Upload 42 files
Browse files- feature_extractor/preprocessor_config.json +28 -0
- pics/deepfloyd_if_scheme.jpg +0 -0
- pics/fid30k_if.jpg +0 -0
- pics/if_architecture.jpg +0 -0
- pics/loss.jpg +0 -0
- pics/lr.jpg +0 -0
- pics/scheme-h.jpg +0 -0
- safety_checker/config.json +168 -0
- safety_checker/model.fp16.safetensors +3 -0
- safety_checker/model.safetensors +3 -0
- safety_checker/pytorch_model.bin +3 -0
- safety_checker/pytorch_model.fp16.bin +3 -0
- scheduler/scheduler_config.json +17 -0
- text_encoder/config.json +31 -0
- text_encoder/model-00001-of-00002.safetensors +3 -0
- text_encoder/model-00002-of-00002.safetensors +3 -0
- text_encoder/model.8bit.safetensors +3 -0
- text_encoder/model.fp16-00001-of-00002.safetensors +3 -0
- text_encoder/model.fp16-00002-of-00002.safetensors +3 -0
- text_encoder/model.safetensors.index.fp16.json +226 -0
- text_encoder/model.safetensors.index.json +226 -0
- text_encoder/pytorch_model-00001-of-00002.bin +3 -0
- text_encoder/pytorch_model-00002-of-00002.bin +3 -0
- text_encoder/pytorch_model.8bit.bin +3 -0
- text_encoder/pytorch_model.bin.index.fp16.json +226 -0
- text_encoder/pytorch_model.bin.index.json +227 -0
- text_encoder/pytorch_model.fp16-00001-of-00002.bin +3 -0
- text_encoder/pytorch_model.fp16-00002-of-00002.bin +3 -0
- text_encoder/special_tokens_map.json +1 -0
- text_encoder/spiece.model +3 -0
- text_encoder/tokenizer_config.json +1 -0
- tokenizer/special_tokens_map.json +107 -0
- tokenizer/spiece.model +3 -0
- tokenizer/tokenizer_config.json +112 -0
- unet/config.json +60 -0
- unet/diffusion_pytorch_model.bin +3 -0
- unet/diffusion_pytorch_model.fp16.bin +3 -0
- unet/diffusion_pytorch_model.fp16.safetensors +3 -0
- unet/diffusion_pytorch_model.safetensors +3 -0
- watermarker/config.json +4 -0
- watermarker/diffusion_pytorch_model.bin +3 -0
- watermarker/diffusion_pytorch_model.safetensors +3 -0
feature_extractor/preprocessor_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"feature_extractor_type": "CLIPFeatureExtractor",
|
| 12 |
+
"image_mean": [
|
| 13 |
+
0.48145466,
|
| 14 |
+
0.4578275,
|
| 15 |
+
0.40821073
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "CLIPImageProcessor",
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.26862954,
|
| 20 |
+
0.26130258,
|
| 21 |
+
0.27577711
|
| 22 |
+
],
|
| 23 |
+
"resample": 3,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"shortest_edge": 224
|
| 27 |
+
}
|
| 28 |
+
}
|
pics/deepfloyd_if_scheme.jpg
ADDED
|
pics/fid30k_if.jpg
ADDED
|
pics/if_architecture.jpg
ADDED
|
pics/loss.jpg
ADDED
|
pics/lr.jpg
ADDED
|
pics/scheme-h.jpg
ADDED
|
safety_checker/config.json
ADDED
|
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_commit_hash": null,
|
| 3 |
+
"_name_or_path": ".",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"IFSafetyChecker"
|
| 6 |
+
],
|
| 7 |
+
"initializer_factor": 1.0,
|
| 8 |
+
"logit_scale_init_value": 2.6592,
|
| 9 |
+
"model_type": "clip",
|
| 10 |
+
"projection_dim": 768,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"_name_or_path": "",
|
| 13 |
+
"add_cross_attention": false,
|
| 14 |
+
"architectures": null,
|
| 15 |
+
"attention_dropout": 0.0,
|
| 16 |
+
"bad_words_ids": null,
|
| 17 |
+
"begin_suppress_tokens": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"cross_attention_hidden_size": null,
|
| 21 |
+
"decoder_start_token_id": null,
|
| 22 |
+
"diversity_penalty": 0.0,
|
| 23 |
+
"do_sample": false,
|
| 24 |
+
"dropout": 0.0,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "quick_gelu",
|
| 33 |
+
"hidden_size": 768,
|
| 34 |
+
"id2label": {
|
| 35 |
+
"0": "LABEL_0",
|
| 36 |
+
"1": "LABEL_1"
|
| 37 |
+
},
|
| 38 |
+
"initializer_factor": 1.0,
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 77,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "clip_text_model",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"prefix": null,
|
| 64 |
+
"problem_type": null,
|
| 65 |
+
"projection_dim": 768,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"suppress_tokens": null,
|
| 73 |
+
"task_specific_params": null,
|
| 74 |
+
"temperature": 1.0,
|
| 75 |
+
"tf_legacy_loss": false,
|
| 76 |
+
"tie_encoder_decoder": false,
|
| 77 |
+
"tie_word_embeddings": true,
|
| 78 |
+
"tokenizer_class": null,
|
| 79 |
+
"top_k": 50,
|
| 80 |
+
"top_p": 1.0,
|
| 81 |
+
"torch_dtype": null,
|
| 82 |
+
"torchscript": false,
|
| 83 |
+
"transformers_version": "4.27.4",
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"vocab_size": 49408
|
| 87 |
+
},
|
| 88 |
+
"torch_dtype": "float16",
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"begin_suppress_tokens": null,
|
| 97 |
+
"bos_token_id": null,
|
| 98 |
+
"chunk_size_feed_forward": 0,
|
| 99 |
+
"cross_attention_hidden_size": null,
|
| 100 |
+
"decoder_start_token_id": null,
|
| 101 |
+
"diversity_penalty": 0.0,
|
| 102 |
+
"do_sample": false,
|
| 103 |
+
"dropout": 0.0,
|
| 104 |
+
"early_stopping": false,
|
| 105 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 106 |
+
"eos_token_id": null,
|
| 107 |
+
"exponential_decay_length_penalty": null,
|
| 108 |
+
"finetuning_task": null,
|
| 109 |
+
"forced_bos_token_id": null,
|
| 110 |
+
"forced_eos_token_id": null,
|
| 111 |
+
"hidden_act": "quick_gelu",
|
| 112 |
+
"hidden_size": 1024,
|
| 113 |
+
"id2label": {
|
| 114 |
+
"0": "LABEL_0",
|
| 115 |
+
"1": "LABEL_1"
|
| 116 |
+
},
|
| 117 |
+
"image_size": 224,
|
| 118 |
+
"initializer_factor": 1.0,
|
| 119 |
+
"initializer_range": 0.02,
|
| 120 |
+
"intermediate_size": 4096,
|
| 121 |
+
"is_decoder": false,
|
| 122 |
+
"is_encoder_decoder": false,
|
| 123 |
+
"label2id": {
|
| 124 |
+
"LABEL_0": 0,
|
| 125 |
+
"LABEL_1": 1
|
| 126 |
+
},
|
| 127 |
+
"layer_norm_eps": 1e-05,
|
| 128 |
+
"length_penalty": 1.0,
|
| 129 |
+
"max_length": 20,
|
| 130 |
+
"min_length": 0,
|
| 131 |
+
"model_type": "clip_vision_model",
|
| 132 |
+
"no_repeat_ngram_size": 0,
|
| 133 |
+
"num_attention_heads": 16,
|
| 134 |
+
"num_beam_groups": 1,
|
| 135 |
+
"num_beams": 1,
|
| 136 |
+
"num_channels": 3,
|
| 137 |
+
"num_hidden_layers": 24,
|
| 138 |
+
"num_return_sequences": 1,
|
| 139 |
+
"output_attentions": false,
|
| 140 |
+
"output_hidden_states": false,
|
| 141 |
+
"output_scores": false,
|
| 142 |
+
"pad_token_id": null,
|
| 143 |
+
"patch_size": 14,
|
| 144 |
+
"prefix": null,
|
| 145 |
+
"problem_type": null,
|
| 146 |
+
"projection_dim": 768,
|
| 147 |
+
"pruned_heads": {},
|
| 148 |
+
"remove_invalid_values": false,
|
| 149 |
+
"repetition_penalty": 1.0,
|
| 150 |
+
"return_dict": true,
|
| 151 |
+
"return_dict_in_generate": false,
|
| 152 |
+
"sep_token_id": null,
|
| 153 |
+
"suppress_tokens": null,
|
| 154 |
+
"task_specific_params": null,
|
| 155 |
+
"temperature": 1.0,
|
| 156 |
+
"tf_legacy_loss": false,
|
| 157 |
+
"tie_encoder_decoder": false,
|
| 158 |
+
"tie_word_embeddings": true,
|
| 159 |
+
"tokenizer_class": null,
|
| 160 |
+
"top_k": 50,
|
| 161 |
+
"top_p": 1.0,
|
| 162 |
+
"torch_dtype": null,
|
| 163 |
+
"torchscript": false,
|
| 164 |
+
"transformers_version": "4.27.4",
|
| 165 |
+
"typical_p": 1.0,
|
| 166 |
+
"use_bfloat16": false
|
| 167 |
+
}
|
| 168 |
+
}
|
safety_checker/model.fp16.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c917ec4f9e64a1b45156c7fb81999c0f6e6379ec79cc3a576ad144ffb5bf572
|
| 3 |
+
size 607990743
|
safety_checker/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ae81b4aeafdbc236594495a5aab48776892b18f996727ba7ad5bd24d6349817
|
| 3 |
+
size 1215926450
|
safety_checker/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a3ad83d248f5eee559ad34ace75f517f6e2560ab42350dcbb8f26fc4519f6e6
|
| 3 |
+
size 1216009409
|
safety_checker/pytorch_model.fp16.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c637b781b23103fb6dc47d0862bdd717bd81bff84111efc5fe022a285d3b5c6b
|
| 3 |
+
size 608075916
|
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "DDPMScheduler",
|
| 3 |
+
"_diffusers_version": "0.15.0.dev0",
|
| 4 |
+
"beta_end": 0.02,
|
| 5 |
+
"beta_schedule": "squaredcos_cap_v2",
|
| 6 |
+
"beta_start": 0.0001,
|
| 7 |
+
"clip_sample": true,
|
| 8 |
+
"clip_sample_range": 1.0,
|
| 9 |
+
"dynamic_thresholding_ratio": 0.95,
|
| 10 |
+
"num_train_timesteps": 1000,
|
| 11 |
+
"prediction_type": "epsilon",
|
| 12 |
+
"sample_max_value": 1.5,
|
| 13 |
+
"thresholding": true,
|
| 14 |
+
"trained_betas": null,
|
| 15 |
+
"variance_type": "learned_range",
|
| 16 |
+
"lambda_min_clipped": -5.1
|
| 17 |
+
}
|
text_encoder/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5EncoderModel"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 10240,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 4096,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "t5",
|
| 19 |
+
"num_decoder_layers": 24,
|
| 20 |
+
"num_heads": 64,
|
| 21 |
+
"num_layers": 24,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "float16",
|
| 28 |
+
"transformers_version": "4.28.0.dev0",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 32128
|
| 31 |
+
}
|
text_encoder/model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5dfaaab934ff0359d88bda7e732f95e810ab711cf9df86d97856580564a6d3bf
|
| 3 |
+
size 9989150322
|
text_encoder/model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41d72c7ea3f3a0026f529f71af16b7e562f1266d5e1dbc09fa3c6413c9a7122e
|
| 3 |
+
size 9060119390
|
text_encoder/model.8bit.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a0b8c00b2e7a168f69a77b16c46240ce76f86e473aaebba2cfb1dd55bbc5303
|
| 3 |
+
size 7917591394
|
text_encoder/model.fp16-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82c990c09b55affae9b36b51d4d7ba071dea3b467c71c3cc88e0d77735bb3b59
|
| 3 |
+
size 9960786792
|
text_encoder/model.fp16-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42818a228ad7133141e6b1319faaa7fdc591c7b02873da3622a4f482cd266f9c
|
| 3 |
+
size 1577127548
|
text_encoder/model.safetensors.index.fp16.json
ADDED
|
@@ -0,0 +1,226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 11537887232
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"encoder.block.0.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 7 |
+
"encoder.block.0.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 8 |
+
"encoder.block.0.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 9 |
+
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00001-of-00002.safetensors",
|
| 10 |
+
"encoder.block.0.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 11 |
+
"encoder.block.0.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 12 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 13 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 14 |
+
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 15 |
+
"encoder.block.0.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 16 |
+
"encoder.block.1.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 17 |
+
"encoder.block.1.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 18 |
+
"encoder.block.1.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 19 |
+
"encoder.block.1.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 20 |
+
"encoder.block.1.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 21 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 22 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 23 |
+
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 24 |
+
"encoder.block.1.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 25 |
+
"encoder.block.10.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 26 |
+
"encoder.block.10.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 27 |
+
"encoder.block.10.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 28 |
+
"encoder.block.10.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 29 |
+
"encoder.block.10.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 30 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 31 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 32 |
+
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 33 |
+
"encoder.block.10.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 34 |
+
"encoder.block.11.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 35 |
+
"encoder.block.11.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 36 |
+
"encoder.block.11.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 37 |
+
"encoder.block.11.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 38 |
+
"encoder.block.11.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 39 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 40 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 41 |
+
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 42 |
+
"encoder.block.11.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 43 |
+
"encoder.block.12.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 44 |
+
"encoder.block.12.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 45 |
+
"encoder.block.12.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 46 |
+
"encoder.block.12.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 47 |
+
"encoder.block.12.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 48 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 49 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 50 |
+
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 51 |
+
"encoder.block.12.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 52 |
+
"encoder.block.13.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 53 |
+
"encoder.block.13.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 54 |
+
"encoder.block.13.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 55 |
+
"encoder.block.13.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 56 |
+
"encoder.block.13.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 57 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 58 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 59 |
+
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 60 |
+
"encoder.block.13.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 61 |
+
"encoder.block.14.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 62 |
+
"encoder.block.14.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 63 |
+
"encoder.block.14.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 64 |
+
"encoder.block.14.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 65 |
+
"encoder.block.14.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 66 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 67 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 68 |
+
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 69 |
+
"encoder.block.14.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 70 |
+
"encoder.block.15.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 71 |
+
"encoder.block.15.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 72 |
+
"encoder.block.15.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 73 |
+
"encoder.block.15.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 74 |
+
"encoder.block.15.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 75 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 76 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 77 |
+
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 78 |
+
"encoder.block.15.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 79 |
+
"encoder.block.16.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 80 |
+
"encoder.block.16.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 81 |
+
"encoder.block.16.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 82 |
+
"encoder.block.16.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 83 |
+
"encoder.block.16.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 84 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 85 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 86 |
+
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 87 |
+
"encoder.block.16.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 88 |
+
"encoder.block.17.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 89 |
+
"encoder.block.17.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 90 |
+
"encoder.block.17.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 91 |
+
"encoder.block.17.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 92 |
+
"encoder.block.17.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 93 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 94 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 95 |
+
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 96 |
+
"encoder.block.17.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 97 |
+
"encoder.block.18.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 98 |
+
"encoder.block.18.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 99 |
+
"encoder.block.18.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 100 |
+
"encoder.block.18.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 101 |
+
"encoder.block.18.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 102 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 103 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 104 |
+
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 105 |
+
"encoder.block.18.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 106 |
+
"encoder.block.19.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 107 |
+
"encoder.block.19.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 108 |
+
"encoder.block.19.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 109 |
+
"encoder.block.19.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 110 |
+
"encoder.block.19.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 111 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 112 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 113 |
+
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 114 |
+
"encoder.block.19.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 115 |
+
"encoder.block.2.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 116 |
+
"encoder.block.2.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 117 |
+
"encoder.block.2.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 118 |
+
"encoder.block.2.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 119 |
+
"encoder.block.2.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 120 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 121 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 122 |
+
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 123 |
+
"encoder.block.2.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 124 |
+
"encoder.block.20.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 125 |
+
"encoder.block.20.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 126 |
+
"encoder.block.20.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 127 |
+
"encoder.block.20.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 128 |
+
"encoder.block.20.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 129 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 130 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 131 |
+
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
|
| 132 |
+
"encoder.block.20.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
|
| 133 |
+
"encoder.block.21.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
|
| 134 |
+
"encoder.block.21.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
|
| 135 |
+
"encoder.block.21.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
|
| 136 |
+
"encoder.block.21.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
|
| 137 |
+
"encoder.block.21.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
|
| 138 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
|
| 139 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
|
| 140 |
+
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
|
| 141 |
+
"encoder.block.21.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
|
| 142 |
+
"encoder.block.22.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
|
| 143 |
+
"encoder.block.22.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
|
| 144 |
+
"encoder.block.22.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
|
| 145 |
+
"encoder.block.22.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
|
| 146 |
+
"encoder.block.22.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
|
| 147 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
|
| 148 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
|
| 149 |
+
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
|
| 150 |
+
"encoder.block.22.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
|
| 151 |
+
"encoder.block.23.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00002.safetensors",
|
| 152 |
+
"encoder.block.23.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00002.safetensors",
|
| 153 |
+
"encoder.block.23.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00002.safetensors",
|
| 154 |
+
"encoder.block.23.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00002.safetensors",
|
| 155 |
+
"encoder.block.23.layer.0.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
|
| 156 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00002.safetensors",
|
| 157 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00002.safetensors",
|
| 158 |
+
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00002.safetensors",
|
| 159 |
+
"encoder.block.23.layer.1.layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
|
| 160 |
+
"encoder.block.3.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 161 |
+
"encoder.block.3.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 162 |
+
"encoder.block.3.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 163 |
+
"encoder.block.3.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 164 |
+
"encoder.block.3.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 165 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 166 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 167 |
+
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 168 |
+
"encoder.block.3.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 169 |
+
"encoder.block.4.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 170 |
+
"encoder.block.4.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 171 |
+
"encoder.block.4.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 172 |
+
"encoder.block.4.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 173 |
+
"encoder.block.4.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 174 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 175 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 176 |
+
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 177 |
+
"encoder.block.4.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 178 |
+
"encoder.block.5.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 179 |
+
"encoder.block.5.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 180 |
+
"encoder.block.5.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 181 |
+
"encoder.block.5.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 182 |
+
"encoder.block.5.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 183 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 184 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 185 |
+
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 186 |
+
"encoder.block.5.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 187 |
+
"encoder.block.6.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 188 |
+
"encoder.block.6.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 189 |
+
"encoder.block.6.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 190 |
+
"encoder.block.6.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 191 |
+
"encoder.block.6.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 192 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 193 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 194 |
+
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 195 |
+
"encoder.block.6.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 196 |
+
"encoder.block.7.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 197 |
+
"encoder.block.7.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 198 |
+
"encoder.block.7.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 199 |
+
"encoder.block.7.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 200 |
+
"encoder.block.7.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 201 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 202 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 203 |
+
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 204 |
+
"encoder.block.7.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 205 |
+
"encoder.block.8.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 206 |
+
"encoder.block.8.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 207 |
+
"encoder.block.8.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 208 |
+
"encoder.block.8.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 209 |
+
"encoder.block.8.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 210 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 211 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 212 |
+
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 213 |
+
"encoder.block.8.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 214 |
+
"encoder.block.9.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00002.safetensors",
|
| 215 |
+
"encoder.block.9.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00002.safetensors",
|
| 216 |
+
"encoder.block.9.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00002.safetensors",
|
| 217 |
+
"encoder.block.9.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00002.safetensors",
|
| 218 |
+
"encoder.block.9.layer.0.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 219 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00002.safetensors",
|
| 220 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00002.safetensors",
|
| 221 |
+
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00002.safetensors",
|
| 222 |
+
"encoder.block.9.layer.1.layer_norm.weight": "model.fp16-00001-of-00002.safetensors",
|
| 223 |
+
"encoder.final_layer_norm.weight": "model.fp16-00002-of-00002.safetensors",
|
| 224 |
+
"shared.weight": "model.fp16-00001-of-00002.safetensors"
|
| 225 |
+
}
|
| 226 |
+
}
|
text_encoder/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 19049242624
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
|
| 45 |
+
"encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 48 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
|
| 49 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
|
| 50 |
+
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
|
| 51 |
+
"encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 52 |
+
"encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
|
| 53 |
+
"encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
|
| 54 |
+
"encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
|
| 55 |
+
"encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
|
| 56 |
+
"encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 57 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
|
| 58 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
|
| 59 |
+
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
|
| 60 |
+
"encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 61 |
+
"encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
|
| 62 |
+
"encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
|
| 63 |
+
"encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
|
| 64 |
+
"encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
|
| 65 |
+
"encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 66 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
|
| 67 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
|
| 68 |
+
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
|
| 69 |
+
"encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 70 |
+
"encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
|
| 71 |
+
"encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
|
| 72 |
+
"encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
|
| 73 |
+
"encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
|
| 74 |
+
"encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 75 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
|
| 76 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
|
| 77 |
+
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
|
| 78 |
+
"encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 79 |
+
"encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
|
| 80 |
+
"encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
|
| 81 |
+
"encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
|
| 82 |
+
"encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
|
| 83 |
+
"encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 84 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
|
| 85 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
|
| 86 |
+
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
|
| 87 |
+
"encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 88 |
+
"encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
|
| 89 |
+
"encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
|
| 90 |
+
"encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
|
| 91 |
+
"encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
|
| 92 |
+
"encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 93 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
|
| 94 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
|
| 95 |
+
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
|
| 96 |
+
"encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 97 |
+
"encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
|
| 98 |
+
"encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
|
| 99 |
+
"encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
|
| 100 |
+
"encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
|
| 101 |
+
"encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 102 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
|
| 103 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
|
| 104 |
+
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
|
| 105 |
+
"encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 106 |
+
"encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
|
| 107 |
+
"encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
|
| 108 |
+
"encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
|
| 109 |
+
"encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 111 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
|
| 113 |
+
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 115 |
+
"encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
|
| 119 |
+
"encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
|
| 125 |
+
"encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 142 |
+
"encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
|
| 143 |
+
"encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
|
| 144 |
+
"encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
|
| 145 |
+
"encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
|
| 146 |
+
"encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 147 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
|
| 148 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
|
| 149 |
+
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
|
| 150 |
+
"encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 151 |
+
"encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
|
| 161 |
+
"encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
|
| 163 |
+
"encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
|
| 167 |
+
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 169 |
+
"encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
|
| 171 |
+
"encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
|
| 173 |
+
"encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
|
| 175 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
|
| 179 |
+
"encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
|
| 181 |
+
"encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 183 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
|
| 185 |
+
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 187 |
+
"encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
|
| 191 |
+
"encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
|
| 193 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
|
| 195 |
+
"encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
|
| 197 |
+
"encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
|
| 199 |
+
"encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
|
| 203 |
+
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 205 |
+
"encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
|
| 207 |
+
"encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
|
| 209 |
+
"encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
|
| 211 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
|
| 215 |
+
"encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
|
| 217 |
+
"encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 219 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
|
| 221 |
+
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
|
| 223 |
+
"encoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"shared.weight": "model-00001-of-00002.safetensors"
|
| 225 |
+
}
|
| 226 |
+
}
|
text_encoder/pytorch_model-00001-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f71ad0624095dae788b1023081dda1b4040bd24f7244a5b5b46eebc09825839
|
| 3 |
+
size 9452285635
|
text_encoder/pytorch_model-00002-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f68f80678299ac59f69b3550ebd47b966571920d8f9e71f42ab61fabaaed868
|
| 3 |
+
size 9597031749
|
text_encoder/pytorch_model.8bit.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c939e223d7b2d41951b27b6d9327ad45d079eb66d01e75f0a3ef59f05cc807a6
|
| 3 |
+
size 7917675826
|
text_encoder/pytorch_model.bin.index.fp16.json
ADDED
|
@@ -0,0 +1,226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 11537887232
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 7 |
+
"encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 8 |
+
"encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 9 |
+
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 10 |
+
"encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 11 |
+
"encoder.block.0.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 12 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 13 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 14 |
+
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 15 |
+
"encoder.block.0.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 16 |
+
"encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 17 |
+
"encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 18 |
+
"encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 19 |
+
"encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 20 |
+
"encoder.block.1.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 21 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 22 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 23 |
+
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 24 |
+
"encoder.block.1.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 25 |
+
"encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 26 |
+
"encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 27 |
+
"encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 28 |
+
"encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 29 |
+
"encoder.block.10.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 30 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 31 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 32 |
+
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 33 |
+
"encoder.block.10.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 34 |
+
"encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 35 |
+
"encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 36 |
+
"encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 37 |
+
"encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 38 |
+
"encoder.block.11.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 39 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 40 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 41 |
+
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 42 |
+
"encoder.block.11.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 43 |
+
"encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 44 |
+
"encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 45 |
+
"encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 46 |
+
"encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 47 |
+
"encoder.block.12.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 48 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 49 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 50 |
+
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 51 |
+
"encoder.block.12.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 52 |
+
"encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 53 |
+
"encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 54 |
+
"encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 55 |
+
"encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 56 |
+
"encoder.block.13.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 57 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 58 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 59 |
+
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 60 |
+
"encoder.block.13.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 61 |
+
"encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 62 |
+
"encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 63 |
+
"encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 64 |
+
"encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 65 |
+
"encoder.block.14.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 66 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 67 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 68 |
+
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 69 |
+
"encoder.block.14.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 70 |
+
"encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 71 |
+
"encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 72 |
+
"encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 73 |
+
"encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 74 |
+
"encoder.block.15.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 75 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 76 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 77 |
+
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 78 |
+
"encoder.block.15.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 79 |
+
"encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 80 |
+
"encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 81 |
+
"encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 82 |
+
"encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 83 |
+
"encoder.block.16.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 84 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 85 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 86 |
+
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 87 |
+
"encoder.block.16.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 88 |
+
"encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 89 |
+
"encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 90 |
+
"encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 91 |
+
"encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 92 |
+
"encoder.block.17.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 93 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 94 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 95 |
+
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 96 |
+
"encoder.block.17.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 97 |
+
"encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 98 |
+
"encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 99 |
+
"encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 100 |
+
"encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 101 |
+
"encoder.block.18.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 102 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 103 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 104 |
+
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 105 |
+
"encoder.block.18.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 106 |
+
"encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 107 |
+
"encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 108 |
+
"encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 109 |
+
"encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 110 |
+
"encoder.block.19.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 111 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 112 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 113 |
+
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 114 |
+
"encoder.block.19.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 115 |
+
"encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 116 |
+
"encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 117 |
+
"encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 118 |
+
"encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 119 |
+
"encoder.block.2.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 120 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 121 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 122 |
+
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 123 |
+
"encoder.block.2.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 124 |
+
"encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 125 |
+
"encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 126 |
+
"encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 127 |
+
"encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 128 |
+
"encoder.block.20.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 129 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 130 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 131 |
+
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 132 |
+
"encoder.block.20.layer.1.layer_norm.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 133 |
+
"encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 134 |
+
"encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 135 |
+
"encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 136 |
+
"encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 137 |
+
"encoder.block.21.layer.0.layer_norm.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 138 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 139 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 140 |
+
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 141 |
+
"encoder.block.21.layer.1.layer_norm.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 142 |
+
"encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 143 |
+
"encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 144 |
+
"encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 145 |
+
"encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 146 |
+
"encoder.block.22.layer.0.layer_norm.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 147 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 148 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 149 |
+
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 150 |
+
"encoder.block.22.layer.1.layer_norm.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 151 |
+
"encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 152 |
+
"encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 153 |
+
"encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 154 |
+
"encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 155 |
+
"encoder.block.23.layer.0.layer_norm.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 156 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 157 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 158 |
+
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 159 |
+
"encoder.block.23.layer.1.layer_norm.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 160 |
+
"encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 161 |
+
"encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 162 |
+
"encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 163 |
+
"encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 164 |
+
"encoder.block.3.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 165 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 166 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 167 |
+
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 168 |
+
"encoder.block.3.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 169 |
+
"encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 170 |
+
"encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 171 |
+
"encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 172 |
+
"encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 173 |
+
"encoder.block.4.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 174 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 175 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 176 |
+
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 177 |
+
"encoder.block.4.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 178 |
+
"encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 179 |
+
"encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 180 |
+
"encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 181 |
+
"encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 182 |
+
"encoder.block.5.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 183 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 184 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 185 |
+
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 186 |
+
"encoder.block.5.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 187 |
+
"encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 188 |
+
"encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 189 |
+
"encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 190 |
+
"encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 191 |
+
"encoder.block.6.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 192 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 193 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 194 |
+
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 195 |
+
"encoder.block.6.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 196 |
+
"encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 197 |
+
"encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 198 |
+
"encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 199 |
+
"encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 200 |
+
"encoder.block.7.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 201 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 202 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 203 |
+
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 204 |
+
"encoder.block.7.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 205 |
+
"encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 206 |
+
"encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 207 |
+
"encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 208 |
+
"encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 209 |
+
"encoder.block.8.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 210 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 211 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 212 |
+
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 213 |
+
"encoder.block.8.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 214 |
+
"encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 215 |
+
"encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 216 |
+
"encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 217 |
+
"encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 218 |
+
"encoder.block.9.layer.0.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 219 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 220 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 221 |
+
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 222 |
+
"encoder.block.9.layer.1.layer_norm.weight": "pytorch_model.fp16-00001-of-00002.bin",
|
| 223 |
+
"encoder.final_layer_norm.weight": "pytorch_model.fp16-00002-of-00002.bin",
|
| 224 |
+
"shared.weight": "pytorch_model.fp16-00001-of-00002.bin"
|
| 225 |
+
}
|
| 226 |
+
}
|
text_encoder/pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,227 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 19575627776
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 7 |
+
"encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 8 |
+
"encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 9 |
+
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
|
| 10 |
+
"encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 11 |
+
"encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 12 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 13 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 14 |
+
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 15 |
+
"encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 16 |
+
"encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 17 |
+
"encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 18 |
+
"encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 19 |
+
"encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 20 |
+
"encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 21 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 22 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 23 |
+
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 24 |
+
"encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 25 |
+
"encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 26 |
+
"encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 27 |
+
"encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 28 |
+
"encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 29 |
+
"encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 30 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 31 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 32 |
+
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 33 |
+
"encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 34 |
+
"encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 35 |
+
"encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 36 |
+
"encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 37 |
+
"encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 38 |
+
"encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 39 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 40 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 41 |
+
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
|
| 42 |
+
"encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 43 |
+
"encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
|
| 44 |
+
"encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
|
| 45 |
+
"encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
|
| 46 |
+
"encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
|
| 47 |
+
"encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 48 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
|
| 49 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 50 |
+
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
|
| 51 |
+
"encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 52 |
+
"encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
|
| 53 |
+
"encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
|
| 54 |
+
"encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
|
| 55 |
+
"encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
|
| 56 |
+
"encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 57 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
|
| 58 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 59 |
+
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
|
| 60 |
+
"encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 61 |
+
"encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
|
| 62 |
+
"encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
|
| 63 |
+
"encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
|
| 64 |
+
"encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
|
| 65 |
+
"encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 66 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
|
| 67 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 68 |
+
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
|
| 69 |
+
"encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 70 |
+
"encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
|
| 71 |
+
"encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
|
| 72 |
+
"encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
|
| 73 |
+
"encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
|
| 74 |
+
"encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 75 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
|
| 76 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 77 |
+
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
|
| 78 |
+
"encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 79 |
+
"encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
|
| 80 |
+
"encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
|
| 81 |
+
"encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
|
| 82 |
+
"encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
|
| 83 |
+
"encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 84 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
|
| 85 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 86 |
+
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
|
| 87 |
+
"encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 88 |
+
"encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
|
| 89 |
+
"encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
|
| 90 |
+
"encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
|
| 91 |
+
"encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
|
| 92 |
+
"encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 93 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
|
| 94 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 95 |
+
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
|
| 96 |
+
"encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 97 |
+
"encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
|
| 98 |
+
"encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
|
| 99 |
+
"encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
|
| 100 |
+
"encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
|
| 101 |
+
"encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 102 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
|
| 103 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 104 |
+
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
|
| 105 |
+
"encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 106 |
+
"encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
|
| 107 |
+
"encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
|
| 108 |
+
"encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
|
| 109 |
+
"encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
|
| 110 |
+
"encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 111 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
|
| 112 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 113 |
+
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
|
| 114 |
+
"encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 115 |
+
"encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 116 |
+
"encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 117 |
+
"encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 118 |
+
"encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 119 |
+
"encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 120 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 121 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 122 |
+
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 123 |
+
"encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 124 |
+
"encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
|
| 125 |
+
"encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
|
| 126 |
+
"encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
|
| 127 |
+
"encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
|
| 128 |
+
"encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 129 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
|
| 130 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 131 |
+
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
|
| 132 |
+
"encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 133 |
+
"encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
|
| 134 |
+
"encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
|
| 135 |
+
"encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
|
| 136 |
+
"encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
|
| 137 |
+
"encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 138 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
|
| 139 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 140 |
+
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
|
| 141 |
+
"encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 142 |
+
"encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
|
| 143 |
+
"encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
|
| 144 |
+
"encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
|
| 145 |
+
"encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
|
| 146 |
+
"encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 147 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
|
| 148 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 149 |
+
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
|
| 150 |
+
"encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 151 |
+
"encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
|
| 152 |
+
"encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
|
| 153 |
+
"encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
|
| 154 |
+
"encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
|
| 155 |
+
"encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 156 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
|
| 157 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
|
| 158 |
+
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
|
| 159 |
+
"encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 160 |
+
"encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 161 |
+
"encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 162 |
+
"encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 163 |
+
"encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 164 |
+
"encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 165 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 166 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 167 |
+
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 168 |
+
"encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 169 |
+
"encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 170 |
+
"encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 171 |
+
"encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 172 |
+
"encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 173 |
+
"encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 174 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 175 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 176 |
+
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 177 |
+
"encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 178 |
+
"encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 179 |
+
"encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 180 |
+
"encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 181 |
+
"encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 182 |
+
"encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 183 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 184 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 185 |
+
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 186 |
+
"encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 187 |
+
"encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 188 |
+
"encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 189 |
+
"encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 190 |
+
"encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 191 |
+
"encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 192 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 193 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 194 |
+
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 195 |
+
"encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 196 |
+
"encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 197 |
+
"encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 198 |
+
"encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 199 |
+
"encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 200 |
+
"encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 201 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 202 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 203 |
+
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 204 |
+
"encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 205 |
+
"encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 206 |
+
"encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 207 |
+
"encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 208 |
+
"encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 209 |
+
"encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 210 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 211 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 212 |
+
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 213 |
+
"encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 214 |
+
"encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
| 215 |
+
"encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
|
| 216 |
+
"encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
|
| 217 |
+
"encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
|
| 218 |
+
"encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 219 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
|
| 220 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
|
| 221 |
+
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
|
| 222 |
+
"encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
|
| 223 |
+
"encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
| 224 |
+
"encoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
|
| 225 |
+
"shared.weight": "pytorch_model-00001-of-00002.bin"
|
| 226 |
+
}
|
| 227 |
+
}
|
text_encoder/pytorch_model.fp16-00001-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7020b9c751d9ee19e350673697e5e40974fb351c85935374bb7aa037694aa95a
|
| 3 |
+
size 9960831045
|
text_encoder/pytorch_model.fp16-00002-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f97e9431a2742bfb42fd0b634de30be0cf5fa1780129e9cd75c83382f8c90c8e
|
| 3 |
+
size 1577134283
|
text_encoder/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
text_encoder/spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
text_encoder/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "name_or_path": "t5-small"}
|
tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
tokenizer/spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"extra_ids": 100,
|
| 106 |
+
"model_max_length": 512,
|
| 107 |
+
"pad_token": "<pad>",
|
| 108 |
+
"sp_model_kwargs": {},
|
| 109 |
+
"special_tokens_map_file": "/home/patrick_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-xxl/snapshots/3db67ab1af984cf10548a73467f0e5bca2aaaeb2/special_tokens_map.json",
|
| 110 |
+
"tokenizer_class": "T5Tokenizer",
|
| 111 |
+
"unk_token": "<unk>"
|
| 112 |
+
}
|
unet/config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.15.0.dev0",
|
| 4 |
+
"_name_or_path": "/home/patrick_huggingface_co/if-temp/",
|
| 5 |
+
"act_fn": "gelu",
|
| 6 |
+
"addition_embed_type": "text",
|
| 7 |
+
"attention_head_dim": 64,
|
| 8 |
+
"block_out_channels": [
|
| 9 |
+
704,
|
| 10 |
+
1408,
|
| 11 |
+
2112,
|
| 12 |
+
2816
|
| 13 |
+
],
|
| 14 |
+
"center_input_sample": false,
|
| 15 |
+
"class_embed_type": null,
|
| 16 |
+
"class_embeddings_concat": false,
|
| 17 |
+
"conv_in_kernel": 3,
|
| 18 |
+
"conv_out_kernel": 3,
|
| 19 |
+
"cross_attention_dim": 2816,
|
| 20 |
+
"cross_attention_norm": "group_norm",
|
| 21 |
+
"down_block_types": [
|
| 22 |
+
"ResnetDownsampleBlock2D",
|
| 23 |
+
"SimpleCrossAttnDownBlock2D",
|
| 24 |
+
"SimpleCrossAttnDownBlock2D",
|
| 25 |
+
"SimpleCrossAttnDownBlock2D"
|
| 26 |
+
],
|
| 27 |
+
"downsample_padding": 1,
|
| 28 |
+
"dual_cross_attention": false,
|
| 29 |
+
"encoder_hid_dim": 4096,
|
| 30 |
+
"encoder_hid_dim_type": "text_proj",
|
| 31 |
+
"flip_sin_to_cos": true,
|
| 32 |
+
"freq_shift": 0,
|
| 33 |
+
"in_channels": 3,
|
| 34 |
+
"layers_per_block": 3,
|
| 35 |
+
"mid_block_scale_factor": 1,
|
| 36 |
+
"mid_block_type": "UNetMidBlock2DSimpleCrossAttn",
|
| 37 |
+
"norm_eps": 1e-05,
|
| 38 |
+
"norm_num_groups": 32,
|
| 39 |
+
"num_class_embeds": null,
|
| 40 |
+
"only_cross_attention": false,
|
| 41 |
+
"out_channels": 6,
|
| 42 |
+
"projection_class_embeddings_input_dim": null,
|
| 43 |
+
"resnet_out_scale_factor": 1.0,
|
| 44 |
+
"resnet_skip_time_act": false,
|
| 45 |
+
"resnet_time_scale_shift": "scale_shift",
|
| 46 |
+
"sample_size": 64,
|
| 47 |
+
"time_cond_proj_dim": null,
|
| 48 |
+
"time_embedding_act_fn": null,
|
| 49 |
+
"time_embedding_dim": null,
|
| 50 |
+
"time_embedding_type": "positional",
|
| 51 |
+
"timestep_post_act": null,
|
| 52 |
+
"up_block_types": [
|
| 53 |
+
"SimpleCrossAttnUpBlock2D",
|
| 54 |
+
"SimpleCrossAttnUpBlock2D",
|
| 55 |
+
"SimpleCrossAttnUpBlock2D",
|
| 56 |
+
"ResnetUpsampleBlock2D"
|
| 57 |
+
],
|
| 58 |
+
"upcast_attention": false,
|
| 59 |
+
"use_linear_projection": false
|
| 60 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a16f77026ee4bf230871b8baf96cfdeeaabb05a4ea6919aed774e8872c2a9ab2
|
| 3 |
+
size 17219076439
|
unet/diffusion_pytorch_model.fp16.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0ff0daf9c7e1ec5bc61444fb4c00942d0e25b3c74d004caf6d63fee2311de44
|
| 3 |
+
size 8609688700
|
unet/diffusion_pytorch_model.fp16.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5ce5e1d0d6ecf9da8988fbf7595c867386f0c98085732e2660fe2c37f04df4b
|
| 3 |
+
size 8609476940
|
unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d478fe3f64e368cd58201e8a6dd5c94264cfe85249125196a2f3b43d90a8d706
|
| 3 |
+
size 17218867967
|
watermarker/config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "IFWatermark",
|
| 3 |
+
"_diffusers_version": "0.16.0.dev0"
|
| 4 |
+
}
|
watermarker/diffusion_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4395e84091cb32cfd49cd3ea1cec69dbed871b7484702edc5909f8cb69252d1f
|
| 3 |
+
size 16347
|
watermarker/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad38e4ca986f391bbd3641064650aab83122b701bdb143effc8e084425df6110
|
| 3 |
+
size 15492
|