hingeloss commited on
Commit
6bee936
1 Parent(s): 1ad7ecd

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hingeloss/gazelle-v4-adapter",
3
+ "architectures": [
4
+ "GazelleForConditionalGeneration"
5
+ ],
6
+ "audio_config": {
7
+ "_name_or_path": "facebook/wav2vec2-base-960h",
8
+ "activation_dropout": 0.1,
9
+ "adapter_attn_dim": null,
10
+ "adapter_kernel_size": 3,
11
+ "adapter_stride": 2,
12
+ "add_adapter": false,
13
+ "add_cross_attention": false,
14
+ "apply_spec_augment": true,
15
+ "architectures": [
16
+ "Wav2Vec2ForCTC"
17
+ ],
18
+ "attention_dropout": 0.1,
19
+ "bad_words_ids": null,
20
+ "begin_suppress_tokens": null,
21
+ "bos_token_id": 1,
22
+ "chunk_size_feed_forward": 0,
23
+ "classifier_proj_size": 256,
24
+ "codevector_dim": 256,
25
+ "contrastive_logits_temperature": 0.1,
26
+ "conv_bias": false,
27
+ "conv_dim": [
28
+ 512,
29
+ 512,
30
+ 512,
31
+ 512,
32
+ 512,
33
+ 512,
34
+ 512
35
+ ],
36
+ "conv_kernel": [
37
+ 10,
38
+ 3,
39
+ 3,
40
+ 3,
41
+ 3,
42
+ 2,
43
+ 2
44
+ ],
45
+ "conv_stride": [
46
+ 5,
47
+ 2,
48
+ 2,
49
+ 2,
50
+ 2,
51
+ 2,
52
+ 2
53
+ ],
54
+ "cross_attention_hidden_size": null,
55
+ "ctc_loss_reduction": "sum",
56
+ "ctc_zero_infinity": false,
57
+ "decoder_start_token_id": null,
58
+ "diversity_loss_weight": 0.1,
59
+ "diversity_penalty": 0.0,
60
+ "do_sample": false,
61
+ "do_stable_layer_norm": false,
62
+ "early_stopping": false,
63
+ "encoder_no_repeat_ngram_size": 0,
64
+ "eos_token_id": 2,
65
+ "exponential_decay_length_penalty": null,
66
+ "feat_extract_activation": "gelu",
67
+ "feat_extract_dropout": 0.0,
68
+ "feat_extract_norm": "group",
69
+ "feat_proj_dropout": 0.1,
70
+ "feat_quantizer_dropout": 0.0,
71
+ "final_dropout": 0.1,
72
+ "finetuning_task": null,
73
+ "forced_bos_token_id": null,
74
+ "forced_eos_token_id": null,
75
+ "gradient_checkpointing": false,
76
+ "hidden_act": "gelu",
77
+ "hidden_dropout": 0.1,
78
+ "hidden_dropout_prob": 0.1,
79
+ "hidden_size": 768,
80
+ "id2label": {
81
+ "0": "LABEL_0",
82
+ "1": "LABEL_1"
83
+ },
84
+ "initializer_range": 0.02,
85
+ "intermediate_size": 3072,
86
+ "is_decoder": false,
87
+ "is_encoder_decoder": false,
88
+ "label2id": {
89
+ "LABEL_0": 0,
90
+ "LABEL_1": 1
91
+ },
92
+ "layer_norm_eps": 1e-05,
93
+ "layerdrop": 0.1,
94
+ "length_penalty": 1.0,
95
+ "mask_feature_length": 10,
96
+ "mask_feature_min_masks": 0,
97
+ "mask_feature_prob": 0.0,
98
+ "mask_time_length": 10,
99
+ "mask_time_min_masks": 2,
100
+ "mask_time_prob": 0.05,
101
+ "max_length": 20,
102
+ "min_length": 0,
103
+ "model_type": "wav2vec2",
104
+ "no_repeat_ngram_size": 0,
105
+ "num_adapter_layers": 3,
106
+ "num_attention_heads": 12,
107
+ "num_beam_groups": 1,
108
+ "num_beams": 1,
109
+ "num_codevector_groups": 2,
110
+ "num_codevectors_per_group": 320,
111
+ "num_conv_pos_embedding_groups": 16,
112
+ "num_conv_pos_embeddings": 128,
113
+ "num_feat_extract_layers": 7,
114
+ "num_hidden_layers": 12,
115
+ "num_negatives": 100,
116
+ "num_return_sequences": 1,
117
+ "output_attentions": false,
118
+ "output_hidden_size": 768,
119
+ "output_hidden_states": false,
120
+ "output_scores": false,
121
+ "pad_token_id": 0,
122
+ "prefix": null,
123
+ "problem_type": null,
124
+ "proj_codevector_dim": 256,
125
+ "pruned_heads": {},
126
+ "remove_invalid_values": false,
127
+ "repetition_penalty": 1.0,
128
+ "return_dict": true,
129
+ "return_dict_in_generate": false,
130
+ "sep_token_id": null,
131
+ "suppress_tokens": null,
132
+ "task_specific_params": null,
133
+ "tdnn_dilation": [
134
+ 1,
135
+ 2,
136
+ 3,
137
+ 1,
138
+ 1
139
+ ],
140
+ "tdnn_dim": [
141
+ 512,
142
+ 512,
143
+ 512,
144
+ 512,
145
+ 1500
146
+ ],
147
+ "tdnn_kernel": [
148
+ 5,
149
+ 3,
150
+ 3,
151
+ 1,
152
+ 1
153
+ ],
154
+ "temperature": 1.0,
155
+ "tf_legacy_loss": false,
156
+ "tie_encoder_decoder": false,
157
+ "tie_word_embeddings": true,
158
+ "tokenizer_class": null,
159
+ "top_k": 50,
160
+ "top_p": 1.0,
161
+ "torch_dtype": null,
162
+ "torchscript": false,
163
+ "typical_p": 1.0,
164
+ "use_bfloat16": false,
165
+ "use_weighted_layer_sum": false,
166
+ "vocab_size": 32,
167
+ "xvector_output_dim": 512
168
+ },
169
+ "audio_model_id": "facebook/wav2vec2-base-960h",
170
+ "audio_token_index": 32000,
171
+ "hidden_size": 4096,
172
+ "ignore_index": -100,
173
+ "model_type": "gazelle",
174
+ "projector_hidden_act": "gelu",
175
+ "stack_factor": 8,
176
+ "text_config": {
177
+ "_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
178
+ "architectures": [
179
+ "LlamaForCausalLM"
180
+ ],
181
+ "max_position_embeddings": 4096,
182
+ "model_type": "llama",
183
+ "rms_norm_eps": 1e-05,
184
+ "torch_dtype": "float16"
185
+ },
186
+ "text_model_id": "meta-llama/Llama-2-7b-chat-hf",
187
+ "torch_dtype": "bfloat16",
188
+ "transformers_version": "4.38.1",
189
+ "vocab_size": 32001
190
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.38.1"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfbc9eee5ad84d72f16b06a6069ea15cfd4e6e06012c438b793f03f02ea2b514
3
+ size 4970498792
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ac13402493ed90c04a92ff2ccc10c9d63bb15e93c167de01a372c7820745eaf
3
+ size 4991433112
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22c8dab433a00e789013a19b45b921a0a5762ad01c438c5de6f908ece915f32a
3
+ size 3770853496
model.safetensors.index.json ADDED
@@ -0,0 +1,513 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13732720384
4
+ },
5
+ "weight_map": {
6
+ "audio_tower.encoder.layer_norm.bias": "model-00001-of-00003.safetensors",
7
+ "audio_tower.encoder.layer_norm.weight": "model-00001-of-00003.safetensors",
8
+ "audio_tower.encoder.layers.0.attention.k_proj.bias": "model-00001-of-00003.safetensors",
9
+ "audio_tower.encoder.layers.0.attention.k_proj.weight": "model-00001-of-00003.safetensors",
10
+ "audio_tower.encoder.layers.0.attention.out_proj.bias": "model-00001-of-00003.safetensors",
11
+ "audio_tower.encoder.layers.0.attention.out_proj.weight": "model-00001-of-00003.safetensors",
12
+ "audio_tower.encoder.layers.0.attention.q_proj.bias": "model-00001-of-00003.safetensors",
13
+ "audio_tower.encoder.layers.0.attention.q_proj.weight": "model-00001-of-00003.safetensors",
14
+ "audio_tower.encoder.layers.0.attention.v_proj.bias": "model-00001-of-00003.safetensors",
15
+ "audio_tower.encoder.layers.0.attention.v_proj.weight": "model-00001-of-00003.safetensors",
16
+ "audio_tower.encoder.layers.0.feed_forward.intermediate_dense.bias": "model-00001-of-00003.safetensors",
17
+ "audio_tower.encoder.layers.0.feed_forward.intermediate_dense.weight": "model-00001-of-00003.safetensors",
18
+ "audio_tower.encoder.layers.0.feed_forward.output_dense.bias": "model-00001-of-00003.safetensors",
19
+ "audio_tower.encoder.layers.0.feed_forward.output_dense.weight": "model-00001-of-00003.safetensors",
20
+ "audio_tower.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
21
+ "audio_tower.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
22
+ "audio_tower.encoder.layers.0.layer_norm.bias": "model-00001-of-00003.safetensors",
23
+ "audio_tower.encoder.layers.0.layer_norm.weight": "model-00001-of-00003.safetensors",
24
+ "audio_tower.encoder.layers.1.attention.k_proj.bias": "model-00001-of-00003.safetensors",
25
+ "audio_tower.encoder.layers.1.attention.k_proj.weight": "model-00001-of-00003.safetensors",
26
+ "audio_tower.encoder.layers.1.attention.out_proj.bias": "model-00001-of-00003.safetensors",
27
+ "audio_tower.encoder.layers.1.attention.out_proj.weight": "model-00001-of-00003.safetensors",
28
+ "audio_tower.encoder.layers.1.attention.q_proj.bias": "model-00001-of-00003.safetensors",
29
+ "audio_tower.encoder.layers.1.attention.q_proj.weight": "model-00001-of-00003.safetensors",
30
+ "audio_tower.encoder.layers.1.attention.v_proj.bias": "model-00001-of-00003.safetensors",
31
+ "audio_tower.encoder.layers.1.attention.v_proj.weight": "model-00001-of-00003.safetensors",
32
+ "audio_tower.encoder.layers.1.feed_forward.intermediate_dense.bias": "model-00001-of-00003.safetensors",
33
+ "audio_tower.encoder.layers.1.feed_forward.intermediate_dense.weight": "model-00001-of-00003.safetensors",
34
+ "audio_tower.encoder.layers.1.feed_forward.output_dense.bias": "model-00001-of-00003.safetensors",
35
+ "audio_tower.encoder.layers.1.feed_forward.output_dense.weight": "model-00001-of-00003.safetensors",
36
+ "audio_tower.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
37
+ "audio_tower.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
38
+ "audio_tower.encoder.layers.1.layer_norm.bias": "model-00001-of-00003.safetensors",
39
+ "audio_tower.encoder.layers.1.layer_norm.weight": "model-00001-of-00003.safetensors",
40
+ "audio_tower.encoder.layers.10.attention.k_proj.bias": "model-00001-of-00003.safetensors",
41
+ "audio_tower.encoder.layers.10.attention.k_proj.weight": "model-00001-of-00003.safetensors",
42
+ "audio_tower.encoder.layers.10.attention.out_proj.bias": "model-00001-of-00003.safetensors",
43
+ "audio_tower.encoder.layers.10.attention.out_proj.weight": "model-00001-of-00003.safetensors",
44
+ "audio_tower.encoder.layers.10.attention.q_proj.bias": "model-00001-of-00003.safetensors",
45
+ "audio_tower.encoder.layers.10.attention.q_proj.weight": "model-00001-of-00003.safetensors",
46
+ "audio_tower.encoder.layers.10.attention.v_proj.bias": "model-00001-of-00003.safetensors",
47
+ "audio_tower.encoder.layers.10.attention.v_proj.weight": "model-00001-of-00003.safetensors",
48
+ "audio_tower.encoder.layers.10.feed_forward.intermediate_dense.bias": "model-00001-of-00003.safetensors",
49
+ "audio_tower.encoder.layers.10.feed_forward.intermediate_dense.weight": "model-00001-of-00003.safetensors",
50
+ "audio_tower.encoder.layers.10.feed_forward.output_dense.bias": "model-00001-of-00003.safetensors",
51
+ "audio_tower.encoder.layers.10.feed_forward.output_dense.weight": "model-00001-of-00003.safetensors",
52
+ "audio_tower.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00003.safetensors",
53
+ "audio_tower.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00003.safetensors",
54
+ "audio_tower.encoder.layers.10.layer_norm.bias": "model-00001-of-00003.safetensors",
55
+ "audio_tower.encoder.layers.10.layer_norm.weight": "model-00001-of-00003.safetensors",
56
+ "audio_tower.encoder.layers.11.attention.k_proj.bias": "model-00001-of-00003.safetensors",
57
+ "audio_tower.encoder.layers.11.attention.k_proj.weight": "model-00001-of-00003.safetensors",
58
+ "audio_tower.encoder.layers.11.attention.out_proj.bias": "model-00001-of-00003.safetensors",
59
+ "audio_tower.encoder.layers.11.attention.out_proj.weight": "model-00001-of-00003.safetensors",
60
+ "audio_tower.encoder.layers.11.attention.q_proj.bias": "model-00001-of-00003.safetensors",
61
+ "audio_tower.encoder.layers.11.attention.q_proj.weight": "model-00001-of-00003.safetensors",
62
+ "audio_tower.encoder.layers.11.attention.v_proj.bias": "model-00001-of-00003.safetensors",
63
+ "audio_tower.encoder.layers.11.attention.v_proj.weight": "model-00001-of-00003.safetensors",
64
+ "audio_tower.encoder.layers.11.feed_forward.intermediate_dense.bias": "model-00001-of-00003.safetensors",
65
+ "audio_tower.encoder.layers.11.feed_forward.intermediate_dense.weight": "model-00001-of-00003.safetensors",
66
+ "audio_tower.encoder.layers.11.feed_forward.output_dense.bias": "model-00001-of-00003.safetensors",
67
+ "audio_tower.encoder.layers.11.feed_forward.output_dense.weight": "model-00001-of-00003.safetensors",
68
+ "audio_tower.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00003.safetensors",
69
+ "audio_tower.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00003.safetensors",
70
+ "audio_tower.encoder.layers.11.layer_norm.bias": "model-00001-of-00003.safetensors",
71
+ "audio_tower.encoder.layers.11.layer_norm.weight": "model-00001-of-00003.safetensors",
72
+ "audio_tower.encoder.layers.2.attention.k_proj.bias": "model-00001-of-00003.safetensors",
73
+ "audio_tower.encoder.layers.2.attention.k_proj.weight": "model-00001-of-00003.safetensors",
74
+ "audio_tower.encoder.layers.2.attention.out_proj.bias": "model-00001-of-00003.safetensors",
75
+ "audio_tower.encoder.layers.2.attention.out_proj.weight": "model-00001-of-00003.safetensors",
76
+ "audio_tower.encoder.layers.2.attention.q_proj.bias": "model-00001-of-00003.safetensors",
77
+ "audio_tower.encoder.layers.2.attention.q_proj.weight": "model-00001-of-00003.safetensors",
78
+ "audio_tower.encoder.layers.2.attention.v_proj.bias": "model-00001-of-00003.safetensors",
79
+ "audio_tower.encoder.layers.2.attention.v_proj.weight": "model-00001-of-00003.safetensors",
80
+ "audio_tower.encoder.layers.2.feed_forward.intermediate_dense.bias": "model-00001-of-00003.safetensors",
81
+ "audio_tower.encoder.layers.2.feed_forward.intermediate_dense.weight": "model-00001-of-00003.safetensors",
82
+ "audio_tower.encoder.layers.2.feed_forward.output_dense.bias": "model-00001-of-00003.safetensors",
83
+ "audio_tower.encoder.layers.2.feed_forward.output_dense.weight": "model-00001-of-00003.safetensors",
84
+ "audio_tower.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
85
+ "audio_tower.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
86
+ "audio_tower.encoder.layers.2.layer_norm.bias": "model-00001-of-00003.safetensors",
87
+ "audio_tower.encoder.layers.2.layer_norm.weight": "model-00001-of-00003.safetensors",
88
+ "audio_tower.encoder.layers.3.attention.k_proj.bias": "model-00001-of-00003.safetensors",
89
+ "audio_tower.encoder.layers.3.attention.k_proj.weight": "model-00001-of-00003.safetensors",
90
+ "audio_tower.encoder.layers.3.attention.out_proj.bias": "model-00001-of-00003.safetensors",
91
+ "audio_tower.encoder.layers.3.attention.out_proj.weight": "model-00001-of-00003.safetensors",
92
+ "audio_tower.encoder.layers.3.attention.q_proj.bias": "model-00001-of-00003.safetensors",
93
+ "audio_tower.encoder.layers.3.attention.q_proj.weight": "model-00001-of-00003.safetensors",
94
+ "audio_tower.encoder.layers.3.attention.v_proj.bias": "model-00001-of-00003.safetensors",
95
+ "audio_tower.encoder.layers.3.attention.v_proj.weight": "model-00001-of-00003.safetensors",
96
+ "audio_tower.encoder.layers.3.feed_forward.intermediate_dense.bias": "model-00001-of-00003.safetensors",
97
+ "audio_tower.encoder.layers.3.feed_forward.intermediate_dense.weight": "model-00001-of-00003.safetensors",
98
+ "audio_tower.encoder.layers.3.feed_forward.output_dense.bias": "model-00001-of-00003.safetensors",
99
+ "audio_tower.encoder.layers.3.feed_forward.output_dense.weight": "model-00001-of-00003.safetensors",
100
+ "audio_tower.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
101
+ "audio_tower.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
102
+ "audio_tower.encoder.layers.3.layer_norm.bias": "model-00001-of-00003.safetensors",
103
+ "audio_tower.encoder.layers.3.layer_norm.weight": "model-00001-of-00003.safetensors",
104
+ "audio_tower.encoder.layers.4.attention.k_proj.bias": "model-00001-of-00003.safetensors",
105
+ "audio_tower.encoder.layers.4.attention.k_proj.weight": "model-00001-of-00003.safetensors",
106
+ "audio_tower.encoder.layers.4.attention.out_proj.bias": "model-00001-of-00003.safetensors",
107
+ "audio_tower.encoder.layers.4.attention.out_proj.weight": "model-00001-of-00003.safetensors",
108
+ "audio_tower.encoder.layers.4.attention.q_proj.bias": "model-00001-of-00003.safetensors",
109
+ "audio_tower.encoder.layers.4.attention.q_proj.weight": "model-00001-of-00003.safetensors",
110
+ "audio_tower.encoder.layers.4.attention.v_proj.bias": "model-00001-of-00003.safetensors",
111
+ "audio_tower.encoder.layers.4.attention.v_proj.weight": "model-00001-of-00003.safetensors",
112
+ "audio_tower.encoder.layers.4.feed_forward.intermediate_dense.bias": "model-00001-of-00003.safetensors",
113
+ "audio_tower.encoder.layers.4.feed_forward.intermediate_dense.weight": "model-00001-of-00003.safetensors",
114
+ "audio_tower.encoder.layers.4.feed_forward.output_dense.bias": "model-00001-of-00003.safetensors",
115
+ "audio_tower.encoder.layers.4.feed_forward.output_dense.weight": "model-00001-of-00003.safetensors",
116
+ "audio_tower.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
117
+ "audio_tower.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
118
+ "audio_tower.encoder.layers.4.layer_norm.bias": "model-00001-of-00003.safetensors",
119
+ "audio_tower.encoder.layers.4.layer_norm.weight": "model-00001-of-00003.safetensors",
120
+ "audio_tower.encoder.layers.5.attention.k_proj.bias": "model-00001-of-00003.safetensors",
121
+ "audio_tower.encoder.layers.5.attention.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "audio_tower.encoder.layers.5.attention.out_proj.bias": "model-00001-of-00003.safetensors",
123
+ "audio_tower.encoder.layers.5.attention.out_proj.weight": "model-00001-of-00003.safetensors",
124
+ "audio_tower.encoder.layers.5.attention.q_proj.bias": "model-00001-of-00003.safetensors",
125
+ "audio_tower.encoder.layers.5.attention.q_proj.weight": "model-00001-of-00003.safetensors",
126
+ "audio_tower.encoder.layers.5.attention.v_proj.bias": "model-00001-of-00003.safetensors",
127
+ "audio_tower.encoder.layers.5.attention.v_proj.weight": "model-00001-of-00003.safetensors",
128
+ "audio_tower.encoder.layers.5.feed_forward.intermediate_dense.bias": "model-00001-of-00003.safetensors",
129
+ "audio_tower.encoder.layers.5.feed_forward.intermediate_dense.weight": "model-00001-of-00003.safetensors",
130
+ "audio_tower.encoder.layers.5.feed_forward.output_dense.bias": "model-00001-of-00003.safetensors",
131
+ "audio_tower.encoder.layers.5.feed_forward.output_dense.weight": "model-00001-of-00003.safetensors",
132
+ "audio_tower.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
133
+ "audio_tower.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
134
+ "audio_tower.encoder.layers.5.layer_norm.bias": "model-00001-of-00003.safetensors",
135
+ "audio_tower.encoder.layers.5.layer_norm.weight": "model-00001-of-00003.safetensors",
136
+ "audio_tower.encoder.layers.6.attention.k_proj.bias": "model-00001-of-00003.safetensors",
137
+ "audio_tower.encoder.layers.6.attention.k_proj.weight": "model-00001-of-00003.safetensors",
138
+ "audio_tower.encoder.layers.6.attention.out_proj.bias": "model-00001-of-00003.safetensors",
139
+ "audio_tower.encoder.layers.6.attention.out_proj.weight": "model-00001-of-00003.safetensors",
140
+ "audio_tower.encoder.layers.6.attention.q_proj.bias": "model-00001-of-00003.safetensors",
141
+ "audio_tower.encoder.layers.6.attention.q_proj.weight": "model-00001-of-00003.safetensors",
142
+ "audio_tower.encoder.layers.6.attention.v_proj.bias": "model-00001-of-00003.safetensors",
143
+ "audio_tower.encoder.layers.6.attention.v_proj.weight": "model-00001-of-00003.safetensors",
144
+ "audio_tower.encoder.layers.6.feed_forward.intermediate_dense.bias": "model-00001-of-00003.safetensors",
145
+ "audio_tower.encoder.layers.6.feed_forward.intermediate_dense.weight": "model-00001-of-00003.safetensors",
146
+ "audio_tower.encoder.layers.6.feed_forward.output_dense.bias": "model-00001-of-00003.safetensors",
147
+ "audio_tower.encoder.layers.6.feed_forward.output_dense.weight": "model-00001-of-00003.safetensors",
148
+ "audio_tower.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
149
+ "audio_tower.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
150
+ "audio_tower.encoder.layers.6.layer_norm.bias": "model-00001-of-00003.safetensors",
151
+ "audio_tower.encoder.layers.6.layer_norm.weight": "model-00001-of-00003.safetensors",
152
+ "audio_tower.encoder.layers.7.attention.k_proj.bias": "model-00001-of-00003.safetensors",
153
+ "audio_tower.encoder.layers.7.attention.k_proj.weight": "model-00001-of-00003.safetensors",
154
+ "audio_tower.encoder.layers.7.attention.out_proj.bias": "model-00001-of-00003.safetensors",
155
+ "audio_tower.encoder.layers.7.attention.out_proj.weight": "model-00001-of-00003.safetensors",
156
+ "audio_tower.encoder.layers.7.attention.q_proj.bias": "model-00001-of-00003.safetensors",
157
+ "audio_tower.encoder.layers.7.attention.q_proj.weight": "model-00001-of-00003.safetensors",
158
+ "audio_tower.encoder.layers.7.attention.v_proj.bias": "model-00001-of-00003.safetensors",
159
+ "audio_tower.encoder.layers.7.attention.v_proj.weight": "model-00001-of-00003.safetensors",
160
+ "audio_tower.encoder.layers.7.feed_forward.intermediate_dense.bias": "model-00001-of-00003.safetensors",
161
+ "audio_tower.encoder.layers.7.feed_forward.intermediate_dense.weight": "model-00001-of-00003.safetensors",
162
+ "audio_tower.encoder.layers.7.feed_forward.output_dense.bias": "model-00001-of-00003.safetensors",
163
+ "audio_tower.encoder.layers.7.feed_forward.output_dense.weight": "model-00001-of-00003.safetensors",
164
+ "audio_tower.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
165
+ "audio_tower.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
166
+ "audio_tower.encoder.layers.7.layer_norm.bias": "model-00001-of-00003.safetensors",
167
+ "audio_tower.encoder.layers.7.layer_norm.weight": "model-00001-of-00003.safetensors",
168
+ "audio_tower.encoder.layers.8.attention.k_proj.bias": "model-00001-of-00003.safetensors",
169
+ "audio_tower.encoder.layers.8.attention.k_proj.weight": "model-00001-of-00003.safetensors",
170
+ "audio_tower.encoder.layers.8.attention.out_proj.bias": "model-00001-of-00003.safetensors",
171
+ "audio_tower.encoder.layers.8.attention.out_proj.weight": "model-00001-of-00003.safetensors",
172
+ "audio_tower.encoder.layers.8.attention.q_proj.bias": "model-00001-of-00003.safetensors",
173
+ "audio_tower.encoder.layers.8.attention.q_proj.weight": "model-00001-of-00003.safetensors",
174
+ "audio_tower.encoder.layers.8.attention.v_proj.bias": "model-00001-of-00003.safetensors",
175
+ "audio_tower.encoder.layers.8.attention.v_proj.weight": "model-00001-of-00003.safetensors",
176
+ "audio_tower.encoder.layers.8.feed_forward.intermediate_dense.bias": "model-00001-of-00003.safetensors",
177
+ "audio_tower.encoder.layers.8.feed_forward.intermediate_dense.weight": "model-00001-of-00003.safetensors",
178
+ "audio_tower.encoder.layers.8.feed_forward.output_dense.bias": "model-00001-of-00003.safetensors",
179
+ "audio_tower.encoder.layers.8.feed_forward.output_dense.weight": "model-00001-of-00003.safetensors",
180
+ "audio_tower.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors",
181
+ "audio_tower.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors",
182
+ "audio_tower.encoder.layers.8.layer_norm.bias": "model-00001-of-00003.safetensors",
183
+ "audio_tower.encoder.layers.8.layer_norm.weight": "model-00001-of-00003.safetensors",
184
+ "audio_tower.encoder.layers.9.attention.k_proj.bias": "model-00001-of-00003.safetensors",
185
+ "audio_tower.encoder.layers.9.attention.k_proj.weight": "model-00001-of-00003.safetensors",
186
+ "audio_tower.encoder.layers.9.attention.out_proj.bias": "model-00001-of-00003.safetensors",
187
+ "audio_tower.encoder.layers.9.attention.out_proj.weight": "model-00001-of-00003.safetensors",
188
+ "audio_tower.encoder.layers.9.attention.q_proj.bias": "model-00001-of-00003.safetensors",
189
+ "audio_tower.encoder.layers.9.attention.q_proj.weight": "model-00001-of-00003.safetensors",
190
+ "audio_tower.encoder.layers.9.attention.v_proj.bias": "model-00001-of-00003.safetensors",
191
+ "audio_tower.encoder.layers.9.attention.v_proj.weight": "model-00001-of-00003.safetensors",
192
+ "audio_tower.encoder.layers.9.feed_forward.intermediate_dense.bias": "model-00001-of-00003.safetensors",
193
+ "audio_tower.encoder.layers.9.feed_forward.intermediate_dense.weight": "model-00001-of-00003.safetensors",
194
+ "audio_tower.encoder.layers.9.feed_forward.output_dense.bias": "model-00001-of-00003.safetensors",
195
+ "audio_tower.encoder.layers.9.feed_forward.output_dense.weight": "model-00001-of-00003.safetensors",
196
+ "audio_tower.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors",
197
+ "audio_tower.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors",
198
+ "audio_tower.encoder.layers.9.layer_norm.bias": "model-00001-of-00003.safetensors",
199
+ "audio_tower.encoder.layers.9.layer_norm.weight": "model-00001-of-00003.safetensors",
200
+ "audio_tower.encoder.pos_conv_embed.conv.bias": "model-00001-of-00003.safetensors",
201
+ "audio_tower.encoder.pos_conv_embed.conv.parametrizations.weight.original0": "model-00001-of-00003.safetensors",
202
+ "audio_tower.encoder.pos_conv_embed.conv.parametrizations.weight.original1": "model-00001-of-00003.safetensors",
203
+ "audio_tower.feature_extractor.conv_layers.0.conv.weight": "model-00001-of-00003.safetensors",
204
+ "audio_tower.feature_extractor.conv_layers.0.layer_norm.bias": "model-00001-of-00003.safetensors",
205
+ "audio_tower.feature_extractor.conv_layers.0.layer_norm.weight": "model-00001-of-00003.safetensors",
206
+ "audio_tower.feature_extractor.conv_layers.1.conv.weight": "model-00001-of-00003.safetensors",
207
+ "audio_tower.feature_extractor.conv_layers.2.conv.weight": "model-00001-of-00003.safetensors",
208
+ "audio_tower.feature_extractor.conv_layers.3.conv.weight": "model-00001-of-00003.safetensors",
209
+ "audio_tower.feature_extractor.conv_layers.4.conv.weight": "model-00001-of-00003.safetensors",
210
+ "audio_tower.feature_extractor.conv_layers.5.conv.weight": "model-00001-of-00003.safetensors",
211
+ "audio_tower.feature_extractor.conv_layers.6.conv.weight": "model-00001-of-00003.safetensors",
212
+ "audio_tower.feature_projection.layer_norm.bias": "model-00001-of-00003.safetensors",
213
+ "audio_tower.feature_projection.layer_norm.weight": "model-00001-of-00003.safetensors",
214
+ "audio_tower.feature_projection.projection.bias": "model-00001-of-00003.safetensors",
215
+ "audio_tower.feature_projection.projection.weight": "model-00001-of-00003.safetensors",
216
+ "audio_tower.masked_spec_embed": "model-00001-of-00003.safetensors",
217
+ "language_model.lm_head.weight": "model-00003-of-00003.safetensors",
218
+ "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
219
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
221
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
222
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
223
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
224
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
225
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
226
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
227
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
228
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
229
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
230
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
231
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
232
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
233
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
234
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
235
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
236
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
237
+ "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
238
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
239
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
240
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
241
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
242
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
243
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
244
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
245
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
246
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
247
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
248
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
249
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
250
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
251
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
252
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
253
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
254
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
255
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
256
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
257
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
258
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
259
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
260
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
261
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
262
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
263
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
264
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
265
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
266
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
267
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
268
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
269
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
270
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
271
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
272
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
273
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
274
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
275
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
276
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
277
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
278
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
279
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
280
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
281
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
282
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
283
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
284
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
285
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
286
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
287
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
288
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
289
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
290
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
291
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
292
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
293
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
294
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
295
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
296
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
297
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
298
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
299
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
300
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
301
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
302
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
303
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
304
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
305
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
306
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
307
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
308
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
309
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
310
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
311
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
312
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
313
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
314
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
315
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
316
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
317
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
318
+ "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
319
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
320
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
321
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
322
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
323
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
324
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
325
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
326
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
327
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
328
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
329
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
330
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
331
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
332
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
333
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
334
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
335
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
336
+ "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
337
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
338
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
339
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
340
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
341
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
342
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
343
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
344
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
345
+ "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
346
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
347
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
348
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
349
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
350
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
351
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
352
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
353
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
354
+ "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
355
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
356
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
357
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
358
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
359
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
360
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
361
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
362
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
363
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
364
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
365
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
366
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
367
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
368
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
369
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
370
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
371
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
372
+ "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
373
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
374
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
375
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
376
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
377
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
378
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
379
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
380
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
381
+ "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
382
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
383
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
384
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
385
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
386
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
387
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
388
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
389
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
390
+ "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
391
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
392
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
393
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
394
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
395
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
396
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
397
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
398
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
399
+ "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
400
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
401
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
402
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
403
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
404
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
405
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
406
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
407
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
408
+ "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
409
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
410
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
411
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
412
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
413
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
414
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
415
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
416
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
417
+ "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
418
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
419
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
420
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
421
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
422
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
423
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
424
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
425
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
426
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
427
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
428
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
429
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
430
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
431
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
432
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
433
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
434
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
435
+ "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
436
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
437
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
438
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
439
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
440
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
441
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
442
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
443
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
444
+ "language_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
445
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
446
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
447
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
448
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
449
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
450
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
451
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
452
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
453
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
454
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
455
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
456
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
457
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
458
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
459
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
460
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
461
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
462
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
463
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
464
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
465
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
466
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
467
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
468
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
469
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
470
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
471
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
472
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
473
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
474
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
475
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
476
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
477
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
478
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
479
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
480
+ "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
481
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
482
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
483
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
484
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
485
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
486
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
487
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
488
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
489
+ "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
490
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
491
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
492
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
493
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
494
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
495
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
496
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
497
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
498
+ "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
499
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
500
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
501
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
502
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
503
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
504
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
505
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
506
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
507
+ "language_model.model.norm.weight": "model-00003-of-00003.safetensors",
508
+ "multi_modal_projector.linear_1.weight": "model-00001-of-00003.safetensors",
509
+ "multi_modal_projector.linear_2.weight": "model-00001-of-00003.safetensors",
510
+ "multi_modal_projector.ln_post.weight": "model-00001-of-00003.safetensors",
511
+ "multi_modal_projector.ln_pre.weight": "model-00001-of-00003.safetensors"
512
+ }
513
+ }