Hugging Face's logo

Qwen
/
Qwen2-Audio-7B

Audio-Text-to-Text
Transformers
Safetensors
English
qwen2_audio
text2text-generation
chat
audio
Inference Endpoints
Model card Files Community
2
faychu commited on
Commit
cd5e25c
•
1 Parent(s): 338435c

Add ckpt

Browse files
Files changed (13) hide show
  1. config.json +34 -0
  2. generation_config.json +11 -0
  3. merges.txt +0 -0
  4. model-00001-of-00005.safetensors +3 -0
  5. model-00002-of-00005.safetensors +3 -0
  6. model-00003-of-00005.safetensors +3 -0
  7. model-00004-of-00005.safetensors +3 -0
  8. model-00005-of-00005.safetensors +3 -0
  9. model.safetensors.index.json +883 -0
  10. preprocessor_config.json +14 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +0 -0
  13. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2AudioForConditionalGeneration"
4
+ ],
5
+ "audio_config": {
6
+ "model_type": "qwen2_audio_encoder",
7
+ "num_mel_bins": 128,
8
+ "encoder_layers": 32,
9
+ "encoder_attention_heads": 20,
10
+ "encoder_ffn_dim": 5120,
11
+ "d_model": 1280,
12
+ "activation_function": "gelu",
13
+ "scale_embedding": false,
14
+ "max_source_positions": 1500
15
+ },
16
+ "audio_token_index": 151646,
17
+ "ignore_index": -100,
18
+ "model_type": "qwen2_audio",
19
+ "text_config": {
20
+ "bos_token_id": 151643,
21
+ "eos_token_id": 151645,
22
+ "intermediate_size": 11008,
23
+ "max_position_embeddings": 8192,
24
+ "model_type": "qwen2",
25
+ "rope_theta": 10000,
26
+ "rms_norm_eps": 1e-5,
27
+ "sliding_window": 32768,
28
+ "torch_dtype": "bfloat16",
29
+ "use_mrope": false,
30
+ "vocab_size": 156032
31
+ },
32
+ "transformers_version": "4.38.1",
33
+ "vocab_size": 156032
34
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chat_format": "chatml",
3
+ "eos_token_id": [151643,151645],
4
+ "pad_token_id": 151643,
5
+ "do_sample": true,
6
+ "top_k": 0,
7
+ "top_p": 0.01,
8
+ "temperature": 1.0,
9
+ "repetition_penalty": 1.1,
10
+ "transformers_version": "4.38.1"
11
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa8d805dd49408bcbefbd6f701f24e86994c160f09cb614ebac13e7b79a0a04d
3
+ size 3911340848
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ebca32eb045bf5b6a02a4514ae584fed886ba6fc135a59855c23a42c806aa12
3
+ size 3980786080
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e6495fe1a39b47a40b4e148963787bef81d062b3a48d42193f7fe61120f9e7
3
+ size 3980819456
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:698570ad9538a8810511e63ae6e4ee1d50f0c59c00c1df5568032749c31a0110
3
+ size 3643135696
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfa5fbeeb34eef2331b9ea87d802a06f969b5df5827b5f937839d6873f21ec30
3
+ size 1278214288
model.safetensors.index.json ADDED
@@ -0,0 +1,883 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16794189824
4
+ },
5
+ "weight_map": {
6
+ "audio_tower.conv1.bias": "model-00001-of-00005.safetensors",
7
+ "audio_tower.conv1.weight": "model-00001-of-00005.safetensors",
8
+ "audio_tower.conv2.bias": "model-00001-of-00005.safetensors",
9
+ "audio_tower.conv2.weight": "model-00001-of-00005.safetensors",
10
+ "audio_tower.embed_positions.weight": "model-00001-of-00005.safetensors",
11
+ "audio_tower.layer_norm.bias": "model-00001-of-00005.safetensors",
12
+ "audio_tower.layer_norm.weight": "model-00001-of-00005.safetensors",
13
+ "audio_tower.layers.0.fc1.bias": "model-00001-of-00005.safetensors",
14
+ "audio_tower.layers.0.fc1.weight": "model-00001-of-00005.safetensors",
15
+ "audio_tower.layers.0.fc2.bias": "model-00001-of-00005.safetensors",
16
+ "audio_tower.layers.0.fc2.weight": "model-00001-of-00005.safetensors",
17
+ "audio_tower.layers.0.final_layer_norm.bias": "model-00001-of-00005.safetensors",
18
+ "audio_tower.layers.0.final_layer_norm.weight": "model-00001-of-00005.safetensors",
19
+ "audio_tower.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
20
+ "audio_tower.layers.0.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
21
+ "audio_tower.layers.0.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
22
+ "audio_tower.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
23
+ "audio_tower.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
24
+ "audio_tower.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
25
+ "audio_tower.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
26
+ "audio_tower.layers.0.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
27
+ "audio_tower.layers.0.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
28
+ "audio_tower.layers.1.fc1.bias": "model-00001-of-00005.safetensors",
29
+ "audio_tower.layers.1.fc1.weight": "model-00001-of-00005.safetensors",
30
+ "audio_tower.layers.1.fc2.bias": "model-00001-of-00005.safetensors",
31
+ "audio_tower.layers.1.fc2.weight": "model-00001-of-00005.safetensors",
32
+ "audio_tower.layers.1.final_layer_norm.bias": "model-00001-of-00005.safetensors",
33
+ "audio_tower.layers.1.final_layer_norm.weight": "model-00001-of-00005.safetensors",
34
+ "audio_tower.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
35
+ "audio_tower.layers.1.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
36
+ "audio_tower.layers.1.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
37
+ "audio_tower.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
38
+ "audio_tower.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
39
+ "audio_tower.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
40
+ "audio_tower.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
41
+ "audio_tower.layers.1.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
42
+ "audio_tower.layers.1.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
43
+ "audio_tower.layers.10.fc1.bias": "model-00001-of-00005.safetensors",
44
+ "audio_tower.layers.10.fc1.weight": "model-00001-of-00005.safetensors",
45
+ "audio_tower.layers.10.fc2.bias": "model-00001-of-00005.safetensors",
46
+ "audio_tower.layers.10.fc2.weight": "model-00001-of-00005.safetensors",
47
+ "audio_tower.layers.10.final_layer_norm.bias": "model-00001-of-00005.safetensors",
48
+ "audio_tower.layers.10.final_layer_norm.weight": "model-00001-of-00005.safetensors",
49
+ "audio_tower.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
50
+ "audio_tower.layers.10.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
51
+ "audio_tower.layers.10.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
52
+ "audio_tower.layers.10.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
53
+ "audio_tower.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
54
+ "audio_tower.layers.10.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
55
+ "audio_tower.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
56
+ "audio_tower.layers.10.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
57
+ "audio_tower.layers.10.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
58
+ "audio_tower.layers.11.fc1.bias": "model-00001-of-00005.safetensors",
59
+ "audio_tower.layers.11.fc1.weight": "model-00001-of-00005.safetensors",
60
+ "audio_tower.layers.11.fc2.bias": "model-00001-of-00005.safetensors",
61
+ "audio_tower.layers.11.fc2.weight": "model-00001-of-00005.safetensors",
62
+ "audio_tower.layers.11.final_layer_norm.bias": "model-00001-of-00005.safetensors",
63
+ "audio_tower.layers.11.final_layer_norm.weight": "model-00001-of-00005.safetensors",
64
+ "audio_tower.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
65
+ "audio_tower.layers.11.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
66
+ "audio_tower.layers.11.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
67
+ "audio_tower.layers.11.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
68
+ "audio_tower.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
69
+ "audio_tower.layers.11.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
70
+ "audio_tower.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
71
+ "audio_tower.layers.11.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
72
+ "audio_tower.layers.11.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
73
+ "audio_tower.layers.12.fc1.bias": "model-00001-of-00005.safetensors",
74
+ "audio_tower.layers.12.fc1.weight": "model-00001-of-00005.safetensors",
75
+ "audio_tower.layers.12.fc2.bias": "model-00001-of-00005.safetensors",
76
+ "audio_tower.layers.12.fc2.weight": "model-00001-of-00005.safetensors",
77
+ "audio_tower.layers.12.final_layer_norm.bias": "model-00001-of-00005.safetensors",
78
+ "audio_tower.layers.12.final_layer_norm.weight": "model-00001-of-00005.safetensors",
79
+ "audio_tower.layers.12.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
80
+ "audio_tower.layers.12.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
81
+ "audio_tower.layers.12.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
82
+ "audio_tower.layers.12.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
83
+ "audio_tower.layers.12.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
84
+ "audio_tower.layers.12.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
85
+ "audio_tower.layers.12.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
86
+ "audio_tower.layers.12.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
87
+ "audio_tower.layers.12.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
88
+ "audio_tower.layers.13.fc1.bias": "model-00001-of-00005.safetensors",
89
+ "audio_tower.layers.13.fc1.weight": "model-00001-of-00005.safetensors",
90
+ "audio_tower.layers.13.fc2.bias": "model-00001-of-00005.safetensors",
91
+ "audio_tower.layers.13.fc2.weight": "model-00001-of-00005.safetensors",
92
+ "audio_tower.layers.13.final_layer_norm.bias": "model-00001-of-00005.safetensors",
93
+ "audio_tower.layers.13.final_layer_norm.weight": "model-00001-of-00005.safetensors",
94
+ "audio_tower.layers.13.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
95
+ "audio_tower.layers.13.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
96
+ "audio_tower.layers.13.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
97
+ "audio_tower.layers.13.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
98
+ "audio_tower.layers.13.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
99
+ "audio_tower.layers.13.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
100
+ "audio_tower.layers.13.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
101
+ "audio_tower.layers.13.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
102
+ "audio_tower.layers.13.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
103
+ "audio_tower.layers.14.fc1.bias": "model-00001-of-00005.safetensors",
104
+ "audio_tower.layers.14.fc1.weight": "model-00001-of-00005.safetensors",
105
+ "audio_tower.layers.14.fc2.bias": "model-00001-of-00005.safetensors",
106
+ "audio_tower.layers.14.fc2.weight": "model-00001-of-00005.safetensors",
107
+ "audio_tower.layers.14.final_layer_norm.bias": "model-00001-of-00005.safetensors",
108
+ "audio_tower.layers.14.final_layer_norm.weight": "model-00001-of-00005.safetensors",
109
+ "audio_tower.layers.14.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
110
+ "audio_tower.layers.14.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
111
+ "audio_tower.layers.14.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
112
+ "audio_tower.layers.14.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
113
+ "audio_tower.layers.14.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
114
+ "audio_tower.layers.14.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
115
+ "audio_tower.layers.14.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
116
+ "audio_tower.layers.14.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
117
+ "audio_tower.layers.14.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
118
+ "audio_tower.layers.15.fc1.bias": "model-00001-of-00005.safetensors",
119
+ "audio_tower.layers.15.fc1.weight": "model-00001-of-00005.safetensors",
120
+ "audio_tower.layers.15.fc2.bias": "model-00001-of-00005.safetensors",
121
+ "audio_tower.layers.15.fc2.weight": "model-00001-of-00005.safetensors",
122
+ "audio_tower.layers.15.final_layer_norm.bias": "model-00001-of-00005.safetensors",
123
+ "audio_tower.layers.15.final_layer_norm.weight": "model-00001-of-00005.safetensors",
124
+ "audio_tower.layers.15.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
125
+ "audio_tower.layers.15.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
126
+ "audio_tower.layers.15.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
127
+ "audio_tower.layers.15.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
128
+ "audio_tower.layers.15.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
129
+ "audio_tower.layers.15.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
130
+ "audio_tower.layers.15.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
131
+ "audio_tower.layers.15.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
132
+ "audio_tower.layers.15.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
133
+ "audio_tower.layers.16.fc1.bias": "model-00001-of-00005.safetensors",
134
+ "audio_tower.layers.16.fc1.weight": "model-00001-of-00005.safetensors",
135
+ "audio_tower.layers.16.fc2.bias": "model-00001-of-00005.safetensors",
136
+ "audio_tower.layers.16.fc2.weight": "model-00001-of-00005.safetensors",
137
+ "audio_tower.layers.16.final_layer_norm.bias": "model-00001-of-00005.safetensors",
138
+ "audio_tower.layers.16.final_layer_norm.weight": "model-00001-of-00005.safetensors",
139
+ "audio_tower.layers.16.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
140
+ "audio_tower.layers.16.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
141
+ "audio_tower.layers.16.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
142
+ "audio_tower.layers.16.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
143
+ "audio_tower.layers.16.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
144
+ "audio_tower.layers.16.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
145
+ "audio_tower.layers.16.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
146
+ "audio_tower.layers.16.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
147
+ "audio_tower.layers.16.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
148
+ "audio_tower.layers.17.fc1.bias": "model-00001-of-00005.safetensors",
149
+ "audio_tower.layers.17.fc1.weight": "model-00001-of-00005.safetensors",
150
+ "audio_tower.layers.17.fc2.bias": "model-00001-of-00005.safetensors",
151
+ "audio_tower.layers.17.fc2.weight": "model-00001-of-00005.safetensors",
152
+ "audio_tower.layers.17.final_layer_norm.bias": "model-00001-of-00005.safetensors",
153
+ "audio_tower.layers.17.final_layer_norm.weight": "model-00001-of-00005.safetensors",
154
+ "audio_tower.layers.17.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
155
+ "audio_tower.layers.17.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
156
+ "audio_tower.layers.17.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
157
+ "audio_tower.layers.17.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
158
+ "audio_tower.layers.17.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
159
+ "audio_tower.layers.17.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
160
+ "audio_tower.layers.17.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
161
+ "audio_tower.layers.17.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
162
+ "audio_tower.layers.17.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
163
+ "audio_tower.layers.18.fc1.bias": "model-00001-of-00005.safetensors",
164
+ "audio_tower.layers.18.fc1.weight": "model-00001-of-00005.safetensors",
165
+ "audio_tower.layers.18.fc2.bias": "model-00001-of-00005.safetensors",
166
+ "audio_tower.layers.18.fc2.weight": "model-00001-of-00005.safetensors",
167
+ "audio_tower.layers.18.final_layer_norm.bias": "model-00001-of-00005.safetensors",
168
+ "audio_tower.layers.18.final_layer_norm.weight": "model-00001-of-00005.safetensors",
169
+ "audio_tower.layers.18.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
170
+ "audio_tower.layers.18.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
171
+ "audio_tower.layers.18.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
172
+ "audio_tower.layers.18.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
173
+ "audio_tower.layers.18.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
174
+ "audio_tower.layers.18.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
175
+ "audio_tower.layers.18.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
176
+ "audio_tower.layers.18.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
177
+ "audio_tower.layers.18.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
178
+ "audio_tower.layers.19.fc1.bias": "model-00001-of-00005.safetensors",
179
+ "audio_tower.layers.19.fc1.weight": "model-00001-of-00005.safetensors",
180
+ "audio_tower.layers.19.fc2.bias": "model-00001-of-00005.safetensors",
181
+ "audio_tower.layers.19.fc2.weight": "model-00001-of-00005.safetensors",
182
+ "audio_tower.layers.19.final_layer_norm.bias": "model-00001-of-00005.safetensors",
183
+ "audio_tower.layers.19.final_layer_norm.weight": "model-00001-of-00005.safetensors",
184
+ "audio_tower.layers.19.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
185
+ "audio_tower.layers.19.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
186
+ "audio_tower.layers.19.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
187
+ "audio_tower.layers.19.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
188
+ "audio_tower.layers.19.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
189
+ "audio_tower.layers.19.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
190
+ "audio_tower.layers.19.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
191
+ "audio_tower.layers.19.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
192
+ "audio_tower.layers.19.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
193
+ "audio_tower.layers.2.fc1.bias": "model-00001-of-00005.safetensors",
194
+ "audio_tower.layers.2.fc1.weight": "model-00001-of-00005.safetensors",
195
+ "audio_tower.layers.2.fc2.bias": "model-00001-of-00005.safetensors",
196
+ "audio_tower.layers.2.fc2.weight": "model-00001-of-00005.safetensors",
197
+ "audio_tower.layers.2.final_layer_norm.bias": "model-00001-of-00005.safetensors",
198
+ "audio_tower.layers.2.final_layer_norm.weight": "model-00001-of-00005.safetensors",
199
+ "audio_tower.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
200
+ "audio_tower.layers.2.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
201
+ "audio_tower.layers.2.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
202
+ "audio_tower.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
203
+ "audio_tower.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
204
+ "audio_tower.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
205
+ "audio_tower.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
206
+ "audio_tower.layers.2.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
207
+ "audio_tower.layers.2.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
208
+ "audio_tower.layers.20.fc1.bias": "model-00001-of-00005.safetensors",
209
+ "audio_tower.layers.20.fc1.weight": "model-00001-of-00005.safetensors",
210
+ "audio_tower.layers.20.fc2.bias": "model-00001-of-00005.safetensors",
211
+ "audio_tower.layers.20.fc2.weight": "model-00001-of-00005.safetensors",
212
+ "audio_tower.layers.20.final_layer_norm.bias": "model-00001-of-00005.safetensors",
213
+ "audio_tower.layers.20.final_layer_norm.weight": "model-00001-of-00005.safetensors",
214
+ "audio_tower.layers.20.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
215
+ "audio_tower.layers.20.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
216
+ "audio_tower.layers.20.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
217
+ "audio_tower.layers.20.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
218
+ "audio_tower.layers.20.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
219
+ "audio_tower.layers.20.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
220
+ "audio_tower.layers.20.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
221
+ "audio_tower.layers.20.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
222
+ "audio_tower.layers.20.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
223
+ "audio_tower.layers.21.fc1.bias": "model-00001-of-00005.safetensors",
224
+ "audio_tower.layers.21.fc1.weight": "model-00001-of-00005.safetensors",
225
+ "audio_tower.layers.21.fc2.bias": "model-00001-of-00005.safetensors",
226
+ "audio_tower.layers.21.fc2.weight": "model-00001-of-00005.safetensors",
227
+ "audio_tower.layers.21.final_layer_norm.bias": "model-00001-of-00005.safetensors",
228
+ "audio_tower.layers.21.final_layer_norm.weight": "model-00001-of-00005.safetensors",
229
+ "audio_tower.layers.21.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
230
+ "audio_tower.layers.21.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
231
+ "audio_tower.layers.21.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
232
+ "audio_tower.layers.21.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
233
+ "audio_tower.layers.21.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
234
+ "audio_tower.layers.21.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
235
+ "audio_tower.layers.21.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
236
+ "audio_tower.layers.21.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
237
+ "audio_tower.layers.21.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
238
+ "audio_tower.layers.22.fc1.bias": "model-00001-of-00005.safetensors",
239
+ "audio_tower.layers.22.fc1.weight": "model-00001-of-00005.safetensors",
240
+ "audio_tower.layers.22.fc2.bias": "model-00001-of-00005.safetensors",
241
+ "audio_tower.layers.22.fc2.weight": "model-00001-of-00005.safetensors",
242
+ "audio_tower.layers.22.final_layer_norm.bias": "model-00001-of-00005.safetensors",
243
+ "audio_tower.layers.22.final_layer_norm.weight": "model-00001-of-00005.safetensors",
244
+ "audio_tower.layers.22.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
245
+ "audio_tower.layers.22.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
246
+ "audio_tower.layers.22.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
247
+ "audio_tower.layers.22.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
248
+ "audio_tower.layers.22.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
249
+ "audio_tower.layers.22.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
250
+ "audio_tower.layers.22.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
251
+ "audio_tower.layers.22.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
252
+ "audio_tower.layers.22.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
253
+ "audio_tower.layers.23.fc1.bias": "model-00001-of-00005.safetensors",
254
+ "audio_tower.layers.23.fc1.weight": "model-00001-of-00005.safetensors",
255
+ "audio_tower.layers.23.fc2.bias": "model-00001-of-00005.safetensors",
256
+ "audio_tower.layers.23.fc2.weight": "model-00001-of-00005.safetensors",
257
+ "audio_tower.layers.23.final_layer_norm.bias": "model-00001-of-00005.safetensors",
258
+ "audio_tower.layers.23.final_layer_norm.weight": "model-00001-of-00005.safetensors",
259
+ "audio_tower.layers.23.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
260
+ "audio_tower.layers.23.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
261
+ "audio_tower.layers.23.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
262
+ "audio_tower.layers.23.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
263
+ "audio_tower.layers.23.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
264
+ "audio_tower.layers.23.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
265
+ "audio_tower.layers.23.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
266
+ "audio_tower.layers.23.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
267
+ "audio_tower.layers.23.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
268
+ "audio_tower.layers.24.fc1.bias": "model-00001-of-00005.safetensors",
269
+ "audio_tower.layers.24.fc1.weight": "model-00001-of-00005.safetensors",
270
+ "audio_tower.layers.24.fc2.bias": "model-00001-of-00005.safetensors",
271
+ "audio_tower.layers.24.fc2.weight": "model-00001-of-00005.safetensors",
272
+ "audio_tower.layers.24.final_layer_norm.bias": "model-00001-of-00005.safetensors",
273
+ "audio_tower.layers.24.final_layer_norm.weight": "model-00001-of-00005.safetensors",
274
+ "audio_tower.layers.24.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
275
+ "audio_tower.layers.24.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
276
+ "audio_tower.layers.24.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
277
+ "audio_tower.layers.24.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
278
+ "audio_tower.layers.24.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
279
+ "audio_tower.layers.24.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
280
+ "audio_tower.layers.24.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
281
+ "audio_tower.layers.24.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
282
+ "audio_tower.layers.24.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
283
+ "audio_tower.layers.25.fc1.bias": "model-00001-of-00005.safetensors",
284
+ "audio_tower.layers.25.fc1.weight": "model-00001-of-00005.safetensors",
285
+ "audio_tower.layers.25.fc2.bias": "model-00001-of-00005.safetensors",
286
+ "audio_tower.layers.25.fc2.weight": "model-00001-of-00005.safetensors",
287
+ "audio_tower.layers.25.final_layer_norm.bias": "model-00001-of-00005.safetensors",
288
+ "audio_tower.layers.25.final_layer_norm.weight": "model-00001-of-00005.safetensors",
289
+ "audio_tower.layers.25.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
290
+ "audio_tower.layers.25.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
291
+ "audio_tower.layers.25.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
292
+ "audio_tower.layers.25.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
293
+ "audio_tower.layers.25.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
294
+ "audio_tower.layers.25.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
295
+ "audio_tower.layers.25.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
296
+ "audio_tower.layers.25.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
297
+ "audio_tower.layers.25.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
298
+ "audio_tower.layers.26.fc1.bias": "model-00001-of-00005.safetensors",
299
+ "audio_tower.layers.26.fc1.weight": "model-00001-of-00005.safetensors",
300
+ "audio_tower.layers.26.fc2.bias": "model-00001-of-00005.safetensors",
301
+ "audio_tower.layers.26.fc2.weight": "model-00001-of-00005.safetensors",
302
+ "audio_tower.layers.26.final_layer_norm.bias": "model-00001-of-00005.safetensors",
303
+ "audio_tower.layers.26.final_layer_norm.weight": "model-00001-of-00005.safetensors",
304
+ "audio_tower.layers.26.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
305
+ "audio_tower.layers.26.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
306
+ "audio_tower.layers.26.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
307
+ "audio_tower.layers.26.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
308
+ "audio_tower.layers.26.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
309
+ "audio_tower.layers.26.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
310
+ "audio_tower.layers.26.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
311
+ "audio_tower.layers.26.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
312
+ "audio_tower.layers.26.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
313
+ "audio_tower.layers.27.fc1.bias": "model-00001-of-00005.safetensors",
314
+ "audio_tower.layers.27.fc1.weight": "model-00001-of-00005.safetensors",
315
+ "audio_tower.layers.27.fc2.bias": "model-00001-of-00005.safetensors",
316
+ "audio_tower.layers.27.fc2.weight": "model-00001-of-00005.safetensors",
317
+ "audio_tower.layers.27.final_layer_norm.bias": "model-00001-of-00005.safetensors",
318
+ "audio_tower.layers.27.final_layer_norm.weight": "model-00001-of-00005.safetensors",
319
+ "audio_tower.layers.27.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
320
+ "audio_tower.layers.27.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
321
+ "audio_tower.layers.27.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
322
+ "audio_tower.layers.27.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
323
+ "audio_tower.layers.27.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
324
+ "audio_tower.layers.27.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
325
+ "audio_tower.layers.27.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
326
+ "audio_tower.layers.27.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
327
+ "audio_tower.layers.27.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
328
+ "audio_tower.layers.28.fc1.bias": "model-00001-of-00005.safetensors",
329
+ "audio_tower.layers.28.fc1.weight": "model-00001-of-00005.safetensors",
330
+ "audio_tower.layers.28.fc2.bias": "model-00001-of-00005.safetensors",
331
+ "audio_tower.layers.28.fc2.weight": "model-00001-of-00005.safetensors",
332
+ "audio_tower.layers.28.final_layer_norm.bias": "model-00001-of-00005.safetensors",
333
+ "audio_tower.layers.28.final_layer_norm.weight": "model-00001-of-00005.safetensors",
334
+ "audio_tower.layers.28.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
335
+ "audio_tower.layers.28.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
336
+ "audio_tower.layers.28.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
337
+ "audio_tower.layers.28.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
338
+ "audio_tower.layers.28.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
339
+ "audio_tower.layers.28.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
340
+ "audio_tower.layers.28.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
341
+ "audio_tower.layers.28.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
342
+ "audio_tower.layers.28.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
343
+ "audio_tower.layers.29.fc1.bias": "model-00001-of-00005.safetensors",
344
+ "audio_tower.layers.29.fc1.weight": "model-00001-of-00005.safetensors",
345
+ "audio_tower.layers.29.fc2.bias": "model-00001-of-00005.safetensors",
346
+ "audio_tower.layers.29.fc2.weight": "model-00001-of-00005.safetensors",
347
+ "audio_tower.layers.29.final_layer_norm.bias": "model-00001-of-00005.safetensors",
348
+ "audio_tower.layers.29.final_layer_norm.weight": "model-00001-of-00005.safetensors",
349
+ "audio_tower.layers.29.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
350
+ "audio_tower.layers.29.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
351
+ "audio_tower.layers.29.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
352
+ "audio_tower.layers.29.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
353
+ "audio_tower.layers.29.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
354
+ "audio_tower.layers.29.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
355
+ "audio_tower.layers.29.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
356
+ "audio_tower.layers.29.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
357
+ "audio_tower.layers.29.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
358
+ "audio_tower.layers.3.fc1.bias": "model-00001-of-00005.safetensors",
359
+ "audio_tower.layers.3.fc1.weight": "model-00001-of-00005.safetensors",
360
+ "audio_tower.layers.3.fc2.bias": "model-00001-of-00005.safetensors",
361
+ "audio_tower.layers.3.fc2.weight": "model-00001-of-00005.safetensors",
362
+ "audio_tower.layers.3.final_layer_norm.bias": "model-00001-of-00005.safetensors",
363
+ "audio_tower.layers.3.final_layer_norm.weight": "model-00001-of-00005.safetensors",
364
+ "audio_tower.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
365
+ "audio_tower.layers.3.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
366
+ "audio_tower.layers.3.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
367
+ "audio_tower.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
368
+ "audio_tower.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
369
+ "audio_tower.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
370
+ "audio_tower.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
371
+ "audio_tower.layers.3.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
372
+ "audio_tower.layers.3.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
373
+ "audio_tower.layers.30.fc1.bias": "model-00001-of-00005.safetensors",
374
+ "audio_tower.layers.30.fc1.weight": "model-00001-of-00005.safetensors",
375
+ "audio_tower.layers.30.fc2.bias": "model-00001-of-00005.safetensors",
376
+ "audio_tower.layers.30.fc2.weight": "model-00001-of-00005.safetensors",
377
+ "audio_tower.layers.30.final_layer_norm.bias": "model-00001-of-00005.safetensors",
378
+ "audio_tower.layers.30.final_layer_norm.weight": "model-00001-of-00005.safetensors",
379
+ "audio_tower.layers.30.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
380
+ "audio_tower.layers.30.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
381
+ "audio_tower.layers.30.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
382
+ "audio_tower.layers.30.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
383
+ "audio_tower.layers.30.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
384
+ "audio_tower.layers.30.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
385
+ "audio_tower.layers.30.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
386
+ "audio_tower.layers.30.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
387
+ "audio_tower.layers.30.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
388
+ "audio_tower.layers.31.fc1.bias": "model-00001-of-00005.safetensors",
389
+ "audio_tower.layers.31.fc1.weight": "model-00001-of-00005.safetensors",
390
+ "audio_tower.layers.31.fc2.bias": "model-00001-of-00005.safetensors",
391
+ "audio_tower.layers.31.fc2.weight": "model-00001-of-00005.safetensors",
392
+ "audio_tower.layers.31.final_layer_norm.bias": "model-00001-of-00005.safetensors",
393
+ "audio_tower.layers.31.final_layer_norm.weight": "model-00001-of-00005.safetensors",
394
+ "audio_tower.layers.31.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
395
+ "audio_tower.layers.31.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
396
+ "audio_tower.layers.31.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
397
+ "audio_tower.layers.31.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
398
+ "audio_tower.layers.31.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
399
+ "audio_tower.layers.31.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
400
+ "audio_tower.layers.31.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
401
+ "audio_tower.layers.31.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
402
+ "audio_tower.layers.31.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
403
+ "audio_tower.layers.4.fc1.bias": "model-00001-of-00005.safetensors",
404
+ "audio_tower.layers.4.fc1.weight": "model-00001-of-00005.safetensors",
405
+ "audio_tower.layers.4.fc2.bias": "model-00001-of-00005.safetensors",
406
+ "audio_tower.layers.4.fc2.weight": "model-00001-of-00005.safetensors",
407
+ "audio_tower.layers.4.final_layer_norm.bias": "model-00001-of-00005.safetensors",
408
+ "audio_tower.layers.4.final_layer_norm.weight": "model-00001-of-00005.safetensors",
409
+ "audio_tower.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
410
+ "audio_tower.layers.4.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
411
+ "audio_tower.layers.4.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
412
+ "audio_tower.layers.4.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
413
+ "audio_tower.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
414
+ "audio_tower.layers.4.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
415
+ "audio_tower.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
416
+ "audio_tower.layers.4.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
417
+ "audio_tower.layers.4.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
418
+ "audio_tower.layers.5.fc1.bias": "model-00001-of-00005.safetensors",
419
+ "audio_tower.layers.5.fc1.weight": "model-00001-of-00005.safetensors",
420
+ "audio_tower.layers.5.fc2.bias": "model-00001-of-00005.safetensors",
421
+ "audio_tower.layers.5.fc2.weight": "model-00001-of-00005.safetensors",
422
+ "audio_tower.layers.5.final_layer_norm.bias": "model-00001-of-00005.safetensors",
423
+ "audio_tower.layers.5.final_layer_norm.weight": "model-00001-of-00005.safetensors",
424
+ "audio_tower.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
425
+ "audio_tower.layers.5.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
426
+ "audio_tower.layers.5.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
427
+ "audio_tower.layers.5.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
428
+ "audio_tower.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
429
+ "audio_tower.layers.5.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
430
+ "audio_tower.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
431
+ "audio_tower.layers.5.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
432
+ "audio_tower.layers.5.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
433
+ "audio_tower.layers.6.fc1.bias": "model-00001-of-00005.safetensors",
434
+ "audio_tower.layers.6.fc1.weight": "model-00001-of-00005.safetensors",
435
+ "audio_tower.layers.6.fc2.bias": "model-00001-of-00005.safetensors",
436
+ "audio_tower.layers.6.fc2.weight": "model-00001-of-00005.safetensors",
437
+ "audio_tower.layers.6.final_layer_norm.bias": "model-00001-of-00005.safetensors",
438
+ "audio_tower.layers.6.final_layer_norm.weight": "model-00001-of-00005.safetensors",
439
+ "audio_tower.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
440
+ "audio_tower.layers.6.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
441
+ "audio_tower.layers.6.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
442
+ "audio_tower.layers.6.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
443
+ "audio_tower.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
444
+ "audio_tower.layers.6.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
445
+ "audio_tower.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
446
+ "audio_tower.layers.6.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
447
+ "audio_tower.layers.6.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
448
+ "audio_tower.layers.7.fc1.bias": "model-00001-of-00005.safetensors",
449
+ "audio_tower.layers.7.fc1.weight": "model-00001-of-00005.safetensors",
450
+ "audio_tower.layers.7.fc2.bias": "model-00001-of-00005.safetensors",
451
+ "audio_tower.layers.7.fc2.weight": "model-00001-of-00005.safetensors",
452
+ "audio_tower.layers.7.final_layer_norm.bias": "model-00001-of-00005.safetensors",
453
+ "audio_tower.layers.7.final_layer_norm.weight": "model-00001-of-00005.safetensors",
454
+ "audio_tower.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
455
+ "audio_tower.layers.7.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
456
+ "audio_tower.layers.7.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
457
+ "audio_tower.layers.7.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
458
+ "audio_tower.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
459
+ "audio_tower.layers.7.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
460
+ "audio_tower.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
461
+ "audio_tower.layers.7.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
462
+ "audio_tower.layers.7.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
463
+ "audio_tower.layers.8.fc1.bias": "model-00001-of-00005.safetensors",
464
+ "audio_tower.layers.8.fc1.weight": "model-00001-of-00005.safetensors",
465
+ "audio_tower.layers.8.fc2.bias": "model-00001-of-00005.safetensors",
466
+ "audio_tower.layers.8.fc2.weight": "model-00001-of-00005.safetensors",
467
+ "audio_tower.layers.8.final_layer_norm.bias": "model-00001-of-00005.safetensors",
468
+ "audio_tower.layers.8.final_layer_norm.weight": "model-00001-of-00005.safetensors",
469
+ "audio_tower.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
470
+ "audio_tower.layers.8.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
471
+ "audio_tower.layers.8.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
472
+ "audio_tower.layers.8.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
473
+ "audio_tower.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
474
+ "audio_tower.layers.8.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
475
+ "audio_tower.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
476
+ "audio_tower.layers.8.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
477
+ "audio_tower.layers.8.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
478
+ "audio_tower.layers.9.fc1.bias": "model-00001-of-00005.safetensors",
479
+ "audio_tower.layers.9.fc1.weight": "model-00001-of-00005.safetensors",
480
+ "audio_tower.layers.9.fc2.bias": "model-00001-of-00005.safetensors",
481
+ "audio_tower.layers.9.fc2.weight": "model-00001-of-00005.safetensors",
482
+ "audio_tower.layers.9.final_layer_norm.bias": "model-00001-of-00005.safetensors",
483
+ "audio_tower.layers.9.final_layer_norm.weight": "model-00001-of-00005.safetensors",
484
+ "audio_tower.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
485
+ "audio_tower.layers.9.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
486
+ "audio_tower.layers.9.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
487
+ "audio_tower.layers.9.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
488
+ "audio_tower.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
489
+ "audio_tower.layers.9.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
490
+ "audio_tower.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
491
+ "audio_tower.layers.9.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
492
+ "audio_tower.layers.9.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
493
+ "language_model.lm_head.weight": "model-00005-of-00005.safetensors",
494
+ "language_model.model.embed_tokens.weight": "model-00001-of-00005.safetensors",
495
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
496
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
497
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
498
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
499
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
500
+ "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
501
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
502
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
503
+ "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
504
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
505
+ "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
506
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
507
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
508
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
509
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
510
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
511
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
512
+ "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
513
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
514
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
515
+ "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
516
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
517
+ "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
518
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
519
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
520
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
521
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
522
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
523
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
524
+ "language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
525
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
526
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
527
+ "language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
528
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
529
+ "language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
530
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
531
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
532
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
533
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
534
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
535
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
536
+ "language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
537
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
538
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
539
+ "language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
540
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
541
+ "language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
542
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
543
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
544
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
545
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
546
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
547
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
548
+ "language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
549
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
550
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
551
+ "language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
552
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
553
+ "language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
554
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
555
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
556
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
557
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
558
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
559
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
560
+ "language_model.model.layers.13.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
561
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
562
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
563
+ "language_model.model.layers.13.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
564
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
565
+ "language_model.model.layers.13.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
566
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
567
+ "language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
568
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
569
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
570
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
571
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
572
+ "language_model.model.layers.14.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
573
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
574
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
575
+ "language_model.model.layers.14.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
576
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
577
+ "language_model.model.layers.14.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
578
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
579
+ "language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
580
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
581
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
582
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
583
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
584
+ "language_model.model.layers.15.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
585
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
586
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
587
+ "language_model.model.layers.15.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
588
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
589
+ "language_model.model.layers.15.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
590
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
591
+ "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
592
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
593
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
594
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
595
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
596
+ "language_model.model.layers.16.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
597
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
598
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
599
+ "language_model.model.layers.16.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
600
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
601
+ "language_model.model.layers.16.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
602
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
603
+ "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
604
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
605
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
606
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
607
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
608
+ "language_model.model.layers.17.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
609
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
610
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
611
+ "language_model.model.layers.17.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
612
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
613
+ "language_model.model.layers.17.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
614
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
615
+ "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
616
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
617
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
618
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
619
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
620
+ "language_model.model.layers.18.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
621
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
622
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
623
+ "language_model.model.layers.18.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
624
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
625
+ "language_model.model.layers.18.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
626
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
627
+ "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
628
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
629
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
630
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
631
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
632
+ "language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
633
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
634
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
635
+ "language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
636
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
637
+ "language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
638
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
639
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
640
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
641
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
642
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
643
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
644
+ "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
645
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
646
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
647
+ "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
648
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
649
+ "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
650
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
651
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
652
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
653
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
654
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
655
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
656
+ "language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
657
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
658
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
659
+ "language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
660
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
661
+ "language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
662
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
663
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
664
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
665
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
666
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
667
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
668
+ "language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
669
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
670
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
671
+ "language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
672
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
673
+ "language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
674
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
675
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
676
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
677
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
678
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
679
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
680
+ "language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
681
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
682
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
683
+ "language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
684
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
685
+ "language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
686
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
687
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
688
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
689
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
690
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
691
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
692
+ "language_model.model.layers.23.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
693
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
694
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
695
+ "language_model.model.layers.23.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
696
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
697
+ "language_model.model.layers.23.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
698
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
699
+ "language_model.model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
700
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
701
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
702
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
703
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
704
+ "language_model.model.layers.24.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
705
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
706
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
707
+ "language_model.model.layers.24.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
708
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
709
+ "language_model.model.layers.24.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
710
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
711
+ "language_model.model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
712
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
713
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
714
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
715
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
716
+ "language_model.model.layers.25.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
717
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
718
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
719
+ "language_model.model.layers.25.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
720
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
721
+ "language_model.model.layers.25.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
722
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
723
+ "language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
724
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
725
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
726
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
727
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
728
+ "language_model.model.layers.26.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
729
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
730
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
731
+ "language_model.model.layers.26.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
732
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
733
+ "language_model.model.layers.26.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
734
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
735
+ "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
736
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
737
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
738
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
739
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
740
+ "language_model.model.layers.27.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
741
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
742
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
743
+ "language_model.model.layers.27.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
744
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
745
+ "language_model.model.layers.27.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
746
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
747
+ "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
748
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
749
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
750
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
751
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
752
+ "language_model.model.layers.28.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
753
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
754
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
755
+ "language_model.model.layers.28.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
756
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
757
+ "language_model.model.layers.28.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
758
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
759
+ "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
760
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
761
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
762
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
763
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
764
+ "language_model.model.layers.29.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
765
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
766
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
767
+ "language_model.model.layers.29.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
768
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
769
+ "language_model.model.layers.29.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
770
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
771
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
772
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
773
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
774
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
775
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
776
+ "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
777
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
778
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
779
+ "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
780
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
781
+ "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
782
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
783
+ "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
784
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
785
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
786
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
787
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
788
+ "language_model.model.layers.30.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
789
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
790
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
791
+ "language_model.model.layers.30.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
792
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
793
+ "language_model.model.layers.30.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
794
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
795
+ "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
796
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
797
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
798
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
799
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
800
+ "language_model.model.layers.31.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
801
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
802
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
803
+ "language_model.model.layers.31.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
804
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
805
+ "language_model.model.layers.31.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
806
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
807
+ "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors",
808
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
809
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
810
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
811
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
812
+ "language_model.model.layers.4.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
813
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
814
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
815
+ "language_model.model.layers.4.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
816
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
817
+ "language_model.model.layers.4.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
818
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
819
+ "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
820
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
821
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
822
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
823
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
824
+ "language_model.model.layers.5.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
825
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
826
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
827
+ "language_model.model.layers.5.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
828
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
829
+ "language_model.model.layers.5.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
830
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
831
+ "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
832
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
833
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
834
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
835
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
836
+ "language_model.model.layers.6.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
837
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
838
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
839
+ "language_model.model.layers.6.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
840
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
841
+ "language_model.model.layers.6.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
842
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
843
+ "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
844
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
845
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
846
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
847
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
848
+ "language_model.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
849
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
850
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
851
+ "language_model.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
852
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
853
+ "language_model.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
854
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
855
+ "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
856
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
857
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
858
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
859
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
860
+ "language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
861
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
862
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
863
+ "language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
864
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
865
+ "language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
866
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
867
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
868
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
869
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
870
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
871
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
872
+ "language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
873
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
874
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
875
+ "language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
876
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
877
+ "language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
878
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
879
+ "language_model.model.norm.weight": "model-00004-of-00005.safetensors",
880
+ "multi_modal_projector.linear.bias": "model-00001-of-00005.safetensors",
881
+ "multi_modal_projector.linear.weight": "model-00001-of-00005.safetensors"
882
+ }
883
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 128,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "Qwen2AudioProcessor",
12
+ "return_attention_mask": true,
13
+ "sampling_rate": 16000
14
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff