |
+
"learning_rate": 1.990884868158239e-05,
|
| 50 |
+
"loss": 0.2202,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5,
|
| 55 |
+
"learning_rate": 1.985769795314804e-05,
|
| 56 |
+
"loss": 0.1354,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.56,
|
| 61 |
+
"learning_rate": 1.9795299412524948e-05,
|
| 62 |
+
"loss": 0.2023,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.62,
|
| 67 |
+
"learning_rate": 1.9721724257579907e-05,
|
| 68 |
+
"loss": 0.1093,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.69,
|
| 73 |
+
"learning_rate": 1.963705643889941e-05,
|
| 74 |
+
"loss": 0.126,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.75,
|
| 79 |
+
"learning_rate": 1.954139256400049e-05,
|
| 80 |
+
"loss": 0.1307,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.81,
|
| 85 |
+
"learning_rate": 1.9434841787099804e-05,
|
| 86 |
+
"loss": 0.1108,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.88,
|
| 91 |
+
"learning_rate": 1.9317525684566686e-05,
|
| 92 |
+
"loss": 0.1157,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.94,
|
| 97 |
+
"learning_rate": 1.918957811620231e-05,
|
| 98 |
+
"loss": 0.1541,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.0,
|
| 103 |
+
"learning_rate": 1.9051145072503216e-05,
|
| 104 |
+
"loss": 0.1068,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.06,
|
| 109 |
+
"learning_rate": 1.8902384508083518e-05,
|
| 110 |
+
"loss": 0.1263,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.12,
|
| 115 |
+
"learning_rate": 1.8743466161445823e-05,
|
| 116 |
+
"loss": 0.1382,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.19,
|
| 121 |
+
"learning_rate": 1.857457136130651e-05,
|
| 122 |
+
"loss": 0.1142,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.25,
|
| 127 |
+
"learning_rate": 1.839589281969639e-05,
|
| 128 |
+
"loss": 0.1077,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.31,
|
| 133 |
+
"learning_rate": 1.8207634412072765e-05,
|
| 134 |
+
"loss": 0.116,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.38,
|
| 139 |
+
"learning_rate": 1.8010010944693846e-05,
|
| 140 |
+
"loss": 0.1183,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.44,
|
| 145 |
+
"learning_rate": 1.780324790952092e-05,
|
| 146 |
+
"loss": 0.1205,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.5,
|
| 151 |
+
"learning_rate": 1.758758122692791e-05,
|
| 152 |
+
"loss": 0.1078,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.56,
|
| 157 |
+
"learning_rate": 1.7363256976511972e-05,
|
| 158 |
+
"loss": 0.1143,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.62,
|
| 163 |
+
"learning_rate": 1.7130531116312202e-05,
|
| 164 |
+
"loss": 0.1083,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.69,
|
| 169 |
+
"learning_rate": 1.688966919075687e-05,
|
| 170 |
+
"loss": 0.1096,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.75,
|
| 175 |
+
"learning_rate": 1.6640946027672395e-05,
|
| 176 |
+
"loss": 0.0986,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.81,
|
| 181 |
+
"learning_rate": 1.6384645424699835e-05,
|
| 182 |
+
"loss": 0.11,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.88,
|
| 187 |
+
"learning_rate": 1.612105982547663e-05,
|
| 188 |
+
"loss": 0.0924,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.94,
|
| 193 |
+
"learning_rate": 1.5850489985953076e-05,
|
| 194 |
+
"loss": 0.1262,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.0,
|
| 199 |
+
"learning_rate": 1.5573244631224364e-05,
|
| 200 |
+
"loss": 0.0916,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.06,
|
| 205 |
+
"learning_rate": 1.5289640103269626e-05,
|
| 206 |
+
"loss": 0.0937,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.12,
|
| 211 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 212 |
+
"loss": 0.1017,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.19,
|
| 217 |
+
"learning_rate": 1.4704654806027558e-05,
|
| 218 |
+
"loss": 0.0928,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.25,
|
| 223 |
+
"learning_rate": 1.4403941515576344e-05,
|
| 224 |
+
"loss": 0.1088,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.31,
|
| 229 |
+
"learning_rate": 1.4098203247965876e-05,
|
| 230 |
+
"loss": 0.1034,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.38,
|
| 235 |
+
"learning_rate": 1.3787788856105762e-05,
|
| 236 |
+
"loss": 0.1024,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.44,
|
| 241 |
+
"learning_rate": 1.3473052528448203e-05,
|
| 242 |
+
"loss": 0.0874,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.5,
|
| 247 |
+
"learning_rate": 1.3154353384852559e-05,
|
| 248 |
+
"loss": 0.097,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.56,
|
| 253 |
+
"learning_rate": 1.283205506682304e-05,
|
| 254 |
+
"loss": 0.0948,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.62,
|
| 259 |
+
"learning_rate": 1.2506525322587207e-05,
|
| 260 |
+
"loss": 0.0788,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.69,
|
| 265 |
+
"learning_rate": 1.2178135587488515e-05,
|
| 266 |
+
"loss": 0.087,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.75,
|
| 271 |
+
"learning_rate": 1.1847260560171895e-05,
|
| 272 |
+
"loss": 0.0866,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.81,
|
| 277 |
+
"learning_rate": 1.1514277775045768e-05,
|
| 278 |
+
"loss": 0.0992,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.88,
|
| 283 |
+
"learning_rate": 1.1179567171508463e-05,
|
| 284 |
+
"loss": 0.0916,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.94,
|
| 289 |
+
"learning_rate": 1.0843510660430447e-05,
|
| 290 |
+
"loss": 0.0786,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 3.0,
|
| 295 |
+
"learning_rate": 1.0506491688387128e-05,
|
| 296 |
+
"loss": 0.0915,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 3.06,
|
| 301 |
+
"learning_rate": 1.0168894800139311e-05,
|
| 302 |
+
"loss": 0.0815,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.12,
|
| 307 |
+
"learning_rate": 9.83110519986069e-06,
|
| 308 |
+
"loss": 0.0762,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.19,
|
| 313 |
+
"learning_rate": 9.493508311612874e-06,
|
| 314 |
+
"loss": 0.0908,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 3.25,
|
| 319 |
+
"learning_rate": 9.156489339569555e-06,
|
| 320 |
+
"loss": 0.0753,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.31,
|
| 325 |
+
"learning_rate": 8.820432828491542e-06,
|
| 326 |
+
"loss": 0.0576,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 3.38,
|
| 331 |
+
"learning_rate": 8.485722224954237e-06,
|
| 332 |
+
"loss": 0.0742,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 3.44,
|
| 337 |
+
"learning_rate": 8.15273943982811e-06,
|
| 338 |
+
"loss": 0.0976,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.5,
|
| 343 |
+
"learning_rate": 7.821864412511485e-06,
|
| 344 |
+
"loss": 0.0964,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.56,
|
| 349 |
+
"learning_rate": 7.493474677412795e-06,
|
| 350 |
+
"loss": 0.0894,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.62,
|
| 355 |
+
"learning_rate": 7.16794493317696e-06,
|
| 356 |
+
"loss": 0.0877,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 3.69,
|
| 361 |
+
"learning_rate": 6.845646615147445e-06,
|
| 362 |
+
"loss": 0.0871,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.75,
|
| 367 |
+
"learning_rate": 6.526947471551799e-06,
|
| 368 |
+
"loss": 0.0714,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 3.81,
|
| 373 |
+
"learning_rate": 6.21221114389424e-06,
|
| 374 |
+
"loss": 0.0806,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 3.88,
|
| 379 |
+
"learning_rate": 5.901796752034128e-06,
|
| 380 |
+
"loss": 0.0879,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.94,
|
| 385 |
+
"learning_rate": 5.5960584844236565e-06,
|
| 386 |
+
"loss": 0.0731,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 4.0,
|
| 391 |
+
"learning_rate": 5.295345193972445e-06,
|
| 392 |
+
"loss": 0.0867,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.06,
|
| 397 |
+
"learning_rate": 5.000000000000003e-06,
|
| 398 |
+
"loss": 0.0633,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.12,
|
| 403 |
+
"learning_rate": 4.710359896730379e-06,
|
| 404 |
+
"loss": 0.0632,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 4.19,
|
| 409 |
+
"learning_rate": 4.426755368775637e-06,
|
| 410 |
+
"loss": 0.0824,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 4.25,
|
| 415 |
+
"learning_rate": 4.149510014046922e-06,
|
| 416 |
+
"loss": 0.0883,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 4.31,
|
| 421 |
+
"learning_rate": 3.878940174523371e-06,
|
| 422 |
+
"loss": 0.0598,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 4.38,
|
| 427 |
+
"learning_rate": 3.6153545753001663e-06,
|
| 428 |
+
"loss": 0.0612,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 4.44,
|
| 433 |
+
"learning_rate": 3.3590539723276083e-06,
|
| 434 |
+
"loss": 0.0597,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 4.5,
|
| 439 |
+
"learning_rate": 3.110330809243134e-06,
|
| 440 |
+
"loss": 0.0798,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.56,
|
| 445 |
+
"learning_rate": 2.869468883687798e-06,
|
| 446 |
+
"loss": 0.0694,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 4.62,
|
| 451 |
+
"learning_rate": 2.6367430234880286e-06,
|
| 452 |
+
"loss": 0.0791,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 4.69,
|
| 457 |
+
"learning_rate": 2.4124187730720916e-06,
|
| 458 |
+
"loss": 0.0692,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 4.75,
|
| 463 |
+
"learning_rate": 2.196752090479083e-06,
|
| 464 |
+
"loss": 0.0687,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 4.81,
|
| 469 |
+
"learning_rate": 1.9899890553061565e-06,
|
| 470 |
+
"loss": 0.0582,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 4.88,
|
| 475 |
+
"learning_rate": 1.7923655879272395e-06,
|
| 476 |
+
"loss": 0.056,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 4.94,
|
| 481 |
+
"learning_rate": 1.60410718030361e-06,
|
| 482 |
+
"loss": 0.0554,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 5.0,
|
| 487 |
+
"learning_rate": 1.425428638693489e-06,
|
| 488 |
+
"loss": 0.0484,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 5.06,
|
| 493 |
+
"learning_rate": 1.2565338385541792e-06,
|
| 494 |
+
"loss": 0.0637,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 5.12,
|
| 499 |
+
"learning_rate": 1.097615491916485e-06,
|
| 500 |
+
"loss": 0.0595,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 5.19,
|
| 505 |
+
"learning_rate": 9.488549274967873e-07,
|
| 506 |
+
"loss": 0.0533,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 5.25,
|
| 511 |
+
"learning_rate": 8.10421883797694e-07,
|
| 512 |
+
"loss": 0.0834,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 5.31,
|
| 517 |
+
"learning_rate": 6.824743154333157e-07,
|
| 518 |
+
"loss": 0.0598,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 5.38,
|
| 523 |
+
"learning_rate": 5.651582129001987e-07,
|
| 524 |
+
"loss": 0.0504,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 5.44,
|
| 529 |
+
"learning_rate": 4.5860743599951186e-07,
|
| 530 |
+
"loss": 0.0688,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 5.5,
|
| 535 |
+
"learning_rate": 3.629435611005916e-07,
|
| 536 |
+
"loss": 0.0621,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 5.56,
|
| 541 |
+
"learning_rate": 2.7827574242009434e-07,
|
| 542 |
+
"loss": 0.0482,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 5.62,
|
| 547 |
+
"learning_rate": 2.0470058747505516e-07,
|
| 548 |
+
"loss": 0.0515,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 5.69,
|
| 553 |
+
"learning_rate": 1.4230204685196202e-07,
|
| 554 |
+
"loss": 0.0695,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 5.75,
|
| 559 |
+
"learning_rate": 9.11513184176116e-08,
|
| 560 |
+
"loss": 0.051,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 5.81,
|
| 565 |
+
"learning_rate": 5.1306766081048456e-08,
|
| 566 |
+
"loss": 0.0379,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 5.88,
|
| 571 |
+
"learning_rate": 2.2813853199292745e-08,
|
| 572 |
+
"loss": 0.0565,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 5.94,
|
| 577 |
+
"learning_rate": 5.705090702819993e-09,
|
| 578 |
+
"loss": 0.0524,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 6.0,
|
| 583 |
+
"learning_rate": 0.0,
|
| 584 |
+
"loss": 0.0478,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 6.0,
|
| 589 |
+
"step": 96,
|
| 590 |
+
"total_flos": 2277230247936.0,
|
| 591 |
+
"train_loss": 0.14340813954671225,
|
| 592 |
+
"train_runtime": 691.2623,
|
| 593 |
+
"train_samples_per_second": 8.515,
|
| 594 |
+
"train_steps_per_second": 0.139
|
| 595 |
+
}
|
| 596 |
+
],
|
| 597 |
+
"logging_steps": 1.0,
|
| 598 |
+
"max_steps": 96,
|
| 599 |
+
"num_input_tokens_seen": 0,
|
| 600 |
+
"num_train_epochs": 6,
|
| 601 |
+
"save_steps": 800,
|
| 602 |
+
"total_flos": 2277230247936.0,
|
| 603 |
+
"train_batch_size": 8,
|
| 604 |
+
"trial_name": null,
|
| 605 |
+
"trial_params": null
|
| 606 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:157740e95b0cd56a2da718155747be7ff16e8af811fcfb64b9043f50b87362a0
|
| 3 |
+
size 6139
|