Hugging Face's logo

pirxus
/
wavlm-large_olmo1b_lora_r16a16_np_ua_swft

Transformers
Safetensors
Model card Files Community
pirxus commited on
Commit
4971e2f
·
verified ·
1 Parent(s): 4c110c8

Upload Loadable

Browse files
Files changed (6) hide show
  1. README.md +199 -0
  2. config.json +317 -0
  3. generation_config.json +8 -0
  4. model-00001-of-00002.safetensors +3 -0
  5. model-00002-of-00002.safetensors +3 -0
  6. model.safetensors.index.json +870 -0
README.md ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags: []
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+ This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
config.json ADDED
@@ -0,0 +1,317 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/matylda6/isedlacek/projects/huggingface_asr/exp/spokenwoz_multiwoz_lora_r16a16_bs96_np_ua_ftsw1ep/checkpoint-385",
3
+ "architectures": [
4
+ "Loadable"
5
+ ],
6
+ "ce_loss_weight": 1.0,
7
+ "connector_type": "encoder_stacked",
8
+ "downsampling_factor": 6,
9
+ "encoder_config": {
10
+ "_attn_implementation_autoset": true,
11
+ "_name_or_path": "microsoft/wavlm-large",
12
+ "activation_dropout": 0.0,
13
+ "adapter_kernel_size": 3,
14
+ "adapter_stride": 2,
15
+ "add_adapter": false,
16
+ "add_cross_attention": false,
17
+ "apply_spec_augment": false,
18
+ "architectures": [
19
+ "WavLMModel"
20
+ ],
21
+ "attention_dropout": 0.1,
22
+ "bad_words_ids": null,
23
+ "begin_suppress_tokens": null,
24
+ "bos_token_id": 1,
25
+ "chunk_size_feed_forward": 0,
26
+ "classifier_proj_size": 256,
27
+ "codevector_dim": 768,
28
+ "contrastive_logits_temperature": 0.1,
29
+ "conv_bias": false,
30
+ "conv_dim": [
31
+ 512,
32
+ 512,
33
+ 512,
34
+ 512,
35
+ 512,
36
+ 512,
37
+ 512
38
+ ],
39
+ "conv_kernel": [
40
+ 10,
41
+ 3,
42
+ 3,
43
+ 3,
44
+ 3,
45
+ 2,
46
+ 2
47
+ ],
48
+ "conv_stride": [
49
+ 5,
50
+ 2,
51
+ 2,
52
+ 2,
53
+ 2,
54
+ 2,
55
+ 2
56
+ ],
57
+ "cross_attention_hidden_size": null,
58
+ "ctc_loss_reduction": "sum",
59
+ "ctc_zero_infinity": false,
60
+ "decoder_start_token_id": null,
61
+ "diversity_loss_weight": 0.1,
62
+ "diversity_penalty": 0.0,
63
+ "do_sample": false,
64
+ "do_stable_layer_norm": true,
65
+ "early_stopping": false,
66
+ "encoder_no_repeat_ngram_size": 0,
67
+ "eos_token_id": 2,
68
+ "exponential_decay_length_penalty": null,
69
+ "feat_extract_activation": "gelu",
70
+ "feat_extract_dropout": 0.0,
71
+ "feat_extract_norm": "layer",
72
+ "feat_proj_dropout": 0.1,
73
+ "feat_quantizer_dropout": 0.0,
74
+ "final_dropout": 0.0,
75
+ "finetuning_task": null,
76
+ "forced_bos_token_id": null,
77
+ "forced_eos_token_id": null,
78
+ "gradient_checkpointing": false,
79
+ "hidden_act": "gelu",
80
+ "hidden_dropout": 0.1,
81
+ "hidden_size": 1024,
82
+ "id2label": {
83
+ "0": "LABEL_0",
84
+ "1": "LABEL_1"
85
+ },
86
+ "initializer_range": 0.02,
87
+ "intermediate_size": 4096,
88
+ "is_decoder": false,
89
+ "is_encoder_decoder": false,
90
+ "label2id": {
91
+ "LABEL_0": 0,
92
+ "LABEL_1": 1
93
+ },
94
+ "layer_norm_eps": 1e-05,
95
+ "layer_to_extract": null,
96
+ "layerdrop": 0.1,
97
+ "length_penalty": 1.0,
98
+ "mask_channel_length": 10,
99
+ "mask_channel_min_space": 1,
100
+ "mask_channel_other": 0.0,
101
+ "mask_channel_prob": 0.0,
102
+ "mask_channel_selection": "static",
103
+ "mask_feature_length": 10,
104
+ "mask_feature_min_masks": 0,
105
+ "mask_feature_prob": 0.0,
106
+ "mask_time_length": 10,
107
+ "mask_time_min_masks": 2,
108
+ "mask_time_min_space": 1,
109
+ "mask_time_other": 0.0,
110
+ "mask_time_prob": 0.075,
111
+ "mask_time_selection": "static",
112
+ "max_bucket_distance": 800,
113
+ "max_length": 20,
114
+ "min_length": 0,
115
+ "model_type": "",
116
+ "no_repeat_ngram_size": 0,
117
+ "num_adapter_layers": 3,
118
+ "num_attention_heads": 16,
119
+ "num_beam_groups": 1,
120
+ "num_beams": 1,
121
+ "num_buckets": 320,
122
+ "num_codevector_groups": 2,
123
+ "num_codevectors_per_group": 320,
124
+ "num_conv_pos_embedding_groups": 16,
125
+ "num_conv_pos_embeddings": 128,
126
+ "num_ctc_classes": 80,
127
+ "num_feat_extract_layers": 7,
128
+ "num_hidden_layers": 24,
129
+ "num_negatives": 100,
130
+ "num_return_sequences": 1,
131
+ "output_attentions": false,
132
+ "output_hidden_size": 1024,
133
+ "output_hidden_states": false,
134
+ "output_scores": false,
135
+ "pad_token_id": 0,
136
+ "prefix": null,
137
+ "problem_type": null,
138
+ "proj_codevector_dim": 768,
139
+ "pruned_heads": {},
140
+ "remove_invalid_values": false,
141
+ "repetition_penalty": 1.0,
142
+ "replace_prob": 0.5,
143
+ "return_dict": true,
144
+ "return_dict_in_generate": false,
145
+ "sep_token_id": null,
146
+ "suppress_tokens": null,
147
+ "task_specific_params": null,
148
+ "tdnn_dilation": [
149
+ 1,
150
+ 2,
151
+ 3,
152
+ 1,
153
+ 1
154
+ ],
155
+ "tdnn_dim": [
156
+ 512,
157
+ 512,
158
+ 512,
159
+ 512,
160
+ 1500
161
+ ],
162
+ "tdnn_kernel": [
163
+ 5,
164
+ 3,
165
+ 3,
166
+ 1,
167
+ 1
168
+ ],
169
+ "temperature": 1.0,
170
+ "tf_legacy_loss": false,
171
+ "tie_encoder_decoder": false,
172
+ "tie_word_embeddings": true,
173
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
174
+ "top_k": 50,
175
+ "top_p": 1.0,
176
+ "torch_dtype": "float32",
177
+ "torchscript": false,
178
+ "typical_p": 1.0,
179
+ "use_bfloat16": false,
180
+ "use_weighted_layer_sum": false,
181
+ "vocab_size": 32,
182
+ "xvector_output_dim": 512
183
+ },
184
+ "freeze_encoder": false,
185
+ "init_prompt_from_embeds": false,
186
+ "lm_config": {
187
+ "_attn_implementation_autoset": true,
188
+ "_name_or_path": "allenai/OLMo-1B-hf",
189
+ "add_cross_attention": false,
190
+ "architectures": [
191
+ "OlmoForCausalLM"
192
+ ],
193
+ "attention_bias": false,
194
+ "attention_dropout": 0.0,
195
+ "bad_words_ids": null,
196
+ "begin_suppress_tokens": null,
197
+ "bos_token_id": null,
198
+ "chunk_size_feed_forward": 0,
199
+ "clip_qkv": null,
200
+ "cross_attention_hidden_size": null,
201
+ "decoder_start_token_id": null,
202
+ "diversity_penalty": 0.0,
203
+ "do_sample": false,
204
+ "early_stopping": false,
205
+ "encoder_no_repeat_ngram_size": 0,
206
+ "eos_token_id": 50279,
207
+ "exponential_decay_length_penalty": null,
208
+ "finetuning_task": null,
209
+ "forced_bos_token_id": null,
210
+ "forced_eos_token_id": null,
211
+ "hidden_act": "silu",
212
+ "hidden_size": 2048,
213
+ "id2label": {
214
+ "0": "LABEL_0",
215
+ "1": "LABEL_1"
216
+ },
217
+ "initializer_range": 0.02,
218
+ "intermediate_size": 8192,
219
+ "is_decoder": false,
220
+ "is_encoder_decoder": false,
221
+ "label2id": {
222
+ "LABEL_0": 0,
223
+ "LABEL_1": 1
224
+ },
225
+ "length_penalty": 1.0,
226
+ "max_length": 20,
227
+ "max_position_embeddings": 2048,
228
+ "min_length": 0,
229
+ "model_type": "",
230
+ "no_repeat_ngram_size": 0,
231
+ "num_attention_heads": 16,
232
+ "num_beam_groups": 1,
233
+ "num_beams": 1,
234
+ "num_hidden_layers": 16,
235
+ "num_key_value_heads": 16,
236
+ "num_return_sequences": 1,
237
+ "output_attentions": false,
238
+ "output_hidden_states": false,
239
+ "output_scores": false,
240
+ "pad_token_id": 50279,
241
+ "prefix": null,
242
+ "pretraining_tp": 1,
243
+ "problem_type": null,
244
+ "pruned_heads": {},
245
+ "remove_invalid_values": false,
246
+ "repetition_penalty": 1.0,
247
+ "return_dict": true,
248
+ "return_dict_in_generate": false,
249
+ "rope_scaling": null,
250
+ "rope_theta": 10000.0,
251
+ "sep_token_id": null,
252
+ "suppress_tokens": null,
253
+ "task_specific_params": null,
254
+ "temperature": 1.0,
255
+ "tf_legacy_loss": false,
256
+ "tie_encoder_decoder": false,
257
+ "tie_word_embeddings": true,
258
+ "tokenizer_class": null,
259
+ "top_k": 50,
260
+ "top_p": 1.0,
261
+ "torch_dtype": "bfloat16",
262
+ "torchscript": false,
263
+ "typical_p": 1.0,
264
+ "use_bfloat16": false,
265
+ "use_cache": true,
266
+ "vocab_size": 50304
267
+ },
268
+ "lora_config": {
269
+ "alpha_pattern": {},
270
+ "auto_mapping": null,
271
+ "base_model_name_or_path": null,
272
+ "bias": "none",
273
+ "fan_in_fan_out": false,
274
+ "inference_mode": false,
275
+ "init_lora_weights": true,
276
+ "layer_replication": null,
277
+ "layers_pattern": null,
278
+ "layers_to_transform": null,
279
+ "loftq_config": {},
280
+ "lora_alpha": 16,
281
+ "lora_dropout": 0.1,
282
+ "megatron_config": null,
283
+ "megatron_core": "megatron.core",
284
+ "modules_to_save": null,
285
+ "peft_type": "LORA",
286
+ "r": 16,
287
+ "rank_pattern": {},
288
+ "revision": null,
289
+ "target_modules": "all-linear",
290
+ "task_type": "CAUSAL_LM",
291
+ "use_dora": false,
292
+ "use_rslora": false
293
+ },
294
+ "mm_loss_weight": 0.0,
295
+ "mm_micro_loss": "dot",
296
+ "mm_pooling": null,
297
+ "modality_matching": true,
298
+ "num_pretrain_epochs": 0,
299
+ "num_query_tokens": 80,
300
+ "pad_token_id": 50279,
301
+ "prompt_tuning_prefix_init": null,
302
+ "prompt_tuning_prefix_len": 0,
303
+ "prompt_tuning_suffix_init": null,
304
+ "prompt_tuning_suffix_len": 0,
305
+ "qformer_config": {
306
+ "cross_attention_frequency": 1,
307
+ "encoder_hidden_size": 1024,
308
+ "hidden_act": "gelu_new",
309
+ "hidden_size": 1024,
310
+ "intermediate_size": 4096,
311
+ "model_type": "blip_2_qformer",
312
+ "num_attention_heads": 16,
313
+ "num_hidden_layers": 2
314
+ },
315
+ "torch_dtype": "float32",
316
+ "transformers_version": "4.48.2"
317
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_end_token_id": 50279,
3
+ "eos_token_id": 50279,
4
+ "max_new_tokens": 400,
5
+ "num_beams": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.48.2"
8
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcd7c8ba69b8971fe54748795601b5d030a384af95d1e7e3744738b48b70e3cb
3
+ size 4999563240
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13a6b2cdc5cdb3baa8f5bc77332de1953da3f37f371920e195e819fc6bbf6a95
3
+ size 1394170976
model.safetensors.index.json ADDED
@@ -0,0 +1,870 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6393617152
4
+ },
5
+ "weight_map": {
6
+ "connector.connector.embed_positions.weight": "model-00002-of-00002.safetensors",
7
+ "connector.connector.embed_tokens.weight": "model-00002-of-00002.safetensors",
8
+ "connector.connector.layers.0.fc1.bias": "model-00002-of-00002.safetensors",
9
+ "connector.connector.layers.0.fc1.weight": "model-00002-of-00002.safetensors",
10
+ "connector.connector.layers.0.fc2.bias": "model-00002-of-00002.safetensors",
11
+ "connector.connector.layers.0.fc2.weight": "model-00002-of-00002.safetensors",
12
+ "connector.connector.layers.0.final_layer_norm.bias": "model-00002-of-00002.safetensors",
13
+ "connector.connector.layers.0.final_layer_norm.weight": "model-00002-of-00002.safetensors",
14
+ "connector.connector.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
15
+ "connector.connector.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
16
+ "connector.connector.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
17
+ "connector.connector.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
18
+ "connector.connector.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
19
+ "connector.connector.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
20
+ "connector.connector.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
21
+ "connector.connector.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
22
+ "connector.connector.layers.0.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
23
+ "connector.connector.layers.0.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
24
+ "connector.connector.layers.1.fc1.bias": "model-00002-of-00002.safetensors",
25
+ "connector.connector.layers.1.fc1.weight": "model-00002-of-00002.safetensors",
26
+ "connector.connector.layers.1.fc2.bias": "model-00002-of-00002.safetensors",
27
+ "connector.connector.layers.1.fc2.weight": "model-00002-of-00002.safetensors",
28
+ "connector.connector.layers.1.final_layer_norm.bias": "model-00002-of-00002.safetensors",
29
+ "connector.connector.layers.1.final_layer_norm.weight": "model-00002-of-00002.safetensors",
30
+ "connector.connector.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
31
+ "connector.connector.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
32
+ "connector.connector.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
33
+ "connector.connector.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
34
+ "connector.connector.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
35
+ "connector.connector.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
36
+ "connector.connector.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
37
+ "connector.connector.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
38
+ "connector.connector.layers.1.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
39
+ "connector.connector.layers.1.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
40
+ "connector.fc.bias": "model-00002-of-00002.safetensors",
41
+ "connector.fc.weight": "model-00002-of-00002.safetensors",
42
+ "connector.language_projection.bias": "model-00002-of-00002.safetensors",
43
+ "connector.language_projection.weight": "model-00002-of-00002.safetensors",
44
+ "decoder.base_model.model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
45
+ "decoder.base_model.model.model.layers.0.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
46
+ "decoder.base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
47
+ "decoder.base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
48
+ "decoder.base_model.model.model.layers.0.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
49
+ "decoder.base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
50
+ "decoder.base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
51
+ "decoder.base_model.model.model.layers.0.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
52
+ "decoder.base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
53
+ "decoder.base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
54
+ "decoder.base_model.model.model.layers.0.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
55
+ "decoder.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
56
+ "decoder.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
57
+ "decoder.base_model.model.model.layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
58
+ "decoder.base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
59
+ "decoder.base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
60
+ "decoder.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
61
+ "decoder.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
62
+ "decoder.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
63
+ "decoder.base_model.model.model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
64
+ "decoder.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
65
+ "decoder.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
66
+ "decoder.base_model.model.model.layers.1.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
67
+ "decoder.base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
68
+ "decoder.base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
69
+ "decoder.base_model.model.model.layers.1.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
70
+ "decoder.base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
71
+ "decoder.base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
72
+ "decoder.base_model.model.model.layers.1.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
73
+ "decoder.base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
74
+ "decoder.base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
75
+ "decoder.base_model.model.model.layers.1.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
76
+ "decoder.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
77
+ "decoder.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
78
+ "decoder.base_model.model.model.layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
79
+ "decoder.base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
80
+ "decoder.base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
81
+ "decoder.base_model.model.model.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
82
+ "decoder.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
83
+ "decoder.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
84
+ "decoder.base_model.model.model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
85
+ "decoder.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
86
+ "decoder.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
87
+ "decoder.base_model.model.model.layers.10.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
88
+ "decoder.base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
89
+ "decoder.base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
90
+ "decoder.base_model.model.model.layers.10.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
91
+ "decoder.base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
92
+ "decoder.base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
93
+ "decoder.base_model.model.model.layers.10.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
94
+ "decoder.base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
95
+ "decoder.base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
96
+ "decoder.base_model.model.model.layers.10.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
97
+ "decoder.base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
98
+ "decoder.base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
99
+ "decoder.base_model.model.model.layers.10.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
100
+ "decoder.base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
101
+ "decoder.base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
102
+ "decoder.base_model.model.model.layers.10.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
103
+ "decoder.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
104
+ "decoder.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
105
+ "decoder.base_model.model.model.layers.10.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
106
+ "decoder.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
107
+ "decoder.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
108
+ "decoder.base_model.model.model.layers.11.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
109
+ "decoder.base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
110
+ "decoder.base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
111
+ "decoder.base_model.model.model.layers.11.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
112
+ "decoder.base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
113
+ "decoder.base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
114
+ "decoder.base_model.model.model.layers.11.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
115
+ "decoder.base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
116
+ "decoder.base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
117
+ "decoder.base_model.model.model.layers.11.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
118
+ "decoder.base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
119
+ "decoder.base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
120
+ "decoder.base_model.model.model.layers.11.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
121
+ "decoder.base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
122
+ "decoder.base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
123
+ "decoder.base_model.model.model.layers.11.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
124
+ "decoder.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
125
+ "decoder.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
126
+ "decoder.base_model.model.model.layers.11.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
127
+ "decoder.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
128
+ "decoder.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
129
+ "decoder.base_model.model.model.layers.12.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
130
+ "decoder.base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
131
+ "decoder.base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
132
+ "decoder.base_model.model.model.layers.12.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
133
+ "decoder.base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
134
+ "decoder.base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
135
+ "decoder.base_model.model.model.layers.12.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
136
+ "decoder.base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
137
+ "decoder.base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
138
+ "decoder.base_model.model.model.layers.12.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
139
+ "decoder.base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
140
+ "decoder.base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
141
+ "decoder.base_model.model.model.layers.12.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
142
+ "decoder.base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
143
+ "decoder.base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
144
+ "decoder.base_model.model.model.layers.12.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
145
+ "decoder.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
146
+ "decoder.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
147
+ "decoder.base_model.model.model.layers.12.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
148
+ "decoder.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
149
+ "decoder.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
150
+ "decoder.base_model.model.model.layers.13.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
151
+ "decoder.base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
152
+ "decoder.base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
153
+ "decoder.base_model.model.model.layers.13.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
154
+ "decoder.base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
155
+ "decoder.base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
156
+ "decoder.base_model.model.model.layers.13.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
157
+ "decoder.base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
158
+ "decoder.base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
159
+ "decoder.base_model.model.model.layers.13.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
160
+ "decoder.base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
161
+ "decoder.base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
162
+ "decoder.base_model.model.model.layers.13.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
163
+ "decoder.base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
164
+ "decoder.base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
165
+ "decoder.base_model.model.model.layers.13.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
166
+ "decoder.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
167
+ "decoder.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
168
+ "decoder.base_model.model.model.layers.13.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
169
+ "decoder.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
170
+ "decoder.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
171
+ "decoder.base_model.model.model.layers.14.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
172
+ "decoder.base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
173
+ "decoder.base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
174
+ "decoder.base_model.model.model.layers.14.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
175
+ "decoder.base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
176
+ "decoder.base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
177
+ "decoder.base_model.model.model.layers.14.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
178
+ "decoder.base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
179
+ "decoder.base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
180
+ "decoder.base_model.model.model.layers.14.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
181
+ "decoder.base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
182
+ "decoder.base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
183
+ "decoder.base_model.model.model.layers.14.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
184
+ "decoder.base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
185
+ "decoder.base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
186
+ "decoder.base_model.model.model.layers.14.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
187
+ "decoder.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
188
+ "decoder.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
189
+ "decoder.base_model.model.model.layers.14.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
190
+ "decoder.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
191
+ "decoder.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
192
+ "decoder.base_model.model.model.layers.15.mlp.down_proj.base_layer.weight": "model-00002-of-00002.safetensors",
193
+ "decoder.base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
194
+ "decoder.base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
195
+ "decoder.base_model.model.model.layers.15.mlp.gate_proj.base_layer.weight": "model-00002-of-00002.safetensors",
196
+ "decoder.base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
197
+ "decoder.base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
198
+ "decoder.base_model.model.model.layers.15.mlp.up_proj.base_layer.weight": "model-00002-of-00002.safetensors",
199
+ "decoder.base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
200
+ "decoder.base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
201
+ "decoder.base_model.model.model.layers.15.self_attn.k_proj.base_layer.weight": "model-00002-of-00002.safetensors",
202
+ "decoder.base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
203
+ "decoder.base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
204
+ "decoder.base_model.model.model.layers.15.self_attn.o_proj.base_layer.weight": "model-00002-of-00002.safetensors",
205
+ "decoder.base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
206
+ "decoder.base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
207
+ "decoder.base_model.model.model.layers.15.self_attn.q_proj.base_layer.weight": "model-00002-of-00002.safetensors",
208
+ "decoder.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
209
+ "decoder.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
210
+ "decoder.base_model.model.model.layers.15.self_attn.v_proj.base_layer.weight": "model-00002-of-00002.safetensors",
211
+ "decoder.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00002.safetensors",
212
+ "decoder.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00002.safetensors",
213
+ "decoder.base_model.model.model.layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
214
+ "decoder.base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
215
+ "decoder.base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
216
+ "decoder.base_model.model.model.layers.2.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
217
+ "decoder.base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
218
+ "decoder.base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
219
+ "decoder.base_model.model.model.layers.2.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
220
+ "decoder.base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
221
+ "decoder.base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
222
+ "decoder.base_model.model.model.layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
223
+ "decoder.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
224
+ "decoder.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
225
+ "decoder.base_model.model.model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
226
+ "decoder.base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
227
+ "decoder.base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
228
+ "decoder.base_model.model.model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
229
+ "decoder.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
230
+ "decoder.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
231
+ "decoder.base_model.model.model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
232
+ "decoder.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
233
+ "decoder.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
234
+ "decoder.base_model.model.model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
235
+ "decoder.base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
236
+ "decoder.base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
237
+ "decoder.base_model.model.model.layers.3.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
238
+ "decoder.base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
239
+ "decoder.base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
240
+ "decoder.base_model.model.model.layers.3.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
241
+ "decoder.base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
242
+ "decoder.base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
243
+ "decoder.base_model.model.model.layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
244
+ "decoder.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
245
+ "decoder.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
246
+ "decoder.base_model.model.model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
247
+ "decoder.base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
248
+ "decoder.base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
249
+ "decoder.base_model.model.model.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
250
+ "decoder.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
251
+ "decoder.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
252
+ "decoder.base_model.model.model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
253
+ "decoder.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
254
+ "decoder.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
255
+ "decoder.base_model.model.model.layers.4.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
256
+ "decoder.base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
257
+ "decoder.base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
258
+ "decoder.base_model.model.model.layers.4.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
259
+ "decoder.base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
260
+ "decoder.base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
261
+ "decoder.base_model.model.model.layers.4.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
262
+ "decoder.base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
263
+ "decoder.base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
264
+ "decoder.base_model.model.model.layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
265
+ "decoder.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
266
+ "decoder.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
267
+ "decoder.base_model.model.model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
268
+ "decoder.base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
269
+ "decoder.base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
270
+ "decoder.base_model.model.model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
271
+ "decoder.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
272
+ "decoder.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
273
+ "decoder.base_model.model.model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
274
+ "decoder.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
275
+ "decoder.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
276
+ "decoder.base_model.model.model.layers.5.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
277
+ "decoder.base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
278
+ "decoder.base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
279
+ "decoder.base_model.model.model.layers.5.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
280
+ "decoder.base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
281
+ "decoder.base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
282
+ "decoder.base_model.model.model.layers.5.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
283
+ "decoder.base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
284
+ "decoder.base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
285
+ "decoder.base_model.model.model.layers.5.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
286
+ "decoder.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
287
+ "decoder.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
288
+ "decoder.base_model.model.model.layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
289
+ "decoder.base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
290
+ "decoder.base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
291
+ "decoder.base_model.model.model.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
292
+ "decoder.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
293
+ "decoder.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
294
+ "decoder.base_model.model.model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
295
+ "decoder.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
296
+ "decoder.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
297
+ "decoder.base_model.model.model.layers.6.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
298
+ "decoder.base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
299
+ "decoder.base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
300
+ "decoder.base_model.model.model.layers.6.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
301
+ "decoder.base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
302
+ "decoder.base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
303
+ "decoder.base_model.model.model.layers.6.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
304
+ "decoder.base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
305
+ "decoder.base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
306
+ "decoder.base_model.model.model.layers.6.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
307
+ "decoder.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
308
+ "decoder.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
309
+ "decoder.base_model.model.model.layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
310
+ "decoder.base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
311
+ "decoder.base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
312
+ "decoder.base_model.model.model.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
313
+ "decoder.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
314
+ "decoder.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
315
+ "decoder.base_model.model.model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
316
+ "decoder.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
317
+ "decoder.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
318
+ "decoder.base_model.model.model.layers.7.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
319
+ "decoder.base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
320
+ "decoder.base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
321
+ "decoder.base_model.model.model.layers.7.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
322
+ "decoder.base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
323
+ "decoder.base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
324
+ "decoder.base_model.model.model.layers.7.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
325
+ "decoder.base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
326
+ "decoder.base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
327
+ "decoder.base_model.model.model.layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
328
+ "decoder.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
329
+ "decoder.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
330
+ "decoder.base_model.model.model.layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
331
+ "decoder.base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
332
+ "decoder.base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
333
+ "decoder.base_model.model.model.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
334
+ "decoder.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
335
+ "decoder.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
336
+ "decoder.base_model.model.model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
337
+ "decoder.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
338
+ "decoder.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
339
+ "decoder.base_model.model.model.layers.8.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
340
+ "decoder.base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
341
+ "decoder.base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
342
+ "decoder.base_model.model.model.layers.8.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
343
+ "decoder.base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
344
+ "decoder.base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
345
+ "decoder.base_model.model.model.layers.8.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
346
+ "decoder.base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
347
+ "decoder.base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
348
+ "decoder.base_model.model.model.layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
349
+ "decoder.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
350
+ "decoder.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
351
+ "decoder.base_model.model.model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
352
+ "decoder.base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
353
+ "decoder.base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
354
+ "decoder.base_model.model.model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
355
+ "decoder.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
356
+ "decoder.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
357
+ "decoder.base_model.model.model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
358
+ "decoder.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
359
+ "decoder.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
360
+ "decoder.base_model.model.model.layers.9.mlp.down_proj.base_layer.weight": "model-00001-of-00002.safetensors",
361
+ "decoder.base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
362
+ "decoder.base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
363
+ "decoder.base_model.model.model.layers.9.mlp.gate_proj.base_layer.weight": "model-00001-of-00002.safetensors",
364
+ "decoder.base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
365
+ "decoder.base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
366
+ "decoder.base_model.model.model.layers.9.mlp.up_proj.base_layer.weight": "model-00001-of-00002.safetensors",
367
+ "decoder.base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
368
+ "decoder.base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
369
+ "decoder.base_model.model.model.layers.9.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
370
+ "decoder.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
371
+ "decoder.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
372
+ "decoder.base_model.model.model.layers.9.self_attn.o_proj.base_layer.weight": "model-00001-of-00002.safetensors",
373
+ "decoder.base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
374
+ "decoder.base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
375
+ "decoder.base_model.model.model.layers.9.self_attn.q_proj.base_layer.weight": "model-00001-of-00002.safetensors",
376
+ "decoder.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
377
+ "decoder.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
378
+ "decoder.base_model.model.model.layers.9.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
379
+ "decoder.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
380
+ "decoder.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
381
+ "encoder.encoder.layer_norm.bias": "model-00001-of-00002.safetensors",
382
+ "encoder.encoder.layer_norm.weight": "model-00001-of-00002.safetensors",
383
+ "encoder.encoder.layers.0.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
384
+ "encoder.encoder.layers.0.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
385
+ "encoder.encoder.layers.0.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
386
+ "encoder.encoder.layers.0.attention.k_proj.bias": "model-00001-of-00002.safetensors",
387
+ "encoder.encoder.layers.0.attention.k_proj.weight": "model-00001-of-00002.safetensors",
388
+ "encoder.encoder.layers.0.attention.out_proj.bias": "model-00001-of-00002.safetensors",
389
+ "encoder.encoder.layers.0.attention.out_proj.weight": "model-00001-of-00002.safetensors",
390
+ "encoder.encoder.layers.0.attention.q_proj.bias": "model-00001-of-00002.safetensors",
391
+ "encoder.encoder.layers.0.attention.q_proj.weight": "model-00001-of-00002.safetensors",
392
+ "encoder.encoder.layers.0.attention.rel_attn_embed.weight": "model-00001-of-00002.safetensors",
393
+ "encoder.encoder.layers.0.attention.v_proj.bias": "model-00001-of-00002.safetensors",
394
+ "encoder.encoder.layers.0.attention.v_proj.weight": "model-00001-of-00002.safetensors",
395
+ "encoder.encoder.layers.0.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
396
+ "encoder.encoder.layers.0.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
397
+ "encoder.encoder.layers.0.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
398
+ "encoder.encoder.layers.0.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
399
+ "encoder.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
400
+ "encoder.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
401
+ "encoder.encoder.layers.0.layer_norm.bias": "model-00001-of-00002.safetensors",
402
+ "encoder.encoder.layers.0.layer_norm.weight": "model-00001-of-00002.safetensors",
403
+ "encoder.encoder.layers.1.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
404
+ "encoder.encoder.layers.1.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
405
+ "encoder.encoder.layers.1.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
406
+ "encoder.encoder.layers.1.attention.k_proj.bias": "model-00001-of-00002.safetensors",
407
+ "encoder.encoder.layers.1.attention.k_proj.weight": "model-00001-of-00002.safetensors",
408
+ "encoder.encoder.layers.1.attention.out_proj.bias": "model-00001-of-00002.safetensors",
409
+ "encoder.encoder.layers.1.attention.out_proj.weight": "model-00001-of-00002.safetensors",
410
+ "encoder.encoder.layers.1.attention.q_proj.bias": "model-00001-of-00002.safetensors",
411
+ "encoder.encoder.layers.1.attention.q_proj.weight": "model-00001-of-00002.safetensors",
412
+ "encoder.encoder.layers.1.attention.v_proj.bias": "model-00001-of-00002.safetensors",
413
+ "encoder.encoder.layers.1.attention.v_proj.weight": "model-00001-of-00002.safetensors",
414
+ "encoder.encoder.layers.1.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
415
+ "encoder.encoder.layers.1.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
416
+ "encoder.encoder.layers.1.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
417
+ "encoder.encoder.layers.1.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
418
+ "encoder.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
419
+ "encoder.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
420
+ "encoder.encoder.layers.1.layer_norm.bias": "model-00001-of-00002.safetensors",
421
+ "encoder.encoder.layers.1.layer_norm.weight": "model-00001-of-00002.safetensors",
422
+ "encoder.encoder.layers.10.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
423
+ "encoder.encoder.layers.10.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
424
+ "encoder.encoder.layers.10.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
425
+ "encoder.encoder.layers.10.attention.k_proj.bias": "model-00001-of-00002.safetensors",
426
+ "encoder.encoder.layers.10.attention.k_proj.weight": "model-00001-of-00002.safetensors",
427
+ "encoder.encoder.layers.10.attention.out_proj.bias": "model-00001-of-00002.safetensors",
428
+ "encoder.encoder.layers.10.attention.out_proj.weight": "model-00001-of-00002.safetensors",
429
+ "encoder.encoder.layers.10.attention.q_proj.bias": "model-00001-of-00002.safetensors",
430
+ "encoder.encoder.layers.10.attention.q_proj.weight": "model-00001-of-00002.safetensors",
431
+ "encoder.encoder.layers.10.attention.v_proj.bias": "model-00001-of-00002.safetensors",
432
+ "encoder.encoder.layers.10.attention.v_proj.weight": "model-00001-of-00002.safetensors",
433
+ "encoder.encoder.layers.10.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
434
+ "encoder.encoder.layers.10.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
435
+ "encoder.encoder.layers.10.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
436
+ "encoder.encoder.layers.10.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
437
+ "encoder.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
438
+ "encoder.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
439
+ "encoder.encoder.layers.10.layer_norm.bias": "model-00001-of-00002.safetensors",
440
+ "encoder.encoder.layers.10.layer_norm.weight": "model-00001-of-00002.safetensors",
441
+ "encoder.encoder.layers.11.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
442
+ "encoder.encoder.layers.11.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
443
+ "encoder.encoder.layers.11.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
444
+ "encoder.encoder.layers.11.attention.k_proj.bias": "model-00001-of-00002.safetensors",
445
+ "encoder.encoder.layers.11.attention.k_proj.weight": "model-00001-of-00002.safetensors",
446
+ "encoder.encoder.layers.11.attention.out_proj.bias": "model-00001-of-00002.safetensors",
447
+ "encoder.encoder.layers.11.attention.out_proj.weight": "model-00001-of-00002.safetensors",
448
+ "encoder.encoder.layers.11.attention.q_proj.bias": "model-00001-of-00002.safetensors",
449
+ "encoder.encoder.layers.11.attention.q_proj.weight": "model-00001-of-00002.safetensors",
450
+ "encoder.encoder.layers.11.attention.v_proj.bias": "model-00001-of-00002.safetensors",
451
+ "encoder.encoder.layers.11.attention.v_proj.weight": "model-00001-of-00002.safetensors",
452
+ "encoder.encoder.layers.11.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
453
+ "encoder.encoder.layers.11.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
454
+ "encoder.encoder.layers.11.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
455
+ "encoder.encoder.layers.11.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
456
+ "encoder.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
457
+ "encoder.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
458
+ "encoder.encoder.layers.11.layer_norm.bias": "model-00001-of-00002.safetensors",
459
+ "encoder.encoder.layers.11.layer_norm.weight": "model-00001-of-00002.safetensors",
460
+ "encoder.encoder.layers.12.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
461
+ "encoder.encoder.layers.12.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
462
+ "encoder.encoder.layers.12.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
463
+ "encoder.encoder.layers.12.attention.k_proj.bias": "model-00001-of-00002.safetensors",
464
+ "encoder.encoder.layers.12.attention.k_proj.weight": "model-00001-of-00002.safetensors",
465
+ "encoder.encoder.layers.12.attention.out_proj.bias": "model-00001-of-00002.safetensors",
466
+ "encoder.encoder.layers.12.attention.out_proj.weight": "model-00001-of-00002.safetensors",
467
+ "encoder.encoder.layers.12.attention.q_proj.bias": "model-00001-of-00002.safetensors",
468
+ "encoder.encoder.layers.12.attention.q_proj.weight": "model-00001-of-00002.safetensors",
469
+ "encoder.encoder.layers.12.attention.v_proj.bias": "model-00001-of-00002.safetensors",
470
+ "encoder.encoder.layers.12.attention.v_proj.weight": "model-00001-of-00002.safetensors",
471
+ "encoder.encoder.layers.12.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
472
+ "encoder.encoder.layers.12.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
473
+ "encoder.encoder.layers.12.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
474
+ "encoder.encoder.layers.12.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
475
+ "encoder.encoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
476
+ "encoder.encoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
477
+ "encoder.encoder.layers.12.layer_norm.bias": "model-00001-of-00002.safetensors",
478
+ "encoder.encoder.layers.12.layer_norm.weight": "model-00001-of-00002.safetensors",
479
+ "encoder.encoder.layers.13.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
480
+ "encoder.encoder.layers.13.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
481
+ "encoder.encoder.layers.13.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
482
+ "encoder.encoder.layers.13.attention.k_proj.bias": "model-00001-of-00002.safetensors",
483
+ "encoder.encoder.layers.13.attention.k_proj.weight": "model-00001-of-00002.safetensors",
484
+ "encoder.encoder.layers.13.attention.out_proj.bias": "model-00001-of-00002.safetensors",
485
+ "encoder.encoder.layers.13.attention.out_proj.weight": "model-00001-of-00002.safetensors",
486
+ "encoder.encoder.layers.13.attention.q_proj.bias": "model-00001-of-00002.safetensors",
487
+ "encoder.encoder.layers.13.attention.q_proj.weight": "model-00001-of-00002.safetensors",
488
+ "encoder.encoder.layers.13.attention.v_proj.bias": "model-00001-of-00002.safetensors",
489
+ "encoder.encoder.layers.13.attention.v_proj.weight": "model-00001-of-00002.safetensors",
490
+ "encoder.encoder.layers.13.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
491
+ "encoder.encoder.layers.13.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
492
+ "encoder.encoder.layers.13.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
493
+ "encoder.encoder.layers.13.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
494
+ "encoder.encoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
495
+ "encoder.encoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
496
+ "encoder.encoder.layers.13.layer_norm.bias": "model-00001-of-00002.safetensors",
497
+ "encoder.encoder.layers.13.layer_norm.weight": "model-00001-of-00002.safetensors",
498
+ "encoder.encoder.layers.14.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
499
+ "encoder.encoder.layers.14.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
500
+ "encoder.encoder.layers.14.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
501
+ "encoder.encoder.layers.14.attention.k_proj.bias": "model-00001-of-00002.safetensors",
502
+ "encoder.encoder.layers.14.attention.k_proj.weight": "model-00001-of-00002.safetensors",
503
+ "encoder.encoder.layers.14.attention.out_proj.bias": "model-00001-of-00002.safetensors",
504
+ "encoder.encoder.layers.14.attention.out_proj.weight": "model-00001-of-00002.safetensors",
505
+ "encoder.encoder.layers.14.attention.q_proj.bias": "model-00001-of-00002.safetensors",
506
+ "encoder.encoder.layers.14.attention.q_proj.weight": "model-00001-of-00002.safetensors",
507
+ "encoder.encoder.layers.14.attention.v_proj.bias": "model-00001-of-00002.safetensors",
508
+ "encoder.encoder.layers.14.attention.v_proj.weight": "model-00001-of-00002.safetensors",
509
+ "encoder.encoder.layers.14.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
510
+ "encoder.encoder.layers.14.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
511
+ "encoder.encoder.layers.14.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
512
+ "encoder.encoder.layers.14.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
513
+ "encoder.encoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
514
+ "encoder.encoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
515
+ "encoder.encoder.layers.14.layer_norm.bias": "model-00001-of-00002.safetensors",
516
+ "encoder.encoder.layers.14.layer_norm.weight": "model-00001-of-00002.safetensors",
517
+ "encoder.encoder.layers.15.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
518
+ "encoder.encoder.layers.15.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
519
+ "encoder.encoder.layers.15.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
520
+ "encoder.encoder.layers.15.attention.k_proj.bias": "model-00001-of-00002.safetensors",
521
+ "encoder.encoder.layers.15.attention.k_proj.weight": "model-00001-of-00002.safetensors",
522
+ "encoder.encoder.layers.15.attention.out_proj.bias": "model-00001-of-00002.safetensors",
523
+ "encoder.encoder.layers.15.attention.out_proj.weight": "model-00001-of-00002.safetensors",
524
+ "encoder.encoder.layers.15.attention.q_proj.bias": "model-00001-of-00002.safetensors",
525
+ "encoder.encoder.layers.15.attention.q_proj.weight": "model-00001-of-00002.safetensors",
526
+ "encoder.encoder.layers.15.attention.v_proj.bias": "model-00001-of-00002.safetensors",
527
+ "encoder.encoder.layers.15.attention.v_proj.weight": "model-00001-of-00002.safetensors",
528
+ "encoder.encoder.layers.15.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
529
+ "encoder.encoder.layers.15.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
530
+ "encoder.encoder.layers.15.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
531
+ "encoder.encoder.layers.15.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
532
+ "encoder.encoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
533
+ "encoder.encoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
534
+ "encoder.encoder.layers.15.layer_norm.bias": "model-00001-of-00002.safetensors",
535
+ "encoder.encoder.layers.15.layer_norm.weight": "model-00001-of-00002.safetensors",
536
+ "encoder.encoder.layers.16.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
537
+ "encoder.encoder.layers.16.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
538
+ "encoder.encoder.layers.16.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
539
+ "encoder.encoder.layers.16.attention.k_proj.bias": "model-00001-of-00002.safetensors",
540
+ "encoder.encoder.layers.16.attention.k_proj.weight": "model-00001-of-00002.safetensors",
541
+ "encoder.encoder.layers.16.attention.out_proj.bias": "model-00001-of-00002.safetensors",
542
+ "encoder.encoder.layers.16.attention.out_proj.weight": "model-00001-of-00002.safetensors",
543
+ "encoder.encoder.layers.16.attention.q_proj.bias": "model-00001-of-00002.safetensors",
544
+ "encoder.encoder.layers.16.attention.q_proj.weight": "model-00001-of-00002.safetensors",
545
+ "encoder.encoder.layers.16.attention.v_proj.bias": "model-00001-of-00002.safetensors",
546
+ "encoder.encoder.layers.16.attention.v_proj.weight": "model-00001-of-00002.safetensors",
547
+ "encoder.encoder.layers.16.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
548
+ "encoder.encoder.layers.16.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
549
+ "encoder.encoder.layers.16.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
550
+ "encoder.encoder.layers.16.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
551
+ "encoder.encoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
552
+ "encoder.encoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
553
+ "encoder.encoder.layers.16.layer_norm.bias": "model-00001-of-00002.safetensors",
554
+ "encoder.encoder.layers.16.layer_norm.weight": "model-00001-of-00002.safetensors",
555
+ "encoder.encoder.layers.17.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
556
+ "encoder.encoder.layers.17.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
557
+ "encoder.encoder.layers.17.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
558
+ "encoder.encoder.layers.17.attention.k_proj.bias": "model-00001-of-00002.safetensors",
559
+ "encoder.encoder.layers.17.attention.k_proj.weight": "model-00001-of-00002.safetensors",
560
+ "encoder.encoder.layers.17.attention.out_proj.bias": "model-00001-of-00002.safetensors",
561
+ "encoder.encoder.layers.17.attention.out_proj.weight": "model-00001-of-00002.safetensors",
562
+ "encoder.encoder.layers.17.attention.q_proj.bias": "model-00001-of-00002.safetensors",
563
+ "encoder.encoder.layers.17.attention.q_proj.weight": "model-00001-of-00002.safetensors",
564
+ "encoder.encoder.layers.17.attention.v_proj.bias": "model-00001-of-00002.safetensors",
565
+ "encoder.encoder.layers.17.attention.v_proj.weight": "model-00001-of-00002.safetensors",
566
+ "encoder.encoder.layers.17.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
567
+ "encoder.encoder.layers.17.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
568
+ "encoder.encoder.layers.17.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
569
+ "encoder.encoder.layers.17.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
570
+ "encoder.encoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
571
+ "encoder.encoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
572
+ "encoder.encoder.layers.17.layer_norm.bias": "model-00001-of-00002.safetensors",
573
+ "encoder.encoder.layers.17.layer_norm.weight": "model-00001-of-00002.safetensors",
574
+ "encoder.encoder.layers.18.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
575
+ "encoder.encoder.layers.18.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
576
+ "encoder.encoder.layers.18.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
577
+ "encoder.encoder.layers.18.attention.k_proj.bias": "model-00001-of-00002.safetensors",
578
+ "encoder.encoder.layers.18.attention.k_proj.weight": "model-00001-of-00002.safetensors",
579
+ "encoder.encoder.layers.18.attention.out_proj.bias": "model-00001-of-00002.safetensors",
580
+ "encoder.encoder.layers.18.attention.out_proj.weight": "model-00001-of-00002.safetensors",
581
+ "encoder.encoder.layers.18.attention.q_proj.bias": "model-00001-of-00002.safetensors",
582
+ "encoder.encoder.layers.18.attention.q_proj.weight": "model-00001-of-00002.safetensors",
583
+ "encoder.encoder.layers.18.attention.v_proj.bias": "model-00001-of-00002.safetensors",
584
+ "encoder.encoder.layers.18.attention.v_proj.weight": "model-00001-of-00002.safetensors",
585
+ "encoder.encoder.layers.18.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
586
+ "encoder.encoder.layers.18.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
587
+ "encoder.encoder.layers.18.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
588
+ "encoder.encoder.layers.18.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
589
+ "encoder.encoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
590
+ "encoder.encoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
591
+ "encoder.encoder.layers.18.layer_norm.bias": "model-00001-of-00002.safetensors",
592
+ "encoder.encoder.layers.18.layer_norm.weight": "model-00001-of-00002.safetensors",
593
+ "encoder.encoder.layers.19.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
594
+ "encoder.encoder.layers.19.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
595
+ "encoder.encoder.layers.19.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
596
+ "encoder.encoder.layers.19.attention.k_proj.bias": "model-00001-of-00002.safetensors",
597
+ "encoder.encoder.layers.19.attention.k_proj.weight": "model-00001-of-00002.safetensors",
598
+ "encoder.encoder.layers.19.attention.out_proj.bias": "model-00001-of-00002.safetensors",
599
+ "encoder.encoder.layers.19.attention.out_proj.weight": "model-00001-of-00002.safetensors",
600
+ "encoder.encoder.layers.19.attention.q_proj.bias": "model-00001-of-00002.safetensors",
601
+ "encoder.encoder.layers.19.attention.q_proj.weight": "model-00001-of-00002.safetensors",
602
+ "encoder.encoder.layers.19.attention.v_proj.bias": "model-00001-of-00002.safetensors",
603
+ "encoder.encoder.layers.19.attention.v_proj.weight": "model-00001-of-00002.safetensors",
604
+ "encoder.encoder.layers.19.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
605
+ "encoder.encoder.layers.19.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
606
+ "encoder.encoder.layers.19.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
607
+ "encoder.encoder.layers.19.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
608
+ "encoder.encoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
609
+ "encoder.encoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
610
+ "encoder.encoder.layers.19.layer_norm.bias": "model-00001-of-00002.safetensors",
611
+ "encoder.encoder.layers.19.layer_norm.weight": "model-00001-of-00002.safetensors",
612
+ "encoder.encoder.layers.2.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
613
+ "encoder.encoder.layers.2.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
614
+ "encoder.encoder.layers.2.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
615
+ "encoder.encoder.layers.2.attention.k_proj.bias": "model-00001-of-00002.safetensors",
616
+ "encoder.encoder.layers.2.attention.k_proj.weight": "model-00001-of-00002.safetensors",
617
+ "encoder.encoder.layers.2.attention.out_proj.bias": "model-00001-of-00002.safetensors",
618
+ "encoder.encoder.layers.2.attention.out_proj.weight": "model-00001-of-00002.safetensors",
619
+ "encoder.encoder.layers.2.attention.q_proj.bias": "model-00001-of-00002.safetensors",
620
+ "encoder.encoder.layers.2.attention.q_proj.weight": "model-00001-of-00002.safetensors",
621
+ "encoder.encoder.layers.2.attention.v_proj.bias": "model-00001-of-00002.safetensors",
622
+ "encoder.encoder.layers.2.attention.v_proj.weight": "model-00001-of-00002.safetensors",
623
+ "encoder.encoder.layers.2.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
624
+ "encoder.encoder.layers.2.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
625
+ "encoder.encoder.layers.2.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
626
+ "encoder.encoder.layers.2.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
627
+ "encoder.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
628
+ "encoder.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
629
+ "encoder.encoder.layers.2.layer_norm.bias": "model-00001-of-00002.safetensors",
630
+ "encoder.encoder.layers.2.layer_norm.weight": "model-00001-of-00002.safetensors",
631
+ "encoder.encoder.layers.20.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
632
+ "encoder.encoder.layers.20.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
633
+ "encoder.encoder.layers.20.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
634
+ "encoder.encoder.layers.20.attention.k_proj.bias": "model-00001-of-00002.safetensors",
635
+ "encoder.encoder.layers.20.attention.k_proj.weight": "model-00001-of-00002.safetensors",
636
+ "encoder.encoder.layers.20.attention.out_proj.bias": "model-00001-of-00002.safetensors",
637
+ "encoder.encoder.layers.20.attention.out_proj.weight": "model-00001-of-00002.safetensors",
638
+ "encoder.encoder.layers.20.attention.q_proj.bias": "model-00001-of-00002.safetensors",
639
+ "encoder.encoder.layers.20.attention.q_proj.weight": "model-00001-of-00002.safetensors",
640
+ "encoder.encoder.layers.20.attention.v_proj.bias": "model-00001-of-00002.safetensors",
641
+ "encoder.encoder.layers.20.attention.v_proj.weight": "model-00001-of-00002.safetensors",
642
+ "encoder.encoder.layers.20.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
643
+ "encoder.encoder.layers.20.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
644
+ "encoder.encoder.layers.20.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
645
+ "encoder.encoder.layers.20.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
646
+ "encoder.encoder.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
647
+ "encoder.encoder.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
648
+ "encoder.encoder.layers.20.layer_norm.bias": "model-00001-of-00002.safetensors",
649
+ "encoder.encoder.layers.20.layer_norm.weight": "model-00001-of-00002.safetensors",
650
+ "encoder.encoder.layers.21.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
651
+ "encoder.encoder.layers.21.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
652
+ "encoder.encoder.layers.21.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
653
+ "encoder.encoder.layers.21.attention.k_proj.bias": "model-00001-of-00002.safetensors",
654
+ "encoder.encoder.layers.21.attention.k_proj.weight": "model-00001-of-00002.safetensors",
655
+ "encoder.encoder.layers.21.attention.out_proj.bias": "model-00001-of-00002.safetensors",
656
+ "encoder.encoder.layers.21.attention.out_proj.weight": "model-00001-of-00002.safetensors",
657
+ "encoder.encoder.layers.21.attention.q_proj.bias": "model-00001-of-00002.safetensors",
658
+ "encoder.encoder.layers.21.attention.q_proj.weight": "model-00001-of-00002.safetensors",
659
+ "encoder.encoder.layers.21.attention.v_proj.bias": "model-00001-of-00002.safetensors",
660
+ "encoder.encoder.layers.21.attention.v_proj.weight": "model-00001-of-00002.safetensors",
661
+ "encoder.encoder.layers.21.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
662
+ "encoder.encoder.layers.21.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
663
+ "encoder.encoder.layers.21.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
664
+ "encoder.encoder.layers.21.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
665
+ "encoder.encoder.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
666
+ "encoder.encoder.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
667
+ "encoder.encoder.layers.21.layer_norm.bias": "model-00001-of-00002.safetensors",
668
+ "encoder.encoder.layers.21.layer_norm.weight": "model-00001-of-00002.safetensors",
669
+ "encoder.encoder.layers.22.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
670
+ "encoder.encoder.layers.22.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
671
+ "encoder.encoder.layers.22.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
672
+ "encoder.encoder.layers.22.attention.k_proj.bias": "model-00001-of-00002.safetensors",
673
+ "encoder.encoder.layers.22.attention.k_proj.weight": "model-00001-of-00002.safetensors",
674
+ "encoder.encoder.layers.22.attention.out_proj.bias": "model-00001-of-00002.safetensors",
675
+ "encoder.encoder.layers.22.attention.out_proj.weight": "model-00001-of-00002.safetensors",
676
+ "encoder.encoder.layers.22.attention.q_proj.bias": "model-00001-of-00002.safetensors",
677
+ "encoder.encoder.layers.22.attention.q_proj.weight": "model-00001-of-00002.safetensors",
678
+ "encoder.encoder.layers.22.attention.v_proj.bias": "model-00001-of-00002.safetensors",
679
+ "encoder.encoder.layers.22.attention.v_proj.weight": "model-00001-of-00002.safetensors",
680
+ "encoder.encoder.layers.22.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
681
+ "encoder.encoder.layers.22.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
682
+ "encoder.encoder.layers.22.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
683
+ "encoder.encoder.layers.22.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
684
+ "encoder.encoder.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
685
+ "encoder.encoder.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
686
+ "encoder.encoder.layers.22.layer_norm.bias": "model-00001-of-00002.safetensors",
687
+ "encoder.encoder.layers.22.layer_norm.weight": "model-00001-of-00002.safetensors",
688
+ "encoder.encoder.layers.23.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
689
+ "encoder.encoder.layers.23.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
690
+ "encoder.encoder.layers.23.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
691
+ "encoder.encoder.layers.23.attention.k_proj.bias": "model-00001-of-00002.safetensors",
692
+ "encoder.encoder.layers.23.attention.k_proj.weight": "model-00001-of-00002.safetensors",
693
+ "encoder.encoder.layers.23.attention.out_proj.bias": "model-00001-of-00002.safetensors",
694
+ "encoder.encoder.layers.23.attention.out_proj.weight": "model-00001-of-00002.safetensors",
695
+ "encoder.encoder.layers.23.attention.q_proj.bias": "model-00001-of-00002.safetensors",
696
+ "encoder.encoder.layers.23.attention.q_proj.weight": "model-00001-of-00002.safetensors",
697
+ "encoder.encoder.layers.23.attention.v_proj.bias": "model-00001-of-00002.safetensors",
698
+ "encoder.encoder.layers.23.attention.v_proj.weight": "model-00001-of-00002.safetensors",
699
+ "encoder.encoder.layers.23.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
700
+ "encoder.encoder.layers.23.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
701
+ "encoder.encoder.layers.23.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
702
+ "encoder.encoder.layers.23.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
703
+ "encoder.encoder.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
704
+ "encoder.encoder.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
705
+ "encoder.encoder.layers.23.layer_norm.bias": "model-00001-of-00002.safetensors",
706
+ "encoder.encoder.layers.23.layer_norm.weight": "model-00001-of-00002.safetensors",
707
+ "encoder.encoder.layers.3.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
708
+ "encoder.encoder.layers.3.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
709
+ "encoder.encoder.layers.3.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
710
+ "encoder.encoder.layers.3.attention.k_proj.bias": "model-00001-of-00002.safetensors",
711
+ "encoder.encoder.layers.3.attention.k_proj.weight": "model-00001-of-00002.safetensors",
712
+ "encoder.encoder.layers.3.attention.out_proj.bias": "model-00001-of-00002.safetensors",
713
+ "encoder.encoder.layers.3.attention.out_proj.weight": "model-00001-of-00002.safetensors",
714
+ "encoder.encoder.layers.3.attention.q_proj.bias": "model-00001-of-00002.safetensors",
715
+ "encoder.encoder.layers.3.attention.q_proj.weight": "model-00001-of-00002.safetensors",
716
+ "encoder.encoder.layers.3.attention.v_proj.bias": "model-00001-of-00002.safetensors",
717
+ "encoder.encoder.layers.3.attention.v_proj.weight": "model-00001-of-00002.safetensors",
718
+ "encoder.encoder.layers.3.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
719
+ "encoder.encoder.layers.3.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
720
+ "encoder.encoder.layers.3.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
721
+ "encoder.encoder.layers.3.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
722
+ "encoder.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
723
+ "encoder.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
724
+ "encoder.encoder.layers.3.layer_norm.bias": "model-00001-of-00002.safetensors",
725
+ "encoder.encoder.layers.3.layer_norm.weight": "model-00001-of-00002.safetensors",
726
+ "encoder.encoder.layers.4.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
727
+ "encoder.encoder.layers.4.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
728
+ "encoder.encoder.layers.4.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
729
+ "encoder.encoder.layers.4.attention.k_proj.bias": "model-00001-of-00002.safetensors",
730
+ "encoder.encoder.layers.4.attention.k_proj.weight": "model-00001-of-00002.safetensors",
731
+ "encoder.encoder.layers.4.attention.out_proj.bias": "model-00001-of-00002.safetensors",
732
+ "encoder.encoder.layers.4.attention.out_proj.weight": "model-00001-of-00002.safetensors",
733
+ "encoder.encoder.layers.4.attention.q_proj.bias": "model-00001-of-00002.safetensors",
734
+ "encoder.encoder.layers.4.attention.q_proj.weight": "model-00001-of-00002.safetensors",
735
+ "encoder.encoder.layers.4.attention.v_proj.bias": "model-00001-of-00002.safetensors",
736
+ "encoder.encoder.layers.4.attention.v_proj.weight": "model-00001-of-00002.safetensors",
737
+ "encoder.encoder.layers.4.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
738
+ "encoder.encoder.layers.4.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
739
+ "encoder.encoder.layers.4.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
740
+ "encoder.encoder.layers.4.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
741
+ "encoder.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
742
+ "encoder.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
743
+ "encoder.encoder.layers.4.layer_norm.bias": "model-00001-of-00002.safetensors",
744
+ "encoder.encoder.layers.4.layer_norm.weight": "model-00001-of-00002.safetensors",
745
+ "encoder.encoder.layers.5.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
746
+ "encoder.encoder.layers.5.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
747
+ "encoder.encoder.layers.5.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
748
+ "encoder.encoder.layers.5.attention.k_proj.bias": "model-00001-of-00002.safetensors",
749
+ "encoder.encoder.layers.5.attention.k_proj.weight": "model-00001-of-00002.safetensors",
750
+ "encoder.encoder.layers.5.attention.out_proj.bias": "model-00001-of-00002.safetensors",
751
+ "encoder.encoder.layers.5.attention.out_proj.weight": "model-00001-of-00002.safetensors",
752
+ "encoder.encoder.layers.5.attention.q_proj.bias": "model-00001-of-00002.safetensors",
753
+ "encoder.encoder.layers.5.attention.q_proj.weight": "model-00001-of-00002.safetensors",
754
+ "encoder.encoder.layers.5.attention.v_proj.bias": "model-00001-of-00002.safetensors",
755
+ "encoder.encoder.layers.5.attention.v_proj.weight": "model-00001-of-00002.safetensors",
756
+ "encoder.encoder.layers.5.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
757
+ "encoder.encoder.layers.5.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
758
+ "encoder.encoder.layers.5.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
759
+ "encoder.encoder.layers.5.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
760
+ "encoder.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
761
+ "encoder.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
762
+ "encoder.encoder.layers.5.layer_norm.bias": "model-00001-of-00002.safetensors",
763
+ "encoder.encoder.layers.5.layer_norm.weight": "model-00001-of-00002.safetensors",
764
+ "encoder.encoder.layers.6.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
765
+ "encoder.encoder.layers.6.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
766
+ "encoder.encoder.layers.6.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
767
+ "encoder.encoder.layers.6.attention.k_proj.bias": "model-00001-of-00002.safetensors",
768
+ "encoder.encoder.layers.6.attention.k_proj.weight": "model-00001-of-00002.safetensors",
769
+ "encoder.encoder.layers.6.attention.out_proj.bias": "model-00001-of-00002.safetensors",
770
+ "encoder.encoder.layers.6.attention.out_proj.weight": "model-00001-of-00002.safetensors",
771
+ "encoder.encoder.layers.6.attention.q_proj.bias": "model-00001-of-00002.safetensors",
772
+ "encoder.encoder.layers.6.attention.q_proj.weight": "model-00001-of-00002.safetensors",
773
+ "encoder.encoder.layers.6.attention.v_proj.bias": "model-00001-of-00002.safetensors",
774
+ "encoder.encoder.layers.6.attention.v_proj.weight": "model-00001-of-00002.safetensors",
775
+ "encoder.encoder.layers.6.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
776
+ "encoder.encoder.layers.6.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
777
+ "encoder.encoder.layers.6.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
778
+ "encoder.encoder.layers.6.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
779
+ "encoder.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
780
+ "encoder.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
781
+ "encoder.encoder.layers.6.layer_norm.bias": "model-00001-of-00002.safetensors",
782
+ "encoder.encoder.layers.6.layer_norm.weight": "model-00001-of-00002.safetensors",
783
+ "encoder.encoder.layers.7.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
784
+ "encoder.encoder.layers.7.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
785
+ "encoder.encoder.layers.7.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
786
+ "encoder.encoder.layers.7.attention.k_proj.bias": "model-00001-of-00002.safetensors",
787
+ "encoder.encoder.layers.7.attention.k_proj.weight": "model-00001-of-00002.safetensors",
788
+ "encoder.encoder.layers.7.attention.out_proj.bias": "model-00001-of-00002.safetensors",
789
+ "encoder.encoder.layers.7.attention.out_proj.weight": "model-00001-of-00002.safetensors",
790
+ "encoder.encoder.layers.7.attention.q_proj.bias": "model-00001-of-00002.safetensors",
791
+ "encoder.encoder.layers.7.attention.q_proj.weight": "model-00001-of-00002.safetensors",
792
+ "encoder.encoder.layers.7.attention.v_proj.bias": "model-00001-of-00002.safetensors",
793
+ "encoder.encoder.layers.7.attention.v_proj.weight": "model-00001-of-00002.safetensors",
794
+ "encoder.encoder.layers.7.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
795
+ "encoder.encoder.layers.7.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
796
+ "encoder.encoder.layers.7.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
797
+ "encoder.encoder.layers.7.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
798
+ "encoder.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
799
+ "encoder.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
800
+ "encoder.encoder.layers.7.layer_norm.bias": "model-00001-of-00002.safetensors",
801
+ "encoder.encoder.layers.7.layer_norm.weight": "model-00001-of-00002.safetensors",
802
+ "encoder.encoder.layers.8.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
803
+ "encoder.encoder.layers.8.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
804
+ "encoder.encoder.layers.8.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
805
+ "encoder.encoder.layers.8.attention.k_proj.bias": "model-00001-of-00002.safetensors",
806
+ "encoder.encoder.layers.8.attention.k_proj.weight": "model-00001-of-00002.safetensors",
807
+ "encoder.encoder.layers.8.attention.out_proj.bias": "model-00001-of-00002.safetensors",
808
+ "encoder.encoder.layers.8.attention.out_proj.weight": "model-00001-of-00002.safetensors",
809
+ "encoder.encoder.layers.8.attention.q_proj.bias": "model-00001-of-00002.safetensors",
810
+ "encoder.encoder.layers.8.attention.q_proj.weight": "model-00001-of-00002.safetensors",
811
+ "encoder.encoder.layers.8.attention.v_proj.bias": "model-00001-of-00002.safetensors",
812
+ "encoder.encoder.layers.8.attention.v_proj.weight": "model-00001-of-00002.safetensors",
813
+ "encoder.encoder.layers.8.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
814
+ "encoder.encoder.layers.8.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
815
+ "encoder.encoder.layers.8.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
816
+ "encoder.encoder.layers.8.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
817
+ "encoder.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
818
+ "encoder.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
819
+ "encoder.encoder.layers.8.layer_norm.bias": "model-00001-of-00002.safetensors",
820
+ "encoder.encoder.layers.8.layer_norm.weight": "model-00001-of-00002.safetensors",
821
+ "encoder.encoder.layers.9.attention.gru_rel_pos_const": "model-00001-of-00002.safetensors",
822
+ "encoder.encoder.layers.9.attention.gru_rel_pos_linear.bias": "model-00001-of-00002.safetensors",
823
+ "encoder.encoder.layers.9.attention.gru_rel_pos_linear.weight": "model-00001-of-00002.safetensors",
824
+ "encoder.encoder.layers.9.attention.k_proj.bias": "model-00001-of-00002.safetensors",
825
+ "encoder.encoder.layers.9.attention.k_proj.weight": "model-00001-of-00002.safetensors",
826
+ "encoder.encoder.layers.9.attention.out_proj.bias": "model-00001-of-00002.safetensors",
827
+ "encoder.encoder.layers.9.attention.out_proj.weight": "model-00001-of-00002.safetensors",
828
+ "encoder.encoder.layers.9.attention.q_proj.bias": "model-00001-of-00002.safetensors",
829
+ "encoder.encoder.layers.9.attention.q_proj.weight": "model-00001-of-00002.safetensors",
830
+ "encoder.encoder.layers.9.attention.v_proj.bias": "model-00001-of-00002.safetensors",
831
+ "encoder.encoder.layers.9.attention.v_proj.weight": "model-00001-of-00002.safetensors",
832
+ "encoder.encoder.layers.9.feed_forward.intermediate_dense.bias": "model-00001-of-00002.safetensors",
833
+ "encoder.encoder.layers.9.feed_forward.intermediate_dense.weight": "model-00001-of-00002.safetensors",
834
+ "encoder.encoder.layers.9.feed_forward.output_dense.bias": "model-00001-of-00002.safetensors",
835
+ "encoder.encoder.layers.9.feed_forward.output_dense.weight": "model-00001-of-00002.safetensors",
836
+ "encoder.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
837
+ "encoder.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
838
+ "encoder.encoder.layers.9.layer_norm.bias": "model-00001-of-00002.safetensors",
839
+ "encoder.encoder.layers.9.layer_norm.weight": "model-00001-of-00002.safetensors",
840
+ "encoder.encoder.pos_conv_embed.conv.bias": "model-00001-of-00002.safetensors",
841
+ "encoder.encoder.pos_conv_embed.conv.parametrizations.weight.original0": "model-00001-of-00002.safetensors",
842
+ "encoder.encoder.pos_conv_embed.conv.parametrizations.weight.original1": "model-00001-of-00002.safetensors",
843
+ "encoder.feature_extractor.conv_layers.0.conv.weight": "model-00001-of-00002.safetensors",
844
+ "encoder.feature_extractor.conv_layers.0.layer_norm.bias": "model-00001-of-00002.safetensors",
845
+ "encoder.feature_extractor.conv_layers.0.layer_norm.weight": "model-00001-of-00002.safetensors",
846
+ "encoder.feature_extractor.conv_layers.1.conv.weight": "model-00001-of-00002.safetensors",
847
+ "encoder.feature_extractor.conv_layers.1.layer_norm.bias": "model-00001-of-00002.safetensors",
848
+ "encoder.feature_extractor.conv_layers.1.layer_norm.weight": "model-00001-of-00002.safetensors",
849
+ "encoder.feature_extractor.conv_layers.2.conv.weight": "model-00001-of-00002.safetensors",
850
+ "encoder.feature_extractor.conv_layers.2.layer_norm.bias": "model-00001-of-00002.safetensors",
851
+ "encoder.feature_extractor.conv_layers.2.layer_norm.weight": "model-00001-of-00002.safetensors",
852
+ "encoder.feature_extractor.conv_layers.3.conv.weight": "model-00001-of-00002.safetensors",
853
+ "encoder.feature_extractor.conv_layers.3.layer_norm.bias": "model-00001-of-00002.safetensors",
854
+ "encoder.feature_extractor.conv_layers.3.layer_norm.weight": "model-00001-of-00002.safetensors",
855
+ "encoder.feature_extractor.conv_layers.4.conv.weight": "model-00001-of-00002.safetensors",
856
+ "encoder.feature_extractor.conv_layers.4.layer_norm.bias": "model-00001-of-00002.safetensors",
857
+ "encoder.feature_extractor.conv_layers.4.layer_norm.weight": "model-00001-of-00002.safetensors",
858
+ "encoder.feature_extractor.conv_layers.5.conv.weight": "model-00001-of-00002.safetensors",
859
+ "encoder.feature_extractor.conv_layers.5.layer_norm.bias": "model-00001-of-00002.safetensors",
860
+ "encoder.feature_extractor.conv_layers.5.layer_norm.weight": "model-00001-of-00002.safetensors",
861
+ "encoder.feature_extractor.conv_layers.6.conv.weight": "model-00001-of-00002.safetensors",
862
+ "encoder.feature_extractor.conv_layers.6.layer_norm.bias": "model-00001-of-00002.safetensors",
863
+ "encoder.feature_extractor.conv_layers.6.layer_norm.weight": "model-00001-of-00002.safetensors",
864
+ "encoder.feature_projection.layer_norm.bias": "model-00001-of-00002.safetensors",
865
+ "encoder.feature_projection.layer_norm.weight": "model-00001-of-00002.safetensors",
866
+ "encoder.feature_projection.projection.bias": "model-00001-of-00002.safetensors",
867
+ "encoder.feature_projection.projection.weight": "model-00001-of-00002.safetensors",
868
+ "encoder.masked_spec_embed": "model-00001-of-00002.safetensors"
869
+ }
870
+ }