Commit
•
1496f22
1
Parent(s):
9aa7130
Upload ParlerTTSForConditionalGeneration
Browse files- config.json +42 -14
- model-00001-of-00003.safetensors +2 -2
- model-00002-of-00003.safetensors +2 -2
- model-00003-of-00003.safetensors +2 -2
- model.safetensors.index.json +362 -425
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/home/akhil/parler-tts/
|
| 3 |
"architectures": [
|
| 4 |
"ParlerTTSForConditionalGeneration"
|
| 5 |
],
|
|
@@ -75,7 +75,7 @@
|
|
| 75 |
"use_bfloat16": false
|
| 76 |
},
|
| 77 |
"decoder": {
|
| 78 |
-
"_name_or_path": "
|
| 79 |
"activation_dropout": 0.0,
|
| 80 |
"activation_function": "gelu",
|
| 81 |
"add_cross_attention": true,
|
|
@@ -101,7 +101,7 @@
|
|
| 101 |
"finetuning_task": null,
|
| 102 |
"forced_bos_token_id": null,
|
| 103 |
"forced_eos_token_id": null,
|
| 104 |
-
"hidden_size":
|
| 105 |
"id2label": {
|
| 106 |
"0": "LABEL_0",
|
| 107 |
"1": "LABEL_1"
|
|
@@ -120,13 +120,13 @@
|
|
| 120 |
"min_length": 0,
|
| 121 |
"model_type": "parler_tts_decoder",
|
| 122 |
"no_repeat_ngram_size": 0,
|
| 123 |
-
"num_attention_heads":
|
| 124 |
"num_beam_groups": 1,
|
| 125 |
"num_beams": 1,
|
| 126 |
"num_codebooks": 9,
|
| 127 |
-
"num_cross_attention_key_value_heads":
|
| 128 |
-
"num_hidden_layers":
|
| 129 |
-
"num_key_value_heads":
|
| 130 |
"num_return_sequences": 1,
|
| 131 |
"output_attentions": false,
|
| 132 |
"output_hidden_states": false,
|
|
@@ -163,9 +163,9 @@
|
|
| 163 |
"is_encoder_decoder": true,
|
| 164 |
"model_type": "parler_tts",
|
| 165 |
"pad_token_id": 1024,
|
| 166 |
-
"prompt_cross_attention":
|
| 167 |
"text_encoder": {
|
| 168 |
-
"_name_or_path": "google/flan-t5-
|
| 169 |
"add_cross_attention": false,
|
| 170 |
"architectures": [
|
| 171 |
"T5ForConditionalGeneration"
|
|
@@ -176,9 +176,9 @@
|
|
| 176 |
"chunk_size_feed_forward": 0,
|
| 177 |
"classifier_dropout": 0.0,
|
| 178 |
"cross_attention_hidden_size": null,
|
| 179 |
-
"d_ff":
|
| 180 |
"d_kv": 64,
|
| 181 |
-
"d_model":
|
| 182 |
"decoder_start_token_id": 0,
|
| 183 |
"dense_act_fn": "gelu_new",
|
| 184 |
"diversity_penalty": 0.0,
|
|
@@ -214,7 +214,7 @@
|
|
| 214 |
"num_beam_groups": 1,
|
| 215 |
"num_beams": 1,
|
| 216 |
"num_decoder_layers": 24,
|
| 217 |
-
"num_heads":
|
| 218 |
"num_layers": 24,
|
| 219 |
"num_return_sequences": 1,
|
| 220 |
"output_attentions": false,
|
|
@@ -233,7 +233,35 @@
|
|
| 233 |
"return_dict_in_generate": false,
|
| 234 |
"sep_token_id": null,
|
| 235 |
"suppress_tokens": null,
|
| 236 |
-
"task_specific_params":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 237 |
"temperature": 1.0,
|
| 238 |
"tf_legacy_loss": false,
|
| 239 |
"tie_encoder_decoder": false,
|
|
@@ -241,7 +269,7 @@
|
|
| 241 |
"tokenizer_class": null,
|
| 242 |
"top_k": 50,
|
| 243 |
"top_p": 1.0,
|
| 244 |
-
"torch_dtype":
|
| 245 |
"torchscript": false,
|
| 246 |
"typical_p": 1.0,
|
| 247 |
"use_bfloat16": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/home/akhil/parler-tts/output_dir_training_mix_only/checkpoint-200000-epoch-143",
|
| 3 |
"architectures": [
|
| 4 |
"ParlerTTSForConditionalGeneration"
|
| 5 |
],
|
|
|
|
| 75 |
"use_bfloat16": false
|
| 76 |
},
|
| 77 |
"decoder": {
|
| 78 |
+
"_name_or_path": "/fsx/yoach/tmp/artefacts/parler-tts-large-v2/decoder",
|
| 79 |
"activation_dropout": 0.0,
|
| 80 |
"activation_function": "gelu",
|
| 81 |
"add_cross_attention": true,
|
|
|
|
| 101 |
"finetuning_task": null,
|
| 102 |
"forced_bos_token_id": null,
|
| 103 |
"forced_eos_token_id": null,
|
| 104 |
+
"hidden_size": 1536,
|
| 105 |
"id2label": {
|
| 106 |
"0": "LABEL_0",
|
| 107 |
"1": "LABEL_1"
|
|
|
|
| 120 |
"min_length": 0,
|
| 121 |
"model_type": "parler_tts_decoder",
|
| 122 |
"no_repeat_ngram_size": 0,
|
| 123 |
+
"num_attention_heads": 24,
|
| 124 |
"num_beam_groups": 1,
|
| 125 |
"num_beams": 1,
|
| 126 |
"num_codebooks": 9,
|
| 127 |
+
"num_cross_attention_key_value_heads": 24,
|
| 128 |
+
"num_hidden_layers": 32,
|
| 129 |
+
"num_key_value_heads": 8,
|
| 130 |
"num_return_sequences": 1,
|
| 131 |
"output_attentions": false,
|
| 132 |
"output_hidden_states": false,
|
|
|
|
| 163 |
"is_encoder_decoder": true,
|
| 164 |
"model_type": "parler_tts",
|
| 165 |
"pad_token_id": 1024,
|
| 166 |
+
"prompt_cross_attention": true,
|
| 167 |
"text_encoder": {
|
| 168 |
+
"_name_or_path": "google/flan-t5-xl",
|
| 169 |
"add_cross_attention": false,
|
| 170 |
"architectures": [
|
| 171 |
"T5ForConditionalGeneration"
|
|
|
|
| 176 |
"chunk_size_feed_forward": 0,
|
| 177 |
"classifier_dropout": 0.0,
|
| 178 |
"cross_attention_hidden_size": null,
|
| 179 |
+
"d_ff": 5120,
|
| 180 |
"d_kv": 64,
|
| 181 |
+
"d_model": 2048,
|
| 182 |
"decoder_start_token_id": 0,
|
| 183 |
"dense_act_fn": "gelu_new",
|
| 184 |
"diversity_penalty": 0.0,
|
|
|
|
| 214 |
"num_beam_groups": 1,
|
| 215 |
"num_beams": 1,
|
| 216 |
"num_decoder_layers": 24,
|
| 217 |
+
"num_heads": 32,
|
| 218 |
"num_layers": 24,
|
| 219 |
"num_return_sequences": 1,
|
| 220 |
"output_attentions": false,
|
|
|
|
| 233 |
"return_dict_in_generate": false,
|
| 234 |
"sep_token_id": null,
|
| 235 |
"suppress_tokens": null,
|
| 236 |
+
"task_specific_params": {
|
| 237 |
+
"summarization": {
|
| 238 |
+
"early_stopping": true,
|
| 239 |
+
"length_penalty": 2.0,
|
| 240 |
+
"max_length": 200,
|
| 241 |
+
"min_length": 30,
|
| 242 |
+
"no_repeat_ngram_size": 3,
|
| 243 |
+
"num_beams": 4,
|
| 244 |
+
"prefix": "summarize: "
|
| 245 |
+
},
|
| 246 |
+
"translation_en_to_de": {
|
| 247 |
+
"early_stopping": true,
|
| 248 |
+
"max_length": 300,
|
| 249 |
+
"num_beams": 4,
|
| 250 |
+
"prefix": "translate English to German: "
|
| 251 |
+
},
|
| 252 |
+
"translation_en_to_fr": {
|
| 253 |
+
"early_stopping": true,
|
| 254 |
+
"max_length": 300,
|
| 255 |
+
"num_beams": 4,
|
| 256 |
+
"prefix": "translate English to French: "
|
| 257 |
+
},
|
| 258 |
+
"translation_en_to_ro": {
|
| 259 |
+
"early_stopping": true,
|
| 260 |
+
"max_length": 300,
|
| 261 |
+
"num_beams": 4,
|
| 262 |
+
"prefix": "translate English to Romanian: "
|
| 263 |
+
}
|
| 264 |
+
},
|
| 265 |
"temperature": 1.0,
|
| 266 |
"tf_legacy_loss": false,
|
| 267 |
"tie_encoder_decoder": false,
|
|
|
|
| 269 |
"tokenizer_class": null,
|
| 270 |
"top_k": 50,
|
| 271 |
"top_p": 1.0,
|
| 272 |
+
"torch_dtype": "float32",
|
| 273 |
"torchscript": false,
|
| 274 |
"typical_p": 1.0,
|
| 275 |
"use_bfloat16": false,
|
model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c30d2151a8a9c3343b6998eeec019b46db9d17b84ef234d98ea6723941c2851c
|
| 3 |
+
size 4984365952
|
model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:447e63a6259cea547ee9fc022c44da7355f186f60d6cb6c66a6386bae5fb23f8
|
| 3 |
+
size 4805000272
|
model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94e39b62ef3e7a14a0de2621ed68c9c244bfc9b255d5b9e17b7f8d570e380b03
|
| 3 |
+
size 222560488
|
model.safetensors.index.json
CHANGED
|
@@ -1,127 +1,127 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"audio_encoder.model.decoder.model.0.bias": "model-00001-of-00003.safetensors",
|
| 7 |
"audio_encoder.model.decoder.model.0.weight_g": "model-00001-of-00003.safetensors",
|
| 8 |
-
"audio_encoder.model.decoder.model.0.weight_v": "model-
|
| 9 |
-
"audio_encoder.model.decoder.model.1.block.0.alpha": "model-
|
| 10 |
-
"audio_encoder.model.decoder.model.1.block.1.bias": "model-
|
| 11 |
-
"audio_encoder.model.decoder.model.1.block.1.weight_g": "model-
|
| 12 |
-
"audio_encoder.model.decoder.model.1.block.1.weight_v": "model-
|
| 13 |
-
"audio_encoder.model.decoder.model.1.block.2.block.0.alpha": "model-
|
| 14 |
-
"audio_encoder.model.decoder.model.1.block.2.block.1.bias": "model-
|
| 15 |
-
"audio_encoder.model.decoder.model.1.block.2.block.1.weight_g": "model-
|
| 16 |
-
"audio_encoder.model.decoder.model.1.block.2.block.1.weight_v": "model-
|
| 17 |
-
"audio_encoder.model.decoder.model.1.block.2.block.2.alpha": "model-
|
| 18 |
-
"audio_encoder.model.decoder.model.1.block.2.block.3.bias": "model-
|
| 19 |
-
"audio_encoder.model.decoder.model.1.block.2.block.3.weight_g": "model-
|
| 20 |
-
"audio_encoder.model.decoder.model.1.block.2.block.3.weight_v": "model-
|
| 21 |
-
"audio_encoder.model.decoder.model.1.block.3.block.0.alpha": "model-
|
| 22 |
-
"audio_encoder.model.decoder.model.1.block.3.block.1.bias": "model-
|
| 23 |
-
"audio_encoder.model.decoder.model.1.block.3.block.1.weight_g": "model-
|
| 24 |
-
"audio_encoder.model.decoder.model.1.block.3.block.1.weight_v": "model-
|
| 25 |
-
"audio_encoder.model.decoder.model.1.block.3.block.2.alpha": "model-
|
| 26 |
-
"audio_encoder.model.decoder.model.1.block.3.block.3.bias": "model-
|
| 27 |
-
"audio_encoder.model.decoder.model.1.block.3.block.3.weight_g": "model-
|
| 28 |
-
"audio_encoder.model.decoder.model.1.block.3.block.3.weight_v": "model-
|
| 29 |
-
"audio_encoder.model.decoder.model.1.block.4.block.0.alpha": "model-
|
| 30 |
-
"audio_encoder.model.decoder.model.1.block.4.block.1.bias": "model-
|
| 31 |
-
"audio_encoder.model.decoder.model.1.block.4.block.1.weight_g": "model-
|
| 32 |
-
"audio_encoder.model.decoder.model.1.block.4.block.1.weight_v": "model-
|
| 33 |
-
"audio_encoder.model.decoder.model.1.block.4.block.2.alpha": "model-
|
| 34 |
-
"audio_encoder.model.decoder.model.1.block.4.block.3.bias": "model-
|
| 35 |
-
"audio_encoder.model.decoder.model.1.block.4.block.3.weight_g": "model-
|
| 36 |
-
"audio_encoder.model.decoder.model.1.block.4.block.3.weight_v": "model-
|
| 37 |
-
"audio_encoder.model.decoder.model.2.block.0.alpha": "model-
|
| 38 |
-
"audio_encoder.model.decoder.model.2.block.1.bias": "model-
|
| 39 |
-
"audio_encoder.model.decoder.model.2.block.1.weight_g": "model-
|
| 40 |
-
"audio_encoder.model.decoder.model.2.block.1.weight_v": "model-
|
| 41 |
-
"audio_encoder.model.decoder.model.2.block.2.block.0.alpha": "model-
|
| 42 |
-
"audio_encoder.model.decoder.model.2.block.2.block.1.bias": "model-
|
| 43 |
-
"audio_encoder.model.decoder.model.2.block.2.block.1.weight_g": "model-
|
| 44 |
-
"audio_encoder.model.decoder.model.2.block.2.block.1.weight_v": "model-
|
| 45 |
-
"audio_encoder.model.decoder.model.2.block.2.block.2.alpha": "model-
|
| 46 |
-
"audio_encoder.model.decoder.model.2.block.2.block.3.bias": "model-
|
| 47 |
-
"audio_encoder.model.decoder.model.2.block.2.block.3.weight_g": "model-
|
| 48 |
-
"audio_encoder.model.decoder.model.2.block.2.block.3.weight_v": "model-
|
| 49 |
-
"audio_encoder.model.decoder.model.2.block.3.block.0.alpha": "model-
|
| 50 |
-
"audio_encoder.model.decoder.model.2.block.3.block.1.bias": "model-
|
| 51 |
-
"audio_encoder.model.decoder.model.2.block.3.block.1.weight_g": "model-
|
| 52 |
-
"audio_encoder.model.decoder.model.2.block.3.block.1.weight_v": "model-
|
| 53 |
-
"audio_encoder.model.decoder.model.2.block.3.block.2.alpha": "model-
|
| 54 |
-
"audio_encoder.model.decoder.model.2.block.3.block.3.bias": "model-
|
| 55 |
-
"audio_encoder.model.decoder.model.2.block.3.block.3.weight_g": "model-
|
| 56 |
-
"audio_encoder.model.decoder.model.2.block.3.block.3.weight_v": "model-
|
| 57 |
-
"audio_encoder.model.decoder.model.2.block.4.block.0.alpha": "model-
|
| 58 |
-
"audio_encoder.model.decoder.model.2.block.4.block.1.bias": "model-
|
| 59 |
-
"audio_encoder.model.decoder.model.2.block.4.block.1.weight_g": "model-
|
| 60 |
-
"audio_encoder.model.decoder.model.2.block.4.block.1.weight_v": "model-
|
| 61 |
-
"audio_encoder.model.decoder.model.2.block.4.block.2.alpha": "model-
|
| 62 |
-
"audio_encoder.model.decoder.model.2.block.4.block.3.bias": "model-
|
| 63 |
-
"audio_encoder.model.decoder.model.2.block.4.block.3.weight_g": "model-
|
| 64 |
-
"audio_encoder.model.decoder.model.2.block.4.block.3.weight_v": "model-
|
| 65 |
-
"audio_encoder.model.decoder.model.3.block.0.alpha": "model-
|
| 66 |
-
"audio_encoder.model.decoder.model.3.block.1.bias": "model-
|
| 67 |
-
"audio_encoder.model.decoder.model.3.block.1.weight_g": "model-
|
| 68 |
-
"audio_encoder.model.decoder.model.3.block.1.weight_v": "model-
|
| 69 |
-
"audio_encoder.model.decoder.model.3.block.2.block.0.alpha": "model-
|
| 70 |
-
"audio_encoder.model.decoder.model.3.block.2.block.1.bias": "model-
|
| 71 |
-
"audio_encoder.model.decoder.model.3.block.2.block.1.weight_g": "model-
|
| 72 |
-
"audio_encoder.model.decoder.model.3.block.2.block.1.weight_v": "model-
|
| 73 |
-
"audio_encoder.model.decoder.model.3.block.2.block.2.alpha": "model-
|
| 74 |
-
"audio_encoder.model.decoder.model.3.block.2.block.3.bias": "model-
|
| 75 |
-
"audio_encoder.model.decoder.model.3.block.2.block.3.weight_g": "model-
|
| 76 |
-
"audio_encoder.model.decoder.model.3.block.2.block.3.weight_v": "model-
|
| 77 |
-
"audio_encoder.model.decoder.model.3.block.3.block.0.alpha": "model-
|
| 78 |
-
"audio_encoder.model.decoder.model.3.block.3.block.1.bias": "model-
|
| 79 |
-
"audio_encoder.model.decoder.model.3.block.3.block.1.weight_g": "model-
|
| 80 |
-
"audio_encoder.model.decoder.model.3.block.3.block.1.weight_v": "model-
|
| 81 |
-
"audio_encoder.model.decoder.model.3.block.3.block.2.alpha": "model-
|
| 82 |
-
"audio_encoder.model.decoder.model.3.block.3.block.3.bias": "model-
|
| 83 |
-
"audio_encoder.model.decoder.model.3.block.3.block.3.weight_g": "model-
|
| 84 |
-
"audio_encoder.model.decoder.model.3.block.3.block.3.weight_v": "model-
|
| 85 |
-
"audio_encoder.model.decoder.model.3.block.4.block.0.alpha": "model-
|
| 86 |
-
"audio_encoder.model.decoder.model.3.block.4.block.1.bias": "model-
|
| 87 |
-
"audio_encoder.model.decoder.model.3.block.4.block.1.weight_g": "model-
|
| 88 |
-
"audio_encoder.model.decoder.model.3.block.4.block.1.weight_v": "model-
|
| 89 |
-
"audio_encoder.model.decoder.model.3.block.4.block.2.alpha": "model-
|
| 90 |
-
"audio_encoder.model.decoder.model.3.block.4.block.3.bias": "model-
|
| 91 |
-
"audio_encoder.model.decoder.model.3.block.4.block.3.weight_g": "model-
|
| 92 |
-
"audio_encoder.model.decoder.model.3.block.4.block.3.weight_v": "model-
|
| 93 |
-
"audio_encoder.model.decoder.model.4.block.0.alpha": "model-
|
| 94 |
-
"audio_encoder.model.decoder.model.4.block.1.bias": "model-
|
| 95 |
-
"audio_encoder.model.decoder.model.4.block.1.weight_g": "model-
|
| 96 |
-
"audio_encoder.model.decoder.model.4.block.1.weight_v": "model-
|
| 97 |
-
"audio_encoder.model.decoder.model.4.block.2.block.0.alpha": "model-
|
| 98 |
-
"audio_encoder.model.decoder.model.4.block.2.block.1.bias": "model-
|
| 99 |
-
"audio_encoder.model.decoder.model.4.block.2.block.1.weight_g": "model-
|
| 100 |
-
"audio_encoder.model.decoder.model.4.block.2.block.1.weight_v": "model-
|
| 101 |
-
"audio_encoder.model.decoder.model.4.block.2.block.2.alpha": "model-
|
| 102 |
-
"audio_encoder.model.decoder.model.4.block.2.block.3.bias": "model-
|
| 103 |
-
"audio_encoder.model.decoder.model.4.block.2.block.3.weight_g": "model-
|
| 104 |
-
"audio_encoder.model.decoder.model.4.block.2.block.3.weight_v": "model-
|
| 105 |
-
"audio_encoder.model.decoder.model.4.block.3.block.0.alpha": "model-
|
| 106 |
-
"audio_encoder.model.decoder.model.4.block.3.block.1.bias": "model-
|
| 107 |
-
"audio_encoder.model.decoder.model.4.block.3.block.1.weight_g": "model-
|
| 108 |
-
"audio_encoder.model.decoder.model.4.block.3.block.1.weight_v": "model-
|
| 109 |
-
"audio_encoder.model.decoder.model.4.block.3.block.2.alpha": "model-
|
| 110 |
-
"audio_encoder.model.decoder.model.4.block.3.block.3.bias": "model-
|
| 111 |
-
"audio_encoder.model.decoder.model.4.block.3.block.3.weight_g": "model-
|
| 112 |
-
"audio_encoder.model.decoder.model.4.block.3.block.3.weight_v": "model-
|
| 113 |
-
"audio_encoder.model.decoder.model.4.block.4.block.0.alpha": "model-
|
| 114 |
-
"audio_encoder.model.decoder.model.4.block.4.block.1.bias": "model-
|
| 115 |
-
"audio_encoder.model.decoder.model.4.block.4.block.1.weight_g": "model-
|
| 116 |
-
"audio_encoder.model.decoder.model.4.block.4.block.1.weight_v": "model-
|
| 117 |
-
"audio_encoder.model.decoder.model.4.block.4.block.2.alpha": "model-
|
| 118 |
-
"audio_encoder.model.decoder.model.4.block.4.block.3.bias": "model-
|
| 119 |
-
"audio_encoder.model.decoder.model.4.block.4.block.3.weight_g": "model-
|
| 120 |
-
"audio_encoder.model.decoder.model.4.block.4.block.3.weight_v": "model-
|
| 121 |
-
"audio_encoder.model.decoder.model.5.alpha": "model-
|
| 122 |
-
"audio_encoder.model.decoder.model.6.bias": "model-
|
| 123 |
-
"audio_encoder.model.decoder.model.6.weight_g": "model-
|
| 124 |
-
"audio_encoder.model.decoder.model.6.weight_v": "model-
|
| 125 |
"audio_encoder.model.encoder.block.0.bias": "model-00001-of-00003.safetensors",
|
| 126 |
"audio_encoder.model.encoder.block.0.weight_g": "model-00001-of-00003.safetensors",
|
| 127 |
"audio_encoder.model.encoder.block.0.weight_v": "model-00001-of-00003.safetensors",
|
|
@@ -304,123 +304,123 @@
|
|
| 304 |
"audio_encoder.model.quantizer.quantizers.8.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 305 |
"audio_encoder.model.quantizer.quantizers.8.out_proj.weight_g": "model-00001-of-00003.safetensors",
|
| 306 |
"audio_encoder.model.quantizer.quantizers.8.out_proj.weight_v": "model-00001-of-00003.safetensors",
|
| 307 |
-
"decoder.lm_heads.0.weight": "model-
|
| 308 |
-
"decoder.lm_heads.1.weight": "model-
|
| 309 |
-
"decoder.lm_heads.2.weight": "model-
|
| 310 |
-
"decoder.lm_heads.3.weight": "model-
|
| 311 |
-
"decoder.lm_heads.4.weight": "model-
|
| 312 |
-
"decoder.lm_heads.5.weight": "model-
|
| 313 |
-
"decoder.lm_heads.6.weight": "model-
|
| 314 |
-
"decoder.lm_heads.7.weight": "model-
|
| 315 |
-
"decoder.lm_heads.8.weight": "model-
|
| 316 |
-
"decoder.model.decoder.embed_positions.weights": "model-
|
| 317 |
-
"decoder.model.decoder.embed_tokens.0.weight": "model-
|
| 318 |
-
"decoder.model.decoder.embed_tokens.1.weight": "model-
|
| 319 |
-
"decoder.model.decoder.embed_tokens.2.weight": "model-
|
| 320 |
-
"decoder.model.decoder.embed_tokens.3.weight": "model-
|
| 321 |
-
"decoder.model.decoder.embed_tokens.4.weight": "model-
|
| 322 |
-
"decoder.model.decoder.embed_tokens.5.weight": "model-
|
| 323 |
-
"decoder.model.decoder.embed_tokens.6.weight": "model-
|
| 324 |
-
"decoder.model.decoder.embed_tokens.7.weight": "model-
|
| 325 |
-
"decoder.model.decoder.embed_tokens.8.weight": "model-
|
| 326 |
-
"decoder.model.decoder.layer_norm.bias": "model-
|
| 327 |
-
"decoder.model.decoder.layer_norm.weight": "model-
|
| 328 |
-
"decoder.model.decoder.layers.0.encoder_attn.k_proj.weight": "model-
|
| 329 |
-
"decoder.model.decoder.layers.0.encoder_attn.out_proj.weight": "model-
|
| 330 |
-
"decoder.model.decoder.layers.0.encoder_attn.q_proj.weight": "model-
|
| 331 |
-
"decoder.model.decoder.layers.0.encoder_attn.v_proj.weight": "model-
|
| 332 |
-
"decoder.model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-
|
| 333 |
-
"decoder.model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-
|
| 334 |
-
"decoder.model.decoder.layers.0.fc1.weight": "model-
|
| 335 |
-
"decoder.model.decoder.layers.0.fc2.weight": "model-
|
| 336 |
-
"decoder.model.decoder.layers.0.final_layer_norm.bias": "model-
|
| 337 |
-
"decoder.model.decoder.layers.0.final_layer_norm.weight": "model-
|
| 338 |
-
"decoder.model.decoder.layers.0.self_attn.k_proj.weight": "model-
|
| 339 |
-
"decoder.model.decoder.layers.0.self_attn.out_proj.weight": "model-
|
| 340 |
-
"decoder.model.decoder.layers.0.self_attn.q_proj.weight": "model-
|
| 341 |
-
"decoder.model.decoder.layers.0.self_attn.v_proj.weight": "model-
|
| 342 |
-
"decoder.model.decoder.layers.0.self_attn_layer_norm.bias": "model-
|
| 343 |
-
"decoder.model.decoder.layers.0.self_attn_layer_norm.weight": "model-
|
| 344 |
-
"decoder.model.decoder.layers.1.encoder_attn.k_proj.weight": "model-
|
| 345 |
-
"decoder.model.decoder.layers.1.encoder_attn.out_proj.weight": "model-
|
| 346 |
-
"decoder.model.decoder.layers.1.encoder_attn.q_proj.weight": "model-
|
| 347 |
-
"decoder.model.decoder.layers.1.encoder_attn.v_proj.weight": "model-
|
| 348 |
-
"decoder.model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-
|
| 349 |
-
"decoder.model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-
|
| 350 |
-
"decoder.model.decoder.layers.1.fc1.weight": "model-
|
| 351 |
-
"decoder.model.decoder.layers.1.fc2.weight": "model-
|
| 352 |
-
"decoder.model.decoder.layers.1.final_layer_norm.bias": "model-
|
| 353 |
-
"decoder.model.decoder.layers.1.final_layer_norm.weight": "model-
|
| 354 |
-
"decoder.model.decoder.layers.1.self_attn.k_proj.weight": "model-
|
| 355 |
-
"decoder.model.decoder.layers.1.self_attn.out_proj.weight": "model-
|
| 356 |
-
"decoder.model.decoder.layers.1.self_attn.q_proj.weight": "model-
|
| 357 |
-
"decoder.model.decoder.layers.1.self_attn.v_proj.weight": "model-
|
| 358 |
-
"decoder.model.decoder.layers.1.self_attn_layer_norm.bias": "model-
|
| 359 |
-
"decoder.model.decoder.layers.1.self_attn_layer_norm.weight": "model-
|
| 360 |
-
"decoder.model.decoder.layers.10.encoder_attn.k_proj.weight": "model-
|
| 361 |
-
"decoder.model.decoder.layers.10.encoder_attn.out_proj.weight": "model-
|
| 362 |
-
"decoder.model.decoder.layers.10.encoder_attn.q_proj.weight": "model-
|
| 363 |
-
"decoder.model.decoder.layers.10.encoder_attn.v_proj.weight": "model-
|
| 364 |
-
"decoder.model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-
|
| 365 |
-
"decoder.model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-
|
| 366 |
-
"decoder.model.decoder.layers.10.fc1.weight": "model-
|
| 367 |
-
"decoder.model.decoder.layers.10.fc2.weight": "model-
|
| 368 |
-
"decoder.model.decoder.layers.10.final_layer_norm.bias": "model-
|
| 369 |
-
"decoder.model.decoder.layers.10.final_layer_norm.weight": "model-
|
| 370 |
-
"decoder.model.decoder.layers.10.self_attn.k_proj.weight": "model-
|
| 371 |
-
"decoder.model.decoder.layers.10.self_attn.out_proj.weight": "model-
|
| 372 |
-
"decoder.model.decoder.layers.10.self_attn.q_proj.weight": "model-
|
| 373 |
-
"decoder.model.decoder.layers.10.self_attn.v_proj.weight": "model-
|
| 374 |
-
"decoder.model.decoder.layers.10.self_attn_layer_norm.bias": "model-
|
| 375 |
-
"decoder.model.decoder.layers.10.self_attn_layer_norm.weight": "model-
|
| 376 |
-
"decoder.model.decoder.layers.11.encoder_attn.k_proj.weight": "model-
|
| 377 |
-
"decoder.model.decoder.layers.11.encoder_attn.out_proj.weight": "model-
|
| 378 |
-
"decoder.model.decoder.layers.11.encoder_attn.q_proj.weight": "model-
|
| 379 |
-
"decoder.model.decoder.layers.11.encoder_attn.v_proj.weight": "model-
|
| 380 |
-
"decoder.model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-
|
| 381 |
-
"decoder.model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-
|
| 382 |
-
"decoder.model.decoder.layers.11.fc1.weight": "model-
|
| 383 |
-
"decoder.model.decoder.layers.11.fc2.weight": "model-
|
| 384 |
-
"decoder.model.decoder.layers.11.final_layer_norm.bias": "model-
|
| 385 |
-
"decoder.model.decoder.layers.11.final_layer_norm.weight": "model-
|
| 386 |
-
"decoder.model.decoder.layers.11.self_attn.k_proj.weight": "model-
|
| 387 |
-
"decoder.model.decoder.layers.11.self_attn.out_proj.weight": "model-
|
| 388 |
-
"decoder.model.decoder.layers.11.self_attn.q_proj.weight": "model-
|
| 389 |
-
"decoder.model.decoder.layers.11.self_attn.v_proj.weight": "model-
|
| 390 |
-
"decoder.model.decoder.layers.11.self_attn_layer_norm.bias": "model-
|
| 391 |
-
"decoder.model.decoder.layers.11.self_attn_layer_norm.weight": "model-
|
| 392 |
-
"decoder.model.decoder.layers.12.encoder_attn.k_proj.weight": "model-
|
| 393 |
-
"decoder.model.decoder.layers.12.encoder_attn.out_proj.weight": "model-
|
| 394 |
-
"decoder.model.decoder.layers.12.encoder_attn.q_proj.weight": "model-
|
| 395 |
-
"decoder.model.decoder.layers.12.encoder_attn.v_proj.weight": "model-
|
| 396 |
-
"decoder.model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-
|
| 397 |
-
"decoder.model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-
|
| 398 |
-
"decoder.model.decoder.layers.12.fc1.weight": "model-
|
| 399 |
-
"decoder.model.decoder.layers.12.fc2.weight": "model-
|
| 400 |
-
"decoder.model.decoder.layers.12.final_layer_norm.bias": "model-
|
| 401 |
-
"decoder.model.decoder.layers.12.final_layer_norm.weight": "model-
|
| 402 |
-
"decoder.model.decoder.layers.12.self_attn.k_proj.weight": "model-
|
| 403 |
-
"decoder.model.decoder.layers.12.self_attn.out_proj.weight": "model-
|
| 404 |
-
"decoder.model.decoder.layers.12.self_attn.q_proj.weight": "model-
|
| 405 |
-
"decoder.model.decoder.layers.12.self_attn.v_proj.weight": "model-
|
| 406 |
-
"decoder.model.decoder.layers.12.self_attn_layer_norm.bias": "model-
|
| 407 |
-
"decoder.model.decoder.layers.12.self_attn_layer_norm.weight": "model-
|
| 408 |
-
"decoder.model.decoder.layers.13.encoder_attn.k_proj.weight": "model-
|
| 409 |
-
"decoder.model.decoder.layers.13.encoder_attn.out_proj.weight": "model-
|
| 410 |
-
"decoder.model.decoder.layers.13.encoder_attn.q_proj.weight": "model-
|
| 411 |
-
"decoder.model.decoder.layers.13.encoder_attn.v_proj.weight": "model-
|
| 412 |
-
"decoder.model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-
|
| 413 |
-
"decoder.model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-
|
| 414 |
"decoder.model.decoder.layers.13.fc1.weight": "model-00002-of-00003.safetensors",
|
| 415 |
"decoder.model.decoder.layers.13.fc2.weight": "model-00002-of-00003.safetensors",
|
| 416 |
"decoder.model.decoder.layers.13.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 417 |
"decoder.model.decoder.layers.13.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 418 |
-
"decoder.model.decoder.layers.13.self_attn.k_proj.weight": "model-
|
| 419 |
-
"decoder.model.decoder.layers.13.self_attn.out_proj.weight": "model-
|
| 420 |
-
"decoder.model.decoder.layers.13.self_attn.q_proj.weight": "model-
|
| 421 |
-
"decoder.model.decoder.layers.13.self_attn.v_proj.weight": "model-
|
| 422 |
-
"decoder.model.decoder.layers.13.self_attn_layer_norm.bias": "model-
|
| 423 |
-
"decoder.model.decoder.layers.13.self_attn_layer_norm.weight": "model-
|
| 424 |
"decoder.model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 425 |
"decoder.model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 426 |
"decoder.model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
|
@@ -517,22 +517,22 @@
|
|
| 517 |
"decoder.model.decoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 518 |
"decoder.model.decoder.layers.19.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 519 |
"decoder.model.decoder.layers.19.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 520 |
-
"decoder.model.decoder.layers.2.encoder_attn.k_proj.weight": "model-
|
| 521 |
-
"decoder.model.decoder.layers.2.encoder_attn.out_proj.weight": "model-
|
| 522 |
-
"decoder.model.decoder.layers.2.encoder_attn.q_proj.weight": "model-
|
| 523 |
-
"decoder.model.decoder.layers.2.encoder_attn.v_proj.weight": "model-
|
| 524 |
-
"decoder.model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-
|
| 525 |
-
"decoder.model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-
|
| 526 |
-
"decoder.model.decoder.layers.2.fc1.weight": "model-
|
| 527 |
-
"decoder.model.decoder.layers.2.fc2.weight": "model-
|
| 528 |
-
"decoder.model.decoder.layers.2.final_layer_norm.bias": "model-
|
| 529 |
-
"decoder.model.decoder.layers.2.final_layer_norm.weight": "model-
|
| 530 |
-
"decoder.model.decoder.layers.2.self_attn.k_proj.weight": "model-
|
| 531 |
-
"decoder.model.decoder.layers.2.self_attn.out_proj.weight": "model-
|
| 532 |
-
"decoder.model.decoder.layers.2.self_attn.q_proj.weight": "model-
|
| 533 |
-
"decoder.model.decoder.layers.2.self_attn.v_proj.weight": "model-
|
| 534 |
-
"decoder.model.decoder.layers.2.self_attn_layer_norm.bias": "model-
|
| 535 |
-
"decoder.model.decoder.layers.2.self_attn_layer_norm.weight": "model-
|
| 536 |
"decoder.model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 537 |
"decoder.model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 538 |
"decoder.model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
|
@@ -693,22 +693,22 @@
|
|
| 693 |
"decoder.model.decoder.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 694 |
"decoder.model.decoder.layers.29.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 695 |
"decoder.model.decoder.layers.29.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 696 |
-
"decoder.model.decoder.layers.3.encoder_attn.k_proj.weight": "model-
|
| 697 |
-
"decoder.model.decoder.layers.3.encoder_attn.out_proj.weight": "model-
|
| 698 |
-
"decoder.model.decoder.layers.3.encoder_attn.q_proj.weight": "model-
|
| 699 |
-
"decoder.model.decoder.layers.3.encoder_attn.v_proj.weight": "model-
|
| 700 |
-
"decoder.model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-
|
| 701 |
-
"decoder.model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-
|
| 702 |
-
"decoder.model.decoder.layers.3.fc1.weight": "model-
|
| 703 |
-
"decoder.model.decoder.layers.3.fc2.weight": "model-
|
| 704 |
-
"decoder.model.decoder.layers.3.final_layer_norm.bias": "model-
|
| 705 |
-
"decoder.model.decoder.layers.3.final_layer_norm.weight": "model-
|
| 706 |
-
"decoder.model.decoder.layers.3.self_attn.k_proj.weight": "model-
|
| 707 |
-
"decoder.model.decoder.layers.3.self_attn.out_proj.weight": "model-
|
| 708 |
-
"decoder.model.decoder.layers.3.self_attn.q_proj.weight": "model-
|
| 709 |
-
"decoder.model.decoder.layers.3.self_attn.v_proj.weight": "model-
|
| 710 |
-
"decoder.model.decoder.layers.3.self_attn_layer_norm.bias": "model-
|
| 711 |
-
"decoder.model.decoder.layers.3.self_attn_layer_norm.weight": "model-
|
| 712 |
"decoder.model.decoder.layers.30.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 713 |
"decoder.model.decoder.layers.30.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 714 |
"decoder.model.decoder.layers.30.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
|
@@ -741,169 +741,106 @@
|
|
| 741 |
"decoder.model.decoder.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 742 |
"decoder.model.decoder.layers.31.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 743 |
"decoder.model.decoder.layers.31.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 744 |
-
"decoder.model.decoder.layers.
|
| 745 |
-
"decoder.model.decoder.layers.
|
| 746 |
-
"decoder.model.decoder.layers.
|
| 747 |
-
"decoder.model.decoder.layers.
|
| 748 |
-
"decoder.model.decoder.layers.
|
| 749 |
-
"decoder.model.decoder.layers.
|
| 750 |
-
"decoder.model.decoder.layers.
|
| 751 |
-
"decoder.model.decoder.layers.
|
| 752 |
-
"decoder.model.decoder.layers.
|
| 753 |
-
"decoder.model.decoder.layers.
|
| 754 |
-
"decoder.model.decoder.layers.
|
| 755 |
-
"decoder.model.decoder.layers.
|
| 756 |
-
"decoder.model.decoder.layers.
|
| 757 |
-
"decoder.model.decoder.layers.
|
| 758 |
-
"decoder.model.decoder.layers.
|
| 759 |
-
"decoder.model.decoder.layers.
|
| 760 |
-
"decoder.model.decoder.layers.
|
| 761 |
-
"decoder.model.decoder.layers.
|
| 762 |
-
"decoder.model.decoder.layers.
|
| 763 |
-
"decoder.model.decoder.layers.
|
| 764 |
-
"decoder.model.decoder.layers.
|
| 765 |
-
"decoder.model.decoder.layers.
|
| 766 |
-
"decoder.model.decoder.layers.
|
| 767 |
-
"decoder.model.decoder.layers.
|
| 768 |
-
"decoder.model.decoder.layers.
|
| 769 |
-
"decoder.model.decoder.layers.
|
| 770 |
-
"decoder.model.decoder.layers.
|
| 771 |
-
"decoder.model.decoder.layers.
|
| 772 |
-
"decoder.model.decoder.layers.
|
| 773 |
-
"decoder.model.decoder.layers.
|
| 774 |
-
"decoder.model.decoder.layers.
|
| 775 |
-
"decoder.model.decoder.layers.
|
| 776 |
-
"decoder.model.decoder.layers.
|
| 777 |
-
"decoder.model.decoder.layers.
|
| 778 |
-
"decoder.model.decoder.layers.
|
| 779 |
-
"decoder.model.decoder.layers.
|
| 780 |
-
"decoder.model.decoder.layers.
|
| 781 |
-
"decoder.model.decoder.layers.
|
| 782 |
-
"decoder.model.decoder.layers.
|
| 783 |
-
"decoder.model.decoder.layers.
|
| 784 |
-
"decoder.model.decoder.layers.
|
| 785 |
-
"decoder.model.decoder.layers.
|
| 786 |
-
"decoder.model.decoder.layers.
|
| 787 |
-
"decoder.model.decoder.layers.
|
| 788 |
-
"decoder.model.decoder.layers.
|
| 789 |
-
"decoder.model.decoder.layers.
|
| 790 |
-
"decoder.model.decoder.layers.
|
| 791 |
-
"decoder.model.decoder.layers.
|
| 792 |
-
"decoder.model.decoder.layers.
|
| 793 |
-
"decoder.model.decoder.layers.
|
| 794 |
-
"decoder.model.decoder.layers.
|
| 795 |
-
"decoder.model.decoder.layers.
|
| 796 |
-
"decoder.model.decoder.layers.
|
| 797 |
-
"decoder.model.decoder.layers.
|
| 798 |
-
"decoder.model.decoder.layers.
|
| 799 |
-
"decoder.model.decoder.layers.
|
| 800 |
-
"decoder.model.decoder.layers.
|
| 801 |
-
"decoder.model.decoder.layers.
|
| 802 |
-
"decoder.model.decoder.layers.
|
| 803 |
-
"decoder.model.decoder.layers.
|
| 804 |
-
"decoder.model.decoder.layers.
|
| 805 |
-
"decoder.model.decoder.layers.
|
| 806 |
-
"decoder.model.decoder.layers.
|
| 807 |
-
"decoder.model.decoder.layers.
|
| 808 |
-
"decoder.model.decoder.layers.
|
| 809 |
-
"decoder.model.decoder.layers.
|
| 810 |
-
"decoder.model.decoder.layers.
|
| 811 |
-
"decoder.model.decoder.layers.
|
| 812 |
-
"decoder.model.decoder.layers.
|
| 813 |
-
"decoder.model.decoder.layers.
|
| 814 |
-
"decoder.model.decoder.layers.
|
| 815 |
-
"decoder.model.decoder.layers.
|
| 816 |
-
"decoder.model.decoder.layers.
|
| 817 |
-
"decoder.model.decoder.layers.
|
| 818 |
-
"decoder.model.decoder.layers.
|
| 819 |
-
"decoder.model.decoder.layers.
|
| 820 |
-
"decoder.model.decoder.layers.
|
| 821 |
-
"decoder.model.decoder.layers.
|
| 822 |
-
"decoder.model.decoder.layers.
|
| 823 |
-
"decoder.model.decoder.layers.
|
| 824 |
-
"decoder.model.decoder.layers.
|
| 825 |
-
"decoder.model.decoder.layers.
|
| 826 |
-
"decoder.model.decoder.layers.
|
| 827 |
-
"decoder.model.decoder.layers.
|
| 828 |
-
"decoder.model.decoder.layers.
|
| 829 |
-
"decoder.model.decoder.layers.
|
| 830 |
-
"decoder.model.decoder.layers.
|
| 831 |
-
"decoder.model.decoder.layers.
|
| 832 |
-
"decoder.model.decoder.layers.
|
| 833 |
-
"decoder.model.decoder.layers.
|
| 834 |
-
"decoder.model.decoder.layers.
|
| 835 |
-
"decoder.model.decoder.layers.
|
| 836 |
-
"decoder.model.decoder.layers.
|
| 837 |
-
"decoder.model.decoder.layers.
|
| 838 |
-
"decoder.model.decoder.layers.
|
| 839 |
-
"decoder.model.decoder.layers.
|
| 840 |
-
"
|
| 841 |
-
"decoder.model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 842 |
-
"decoder.model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 843 |
-
"decoder.model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 844 |
-
"decoder.model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 845 |
-
"decoder.model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 846 |
-
"decoder.model.decoder.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
|
| 847 |
-
"decoder.model.decoder.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
|
| 848 |
-
"decoder.model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 849 |
-
"decoder.model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 850 |
-
"decoder.model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 851 |
-
"decoder.model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 852 |
-
"decoder.model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 853 |
-
"decoder.model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 854 |
-
"decoder.model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 855 |
-
"decoder.model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 856 |
-
"decoder.model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 857 |
-
"decoder.model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 858 |
-
"decoder.model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 859 |
-
"decoder.model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 860 |
-
"decoder.model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 861 |
-
"decoder.model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 862 |
-
"decoder.model.decoder.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
|
| 863 |
-
"decoder.model.decoder.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
|
| 864 |
-
"decoder.model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 865 |
-
"decoder.model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 866 |
-
"decoder.model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 867 |
-
"decoder.model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 868 |
-
"decoder.model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 869 |
-
"decoder.model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 870 |
-
"decoder.model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 871 |
-
"decoder.model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 872 |
-
"decoder.model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 873 |
-
"decoder.model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 874 |
-
"decoder.model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 875 |
-
"decoder.model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 876 |
-
"decoder.model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 877 |
-
"decoder.model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 878 |
-
"decoder.model.decoder.layers.8.fc1.weight": "model-00001-of-00003.safetensors",
|
| 879 |
-
"decoder.model.decoder.layers.8.fc2.weight": "model-00001-of-00003.safetensors",
|
| 880 |
-
"decoder.model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 881 |
-
"decoder.model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 882 |
-
"decoder.model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 883 |
-
"decoder.model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 884 |
-
"decoder.model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 885 |
-
"decoder.model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 886 |
-
"decoder.model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 887 |
-
"decoder.model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 888 |
-
"decoder.model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 889 |
-
"decoder.model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 890 |
-
"decoder.model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 891 |
-
"decoder.model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 892 |
-
"decoder.model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 893 |
-
"decoder.model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 894 |
-
"decoder.model.decoder.layers.9.fc1.weight": "model-00001-of-00003.safetensors",
|
| 895 |
-
"decoder.model.decoder.layers.9.fc2.weight": "model-00001-of-00003.safetensors",
|
| 896 |
-
"decoder.model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 897 |
-
"decoder.model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 898 |
-
"decoder.model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 899 |
-
"decoder.model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 900 |
-
"decoder.model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 901 |
-
"decoder.model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 902 |
-
"decoder.model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
| 903 |
-
"decoder.model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
| 904 |
"embed_prompts.weight": "model-00003-of-00003.safetensors",
|
| 905 |
-
"enc_to_dec_proj.bias": "model-
|
| 906 |
-
"enc_to_dec_proj.weight": "model-
|
| 907 |
"text_encoder.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
| 908 |
"text_encoder.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
| 909 |
"text_encoder.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 10011788744
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"audio_encoder.model.decoder.model.0.bias": "model-00001-of-00003.safetensors",
|
| 7 |
"audio_encoder.model.decoder.model.0.weight_g": "model-00001-of-00003.safetensors",
|
| 8 |
+
"audio_encoder.model.decoder.model.0.weight_v": "model-00002-of-00003.safetensors",
|
| 9 |
+
"audio_encoder.model.decoder.model.1.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 10 |
+
"audio_encoder.model.decoder.model.1.block.1.bias": "model-00002-of-00003.safetensors",
|
| 11 |
+
"audio_encoder.model.decoder.model.1.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 12 |
+
"audio_encoder.model.decoder.model.1.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 13 |
+
"audio_encoder.model.decoder.model.1.block.2.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 14 |
+
"audio_encoder.model.decoder.model.1.block.2.block.1.bias": "model-00002-of-00003.safetensors",
|
| 15 |
+
"audio_encoder.model.decoder.model.1.block.2.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 16 |
+
"audio_encoder.model.decoder.model.1.block.2.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 17 |
+
"audio_encoder.model.decoder.model.1.block.2.block.2.alpha": "model-00002-of-00003.safetensors",
|
| 18 |
+
"audio_encoder.model.decoder.model.1.block.2.block.3.bias": "model-00002-of-00003.safetensors",
|
| 19 |
+
"audio_encoder.model.decoder.model.1.block.2.block.3.weight_g": "model-00002-of-00003.safetensors",
|
| 20 |
+
"audio_encoder.model.decoder.model.1.block.2.block.3.weight_v": "model-00002-of-00003.safetensors",
|
| 21 |
+
"audio_encoder.model.decoder.model.1.block.3.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 22 |
+
"audio_encoder.model.decoder.model.1.block.3.block.1.bias": "model-00002-of-00003.safetensors",
|
| 23 |
+
"audio_encoder.model.decoder.model.1.block.3.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 24 |
+
"audio_encoder.model.decoder.model.1.block.3.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 25 |
+
"audio_encoder.model.decoder.model.1.block.3.block.2.alpha": "model-00002-of-00003.safetensors",
|
| 26 |
+
"audio_encoder.model.decoder.model.1.block.3.block.3.bias": "model-00002-of-00003.safetensors",
|
| 27 |
+
"audio_encoder.model.decoder.model.1.block.3.block.3.weight_g": "model-00002-of-00003.safetensors",
|
| 28 |
+
"audio_encoder.model.decoder.model.1.block.3.block.3.weight_v": "model-00002-of-00003.safetensors",
|
| 29 |
+
"audio_encoder.model.decoder.model.1.block.4.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 30 |
+
"audio_encoder.model.decoder.model.1.block.4.block.1.bias": "model-00002-of-00003.safetensors",
|
| 31 |
+
"audio_encoder.model.decoder.model.1.block.4.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 32 |
+
"audio_encoder.model.decoder.model.1.block.4.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 33 |
+
"audio_encoder.model.decoder.model.1.block.4.block.2.alpha": "model-00002-of-00003.safetensors",
|
| 34 |
+
"audio_encoder.model.decoder.model.1.block.4.block.3.bias": "model-00002-of-00003.safetensors",
|
| 35 |
+
"audio_encoder.model.decoder.model.1.block.4.block.3.weight_g": "model-00002-of-00003.safetensors",
|
| 36 |
+
"audio_encoder.model.decoder.model.1.block.4.block.3.weight_v": "model-00002-of-00003.safetensors",
|
| 37 |
+
"audio_encoder.model.decoder.model.2.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 38 |
+
"audio_encoder.model.decoder.model.2.block.1.bias": "model-00002-of-00003.safetensors",
|
| 39 |
+
"audio_encoder.model.decoder.model.2.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 40 |
+
"audio_encoder.model.decoder.model.2.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 41 |
+
"audio_encoder.model.decoder.model.2.block.2.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 42 |
+
"audio_encoder.model.decoder.model.2.block.2.block.1.bias": "model-00002-of-00003.safetensors",
|
| 43 |
+
"audio_encoder.model.decoder.model.2.block.2.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 44 |
+
"audio_encoder.model.decoder.model.2.block.2.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 45 |
+
"audio_encoder.model.decoder.model.2.block.2.block.2.alpha": "model-00002-of-00003.safetensors",
|
| 46 |
+
"audio_encoder.model.decoder.model.2.block.2.block.3.bias": "model-00002-of-00003.safetensors",
|
| 47 |
+
"audio_encoder.model.decoder.model.2.block.2.block.3.weight_g": "model-00002-of-00003.safetensors",
|
| 48 |
+
"audio_encoder.model.decoder.model.2.block.2.block.3.weight_v": "model-00002-of-00003.safetensors",
|
| 49 |
+
"audio_encoder.model.decoder.model.2.block.3.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 50 |
+
"audio_encoder.model.decoder.model.2.block.3.block.1.bias": "model-00002-of-00003.safetensors",
|
| 51 |
+
"audio_encoder.model.decoder.model.2.block.3.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 52 |
+
"audio_encoder.model.decoder.model.2.block.3.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 53 |
+
"audio_encoder.model.decoder.model.2.block.3.block.2.alpha": "model-00002-of-00003.safetensors",
|
| 54 |
+
"audio_encoder.model.decoder.model.2.block.3.block.3.bias": "model-00002-of-00003.safetensors",
|
| 55 |
+
"audio_encoder.model.decoder.model.2.block.3.block.3.weight_g": "model-00002-of-00003.safetensors",
|
| 56 |
+
"audio_encoder.model.decoder.model.2.block.3.block.3.weight_v": "model-00002-of-00003.safetensors",
|
| 57 |
+
"audio_encoder.model.decoder.model.2.block.4.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 58 |
+
"audio_encoder.model.decoder.model.2.block.4.block.1.bias": "model-00002-of-00003.safetensors",
|
| 59 |
+
"audio_encoder.model.decoder.model.2.block.4.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 60 |
+
"audio_encoder.model.decoder.model.2.block.4.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 61 |
+
"audio_encoder.model.decoder.model.2.block.4.block.2.alpha": "model-00002-of-00003.safetensors",
|
| 62 |
+
"audio_encoder.model.decoder.model.2.block.4.block.3.bias": "model-00002-of-00003.safetensors",
|
| 63 |
+
"audio_encoder.model.decoder.model.2.block.4.block.3.weight_g": "model-00002-of-00003.safetensors",
|
| 64 |
+
"audio_encoder.model.decoder.model.2.block.4.block.3.weight_v": "model-00002-of-00003.safetensors",
|
| 65 |
+
"audio_encoder.model.decoder.model.3.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 66 |
+
"audio_encoder.model.decoder.model.3.block.1.bias": "model-00002-of-00003.safetensors",
|
| 67 |
+
"audio_encoder.model.decoder.model.3.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 68 |
+
"audio_encoder.model.decoder.model.3.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 69 |
+
"audio_encoder.model.decoder.model.3.block.2.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 70 |
+
"audio_encoder.model.decoder.model.3.block.2.block.1.bias": "model-00002-of-00003.safetensors",
|
| 71 |
+
"audio_encoder.model.decoder.model.3.block.2.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 72 |
+
"audio_encoder.model.decoder.model.3.block.2.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 73 |
+
"audio_encoder.model.decoder.model.3.block.2.block.2.alpha": "model-00002-of-00003.safetensors",
|
| 74 |
+
"audio_encoder.model.decoder.model.3.block.2.block.3.bias": "model-00002-of-00003.safetensors",
|
| 75 |
+
"audio_encoder.model.decoder.model.3.block.2.block.3.weight_g": "model-00002-of-00003.safetensors",
|
| 76 |
+
"audio_encoder.model.decoder.model.3.block.2.block.3.weight_v": "model-00002-of-00003.safetensors",
|
| 77 |
+
"audio_encoder.model.decoder.model.3.block.3.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 78 |
+
"audio_encoder.model.decoder.model.3.block.3.block.1.bias": "model-00002-of-00003.safetensors",
|
| 79 |
+
"audio_encoder.model.decoder.model.3.block.3.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 80 |
+
"audio_encoder.model.decoder.model.3.block.3.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 81 |
+
"audio_encoder.model.decoder.model.3.block.3.block.2.alpha": "model-00002-of-00003.safetensors",
|
| 82 |
+
"audio_encoder.model.decoder.model.3.block.3.block.3.bias": "model-00002-of-00003.safetensors",
|
| 83 |
+
"audio_encoder.model.decoder.model.3.block.3.block.3.weight_g": "model-00002-of-00003.safetensors",
|
| 84 |
+
"audio_encoder.model.decoder.model.3.block.3.block.3.weight_v": "model-00002-of-00003.safetensors",
|
| 85 |
+
"audio_encoder.model.decoder.model.3.block.4.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 86 |
+
"audio_encoder.model.decoder.model.3.block.4.block.1.bias": "model-00002-of-00003.safetensors",
|
| 87 |
+
"audio_encoder.model.decoder.model.3.block.4.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 88 |
+
"audio_encoder.model.decoder.model.3.block.4.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 89 |
+
"audio_encoder.model.decoder.model.3.block.4.block.2.alpha": "model-00002-of-00003.safetensors",
|
| 90 |
+
"audio_encoder.model.decoder.model.3.block.4.block.3.bias": "model-00002-of-00003.safetensors",
|
| 91 |
+
"audio_encoder.model.decoder.model.3.block.4.block.3.weight_g": "model-00002-of-00003.safetensors",
|
| 92 |
+
"audio_encoder.model.decoder.model.3.block.4.block.3.weight_v": "model-00002-of-00003.safetensors",
|
| 93 |
+
"audio_encoder.model.decoder.model.4.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 94 |
+
"audio_encoder.model.decoder.model.4.block.1.bias": "model-00002-of-00003.safetensors",
|
| 95 |
+
"audio_encoder.model.decoder.model.4.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 96 |
+
"audio_encoder.model.decoder.model.4.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 97 |
+
"audio_encoder.model.decoder.model.4.block.2.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 98 |
+
"audio_encoder.model.decoder.model.4.block.2.block.1.bias": "model-00002-of-00003.safetensors",
|
| 99 |
+
"audio_encoder.model.decoder.model.4.block.2.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 100 |
+
"audio_encoder.model.decoder.model.4.block.2.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 101 |
+
"audio_encoder.model.decoder.model.4.block.2.block.2.alpha": "model-00002-of-00003.safetensors",
|
| 102 |
+
"audio_encoder.model.decoder.model.4.block.2.block.3.bias": "model-00002-of-00003.safetensors",
|
| 103 |
+
"audio_encoder.model.decoder.model.4.block.2.block.3.weight_g": "model-00002-of-00003.safetensors",
|
| 104 |
+
"audio_encoder.model.decoder.model.4.block.2.block.3.weight_v": "model-00002-of-00003.safetensors",
|
| 105 |
+
"audio_encoder.model.decoder.model.4.block.3.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 106 |
+
"audio_encoder.model.decoder.model.4.block.3.block.1.bias": "model-00002-of-00003.safetensors",
|
| 107 |
+
"audio_encoder.model.decoder.model.4.block.3.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 108 |
+
"audio_encoder.model.decoder.model.4.block.3.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 109 |
+
"audio_encoder.model.decoder.model.4.block.3.block.2.alpha": "model-00002-of-00003.safetensors",
|
| 110 |
+
"audio_encoder.model.decoder.model.4.block.3.block.3.bias": "model-00002-of-00003.safetensors",
|
| 111 |
+
"audio_encoder.model.decoder.model.4.block.3.block.3.weight_g": "model-00002-of-00003.safetensors",
|
| 112 |
+
"audio_encoder.model.decoder.model.4.block.3.block.3.weight_v": "model-00002-of-00003.safetensors",
|
| 113 |
+
"audio_encoder.model.decoder.model.4.block.4.block.0.alpha": "model-00002-of-00003.safetensors",
|
| 114 |
+
"audio_encoder.model.decoder.model.4.block.4.block.1.bias": "model-00002-of-00003.safetensors",
|
| 115 |
+
"audio_encoder.model.decoder.model.4.block.4.block.1.weight_g": "model-00002-of-00003.safetensors",
|
| 116 |
+
"audio_encoder.model.decoder.model.4.block.4.block.1.weight_v": "model-00002-of-00003.safetensors",
|
| 117 |
+
"audio_encoder.model.decoder.model.4.block.4.block.2.alpha": "model-00002-of-00003.safetensors",
|
| 118 |
+
"audio_encoder.model.decoder.model.4.block.4.block.3.bias": "model-00002-of-00003.safetensors",
|
| 119 |
+
"audio_encoder.model.decoder.model.4.block.4.block.3.weight_g": "model-00002-of-00003.safetensors",
|
| 120 |
+
"audio_encoder.model.decoder.model.4.block.4.block.3.weight_v": "model-00002-of-00003.safetensors",
|
| 121 |
+
"audio_encoder.model.decoder.model.5.alpha": "model-00002-of-00003.safetensors",
|
| 122 |
+
"audio_encoder.model.decoder.model.6.bias": "model-00002-of-00003.safetensors",
|
| 123 |
+
"audio_encoder.model.decoder.model.6.weight_g": "model-00002-of-00003.safetensors",
|
| 124 |
+
"audio_encoder.model.decoder.model.6.weight_v": "model-00002-of-00003.safetensors",
|
| 125 |
"audio_encoder.model.encoder.block.0.bias": "model-00001-of-00003.safetensors",
|
| 126 |
"audio_encoder.model.encoder.block.0.weight_g": "model-00001-of-00003.safetensors",
|
| 127 |
"audio_encoder.model.encoder.block.0.weight_v": "model-00001-of-00003.safetensors",
|
|
|
|
| 304 |
"audio_encoder.model.quantizer.quantizers.8.out_proj.bias": "model-00001-of-00003.safetensors",
|
| 305 |
"audio_encoder.model.quantizer.quantizers.8.out_proj.weight_g": "model-00001-of-00003.safetensors",
|
| 306 |
"audio_encoder.model.quantizer.quantizers.8.out_proj.weight_v": "model-00001-of-00003.safetensors",
|
| 307 |
+
"decoder.lm_heads.0.weight": "model-00002-of-00003.safetensors",
|
| 308 |
+
"decoder.lm_heads.1.weight": "model-00002-of-00003.safetensors",
|
| 309 |
+
"decoder.lm_heads.2.weight": "model-00002-of-00003.safetensors",
|
| 310 |
+
"decoder.lm_heads.3.weight": "model-00002-of-00003.safetensors",
|
| 311 |
+
"decoder.lm_heads.4.weight": "model-00002-of-00003.safetensors",
|
| 312 |
+
"decoder.lm_heads.5.weight": "model-00002-of-00003.safetensors",
|
| 313 |
+
"decoder.lm_heads.6.weight": "model-00002-of-00003.safetensors",
|
| 314 |
+
"decoder.lm_heads.7.weight": "model-00002-of-00003.safetensors",
|
| 315 |
+
"decoder.lm_heads.8.weight": "model-00002-of-00003.safetensors",
|
| 316 |
+
"decoder.model.decoder.embed_positions.weights": "model-00002-of-00003.safetensors",
|
| 317 |
+
"decoder.model.decoder.embed_tokens.0.weight": "model-00002-of-00003.safetensors",
|
| 318 |
+
"decoder.model.decoder.embed_tokens.1.weight": "model-00002-of-00003.safetensors",
|
| 319 |
+
"decoder.model.decoder.embed_tokens.2.weight": "model-00002-of-00003.safetensors",
|
| 320 |
+
"decoder.model.decoder.embed_tokens.3.weight": "model-00002-of-00003.safetensors",
|
| 321 |
+
"decoder.model.decoder.embed_tokens.4.weight": "model-00002-of-00003.safetensors",
|
| 322 |
+
"decoder.model.decoder.embed_tokens.5.weight": "model-00002-of-00003.safetensors",
|
| 323 |
+
"decoder.model.decoder.embed_tokens.6.weight": "model-00002-of-00003.safetensors",
|
| 324 |
+
"decoder.model.decoder.embed_tokens.7.weight": "model-00002-of-00003.safetensors",
|
| 325 |
+
"decoder.model.decoder.embed_tokens.8.weight": "model-00002-of-00003.safetensors",
|
| 326 |
+
"decoder.model.decoder.layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 327 |
+
"decoder.model.decoder.layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 328 |
+
"decoder.model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 329 |
+
"decoder.model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 330 |
+
"decoder.model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 331 |
+
"decoder.model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 332 |
+
"decoder.model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 333 |
+
"decoder.model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 334 |
+
"decoder.model.decoder.layers.0.fc1.weight": "model-00002-of-00003.safetensors",
|
| 335 |
+
"decoder.model.decoder.layers.0.fc2.weight": "model-00002-of-00003.safetensors",
|
| 336 |
+
"decoder.model.decoder.layers.0.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 337 |
+
"decoder.model.decoder.layers.0.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 338 |
+
"decoder.model.decoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 339 |
+
"decoder.model.decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 340 |
+
"decoder.model.decoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 341 |
+
"decoder.model.decoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 342 |
+
"decoder.model.decoder.layers.0.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 343 |
+
"decoder.model.decoder.layers.0.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 344 |
+
"decoder.model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 345 |
+
"decoder.model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 346 |
+
"decoder.model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 347 |
+
"decoder.model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 348 |
+
"decoder.model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 349 |
+
"decoder.model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 350 |
+
"decoder.model.decoder.layers.1.fc1.weight": "model-00002-of-00003.safetensors",
|
| 351 |
+
"decoder.model.decoder.layers.1.fc2.weight": "model-00002-of-00003.safetensors",
|
| 352 |
+
"decoder.model.decoder.layers.1.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 353 |
+
"decoder.model.decoder.layers.1.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 354 |
+
"decoder.model.decoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 355 |
+
"decoder.model.decoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 356 |
+
"decoder.model.decoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 357 |
+
"decoder.model.decoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 358 |
+
"decoder.model.decoder.layers.1.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 359 |
+
"decoder.model.decoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 360 |
+
"decoder.model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 361 |
+
"decoder.model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 362 |
+
"decoder.model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 363 |
+
"decoder.model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 364 |
+
"decoder.model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 365 |
+
"decoder.model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 366 |
+
"decoder.model.decoder.layers.10.fc1.weight": "model-00002-of-00003.safetensors",
|
| 367 |
+
"decoder.model.decoder.layers.10.fc2.weight": "model-00002-of-00003.safetensors",
|
| 368 |
+
"decoder.model.decoder.layers.10.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 369 |
+
"decoder.model.decoder.layers.10.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 370 |
+
"decoder.model.decoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 371 |
+
"decoder.model.decoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 372 |
+
"decoder.model.decoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 373 |
+
"decoder.model.decoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 374 |
+
"decoder.model.decoder.layers.10.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 375 |
+
"decoder.model.decoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 376 |
+
"decoder.model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 377 |
+
"decoder.model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 378 |
+
"decoder.model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 379 |
+
"decoder.model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 380 |
+
"decoder.model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 381 |
+
"decoder.model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 382 |
+
"decoder.model.decoder.layers.11.fc1.weight": "model-00002-of-00003.safetensors",
|
| 383 |
+
"decoder.model.decoder.layers.11.fc2.weight": "model-00002-of-00003.safetensors",
|
| 384 |
+
"decoder.model.decoder.layers.11.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 385 |
+
"decoder.model.decoder.layers.11.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 386 |
+
"decoder.model.decoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 387 |
+
"decoder.model.decoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 388 |
+
"decoder.model.decoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 389 |
+
"decoder.model.decoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 390 |
+
"decoder.model.decoder.layers.11.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 391 |
+
"decoder.model.decoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 392 |
+
"decoder.model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 393 |
+
"decoder.model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 394 |
+
"decoder.model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 395 |
+
"decoder.model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 396 |
+
"decoder.model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 397 |
+
"decoder.model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 398 |
+
"decoder.model.decoder.layers.12.fc1.weight": "model-00002-of-00003.safetensors",
|
| 399 |
+
"decoder.model.decoder.layers.12.fc2.weight": "model-00002-of-00003.safetensors",
|
| 400 |
+
"decoder.model.decoder.layers.12.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 401 |
+
"decoder.model.decoder.layers.12.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 402 |
+
"decoder.model.decoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 403 |
+
"decoder.model.decoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 404 |
+
"decoder.model.decoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 405 |
+
"decoder.model.decoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 406 |
+
"decoder.model.decoder.layers.12.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 407 |
+
"decoder.model.decoder.layers.12.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 408 |
+
"decoder.model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 409 |
+
"decoder.model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 410 |
+
"decoder.model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 411 |
+
"decoder.model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 412 |
+
"decoder.model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 413 |
+
"decoder.model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 414 |
"decoder.model.decoder.layers.13.fc1.weight": "model-00002-of-00003.safetensors",
|
| 415 |
"decoder.model.decoder.layers.13.fc2.weight": "model-00002-of-00003.safetensors",
|
| 416 |
"decoder.model.decoder.layers.13.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 417 |
"decoder.model.decoder.layers.13.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 418 |
+
"decoder.model.decoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 419 |
+
"decoder.model.decoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 420 |
+
"decoder.model.decoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 421 |
+
"decoder.model.decoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 422 |
+
"decoder.model.decoder.layers.13.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 423 |
+
"decoder.model.decoder.layers.13.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 424 |
"decoder.model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 425 |
"decoder.model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 426 |
"decoder.model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
| 517 |
"decoder.model.decoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 518 |
"decoder.model.decoder.layers.19.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 519 |
"decoder.model.decoder.layers.19.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 520 |
+
"decoder.model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 521 |
+
"decoder.model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 522 |
+
"decoder.model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 523 |
+
"decoder.model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 524 |
+
"decoder.model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 525 |
+
"decoder.model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 526 |
+
"decoder.model.decoder.layers.2.fc1.weight": "model-00002-of-00003.safetensors",
|
| 527 |
+
"decoder.model.decoder.layers.2.fc2.weight": "model-00002-of-00003.safetensors",
|
| 528 |
+
"decoder.model.decoder.layers.2.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 529 |
+
"decoder.model.decoder.layers.2.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 530 |
+
"decoder.model.decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 531 |
+
"decoder.model.decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 532 |
+
"decoder.model.decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 533 |
+
"decoder.model.decoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 534 |
+
"decoder.model.decoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 535 |
+
"decoder.model.decoder.layers.2.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 536 |
"decoder.model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 537 |
"decoder.model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 538 |
"decoder.model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
| 693 |
"decoder.model.decoder.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 694 |
"decoder.model.decoder.layers.29.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 695 |
"decoder.model.decoder.layers.29.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 696 |
+
"decoder.model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 697 |
+
"decoder.model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 698 |
+
"decoder.model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 699 |
+
"decoder.model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 700 |
+
"decoder.model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 701 |
+
"decoder.model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 702 |
+
"decoder.model.decoder.layers.3.fc1.weight": "model-00002-of-00003.safetensors",
|
| 703 |
+
"decoder.model.decoder.layers.3.fc2.weight": "model-00002-of-00003.safetensors",
|
| 704 |
+
"decoder.model.decoder.layers.3.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 705 |
+
"decoder.model.decoder.layers.3.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 706 |
+
"decoder.model.decoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 707 |
+
"decoder.model.decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 708 |
+
"decoder.model.decoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 709 |
+
"decoder.model.decoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 710 |
+
"decoder.model.decoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 711 |
+
"decoder.model.decoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 712 |
"decoder.model.decoder.layers.30.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 713 |
"decoder.model.decoder.layers.30.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 714 |
"decoder.model.decoder.layers.30.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
|
|
|
| 741 |
"decoder.model.decoder.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 742 |
"decoder.model.decoder.layers.31.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 743 |
"decoder.model.decoder.layers.31.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 744 |
+
"decoder.model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 745 |
+
"decoder.model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 746 |
+
"decoder.model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 747 |
+
"decoder.model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 748 |
+
"decoder.model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 749 |
+
"decoder.model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 750 |
+
"decoder.model.decoder.layers.4.fc1.weight": "model-00002-of-00003.safetensors",
|
| 751 |
+
"decoder.model.decoder.layers.4.fc2.weight": "model-00002-of-00003.safetensors",
|
| 752 |
+
"decoder.model.decoder.layers.4.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 753 |
+
"decoder.model.decoder.layers.4.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 754 |
+
"decoder.model.decoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 755 |
+
"decoder.model.decoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 756 |
+
"decoder.model.decoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 757 |
+
"decoder.model.decoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 758 |
+
"decoder.model.decoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 759 |
+
"decoder.model.decoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 760 |
+
"decoder.model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 761 |
+
"decoder.model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 762 |
+
"decoder.model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 763 |
+
"decoder.model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 764 |
+
"decoder.model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 765 |
+
"decoder.model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 766 |
+
"decoder.model.decoder.layers.5.fc1.weight": "model-00002-of-00003.safetensors",
|
| 767 |
+
"decoder.model.decoder.layers.5.fc2.weight": "model-00002-of-00003.safetensors",
|
| 768 |
+
"decoder.model.decoder.layers.5.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 769 |
+
"decoder.model.decoder.layers.5.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 770 |
+
"decoder.model.decoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 771 |
+
"decoder.model.decoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 772 |
+
"decoder.model.decoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 773 |
+
"decoder.model.decoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 774 |
+
"decoder.model.decoder.layers.5.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 775 |
+
"decoder.model.decoder.layers.5.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 776 |
+
"decoder.model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 777 |
+
"decoder.model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 778 |
+
"decoder.model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 779 |
+
"decoder.model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 780 |
+
"decoder.model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 781 |
+
"decoder.model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 782 |
+
"decoder.model.decoder.layers.6.fc1.weight": "model-00002-of-00003.safetensors",
|
| 783 |
+
"decoder.model.decoder.layers.6.fc2.weight": "model-00002-of-00003.safetensors",
|
| 784 |
+
"decoder.model.decoder.layers.6.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 785 |
+
"decoder.model.decoder.layers.6.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 786 |
+
"decoder.model.decoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 787 |
+
"decoder.model.decoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 788 |
+
"decoder.model.decoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 789 |
+
"decoder.model.decoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 790 |
+
"decoder.model.decoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 791 |
+
"decoder.model.decoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 792 |
+
"decoder.model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 793 |
+
"decoder.model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 794 |
+
"decoder.model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 795 |
+
"decoder.model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 796 |
+
"decoder.model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 797 |
+
"decoder.model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 798 |
+
"decoder.model.decoder.layers.7.fc1.weight": "model-00002-of-00003.safetensors",
|
| 799 |
+
"decoder.model.decoder.layers.7.fc2.weight": "model-00002-of-00003.safetensors",
|
| 800 |
+
"decoder.model.decoder.layers.7.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 801 |
+
"decoder.model.decoder.layers.7.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 802 |
+
"decoder.model.decoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 803 |
+
"decoder.model.decoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 804 |
+
"decoder.model.decoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 805 |
+
"decoder.model.decoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 806 |
+
"decoder.model.decoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 807 |
+
"decoder.model.decoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 808 |
+
"decoder.model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 809 |
+
"decoder.model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 810 |
+
"decoder.model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 811 |
+
"decoder.model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 812 |
+
"decoder.model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 813 |
+
"decoder.model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 814 |
+
"decoder.model.decoder.layers.8.fc1.weight": "model-00002-of-00003.safetensors",
|
| 815 |
+
"decoder.model.decoder.layers.8.fc2.weight": "model-00002-of-00003.safetensors",
|
| 816 |
+
"decoder.model.decoder.layers.8.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 817 |
+
"decoder.model.decoder.layers.8.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 818 |
+
"decoder.model.decoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 819 |
+
"decoder.model.decoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 820 |
+
"decoder.model.decoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 821 |
+
"decoder.model.decoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 822 |
+
"decoder.model.decoder.layers.8.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 823 |
+
"decoder.model.decoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 824 |
+
"decoder.model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 825 |
+
"decoder.model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 826 |
+
"decoder.model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 827 |
+
"decoder.model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 828 |
+
"decoder.model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 829 |
+
"decoder.model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 830 |
+
"decoder.model.decoder.layers.9.fc1.weight": "model-00002-of-00003.safetensors",
|
| 831 |
+
"decoder.model.decoder.layers.9.fc2.weight": "model-00002-of-00003.safetensors",
|
| 832 |
+
"decoder.model.decoder.layers.9.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 833 |
+
"decoder.model.decoder.layers.9.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 834 |
+
"decoder.model.decoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 835 |
+
"decoder.model.decoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 836 |
+
"decoder.model.decoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 837 |
+
"decoder.model.decoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 838 |
+
"decoder.model.decoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
| 839 |
+
"decoder.model.decoder.layers.9.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
| 840 |
+
"embed_positions.weights": "model-00003-of-00003.safetensors",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 841 |
"embed_prompts.weight": "model-00003-of-00003.safetensors",
|
| 842 |
+
"enc_to_dec_proj.bias": "model-00002-of-00003.safetensors",
|
| 843 |
+
"enc_to_dec_proj.weight": "model-00002-of-00003.safetensors",
|
| 844 |
"text_encoder.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
|
| 845 |
"text_encoder.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
|
| 846 |
"text_encoder.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
|