初始化项目，由ModelHub XC社区提供模型
Model: meituan/ATT-ModelEval Source: Original Platform
This commit is contained in:
ModelHub XC
52
.gitattributes
vendored
Normal file
52
.gitattributes
vendored
Normal file
@@ -0,0 +1,52 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
9
README.md
Normal file
9
README.md
Normal file
@@ -0,0 +1,9 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
metrics:
|
||||
- mse
|
||||
---
|
||||
|
||||
# Automatically Evaluating the Human-likeness of TTS Systems via Audio-LLM-Based Score Regression
|
||||
|
||||
Lora finetuned on [Qwen2-Audio](https://huggingface.co/Qwen/Qwen2-Audio-7B).
|
||||
3290
added_tokens.json
Normal file
3290
added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
3
chat_template.json
Normal file
3
chat_template.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"chat_template": "{% set audio_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if 'audio' in content or 'audio_url' in content %}{% set audio_count.value = audio_count.value + 1 %}Audio {{ audio_count.value }}: <|audio_bos|><|AUDIO|><|audio_eos|>\n{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
||||
}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"_name_or_path": "/mnt/dolphinfs/hdd_pool/docker/user/hadoop-aipnlp/EVA/lishuailin/qwen-audio-sft/Qwen2-Audio-7B-Instruct",
|
||||
"architectures": [
|
||||
"Qwen2AudioForConditionalGeneration"
|
||||
],
|
||||
"audio_config": {
|
||||
"model_type": "qwen2_audio_encoder"
|
||||
},
|
||||
"audio_token_index": 151646,
|
||||
"hidden_size": 4096,
|
||||
"ignore_index": -100,
|
||||
"keys_to_ignore_at_inference": [
|
||||
"past_key_values"
|
||||
],
|
||||
"model_type": "qwen2_audio",
|
||||
"text_config": {
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 8192,
|
||||
"model_type": "qwen2",
|
||||
"rms_norm_eps": 1e-05,
|
||||
"torch_dtype": "bfloat16",
|
||||
"use_mrope": false,
|
||||
"vocab_size": 156032
|
||||
},
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.46.3",
|
||||
"vocab_size": 156032
|
||||
}
|
||||
4
configuration.json
Normal file
4
configuration.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"framework": "Pytorch",
|
||||
"task": "text-generation"
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"chat_format": "chatml",
|
||||
"do_sample": true,
|
||||
"eos_token_id": 151645,
|
||||
"max_new_tokens": 2048,
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.1,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.5,
|
||||
"transformers_version": "4.46.3"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:18e3a45f83cfb40f9f087cd602a6f3aeadcf19d7eec6290769276ba0009c28f6
|
||||
size 4991459544
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:708aadbf86a7d88aa7707db8e98455dd8a1095ca5fdf03beb6d5825c99727177
|
||||
size 4991757456
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:24777ca294c7f48afc1aa94bfd94a014736f7ea8295619e3a9d22e31d0a1fbe8
|
||||
size 4947691960
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:849d5fea3d01e3efd218aae0695f76a31e53f6e05e57fe81f1009752e7d04b94
|
||||
size 1863387424
|
||||
883
model.safetensors.index.json
Normal file
883
model.safetensors.index.json
Normal file
@@ -0,0 +1,883 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16794189824
|
||||
},
|
||||
"weight_map": {
|
||||
"audio_tower.conv1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.conv1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.conv2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.conv2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.embed_positions.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.0.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.1.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.10.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.11.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.12.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.13.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.14.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.15.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.16.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.17.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.18.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.19.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.2.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.20.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.21.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.22.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.23.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.24.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.25.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.26.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.27.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.28.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.29.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.3.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.30.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.31.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.4.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.5.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.6.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.7.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.8.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.fc1.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.fc1.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.fc2.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.fc2.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.final_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.final_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors",
|
||||
"audio_tower.layers.9.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"language_model.model.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"multi_modal_projector.linear.bias": "model-00001-of-00004.safetensors",
|
||||
"multi_modal_projector.linear.weight": "model-00001-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
14
preprocessor_config.json
Normal file
14
preprocessor_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"chunk_length": 30,
|
||||
"feature_extractor_type": "WhisperFeatureExtractor",
|
||||
"feature_size": 128,
|
||||
"hop_length": 160,
|
||||
"n_fft": 400,
|
||||
"n_samples": 480000,
|
||||
"nb_max_frames": 3000,
|
||||
"padding_side": "right",
|
||||
"padding_value": 0.0,
|
||||
"processor_class": "Qwen2AudioProcessor",
|
||||
"return_attention_mask": true,
|
||||
"sampling_rate": 16000
|
||||
}
|
||||
3305
special_tokens_map.json
Normal file
3305
special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
|
||||
size 12030779
|
||||
29609
tokenizer_config.json
Normal file
29609
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user