transformers-integration (#16)

- transformers weights (85153c4fdd79bb498579b8e155604858b2c68835)
- readme update (af8713bb935454562c2acd83a9bb06adbc76a386)
- readme update (b922b530e498fadf4d97867383447b5b87d04dfe)
- add transformers tag (8a73a4e5c52aad6eabc8a7c6f75206d03828378d)
- Update README.md (e1891876d09409f64087173ea6348cd83bf45436)


Co-authored-by: Eustache Le Bihan <[email protected]>

README.md

@@ -15,6 +15,8 @@ extra_gated_description: >-
   If you want to learn more about how we process your personal data, please read
   our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
 pipeline_tag: audio-text-to-text
+tags:
+- transformers
 ---
 # Voxtral Mini 1.0 (3B) - 2507
 
@@ -48,6 +50,7 @@ Average word error rate (WER) over the FLEURS, Mozilla Common Voice and Multilin
 
 The model can be used with the following frameworks;
 - [`vllm (recommended)`](https://github.com/vllm-project/vllm): See [here](#vllm-recommended)
+- [`Transformers` 🤗](https://github.com/huggingface/transformers): See [here](#transformers-🤗)
 
 **Notes**:
 
@@ -235,4 +238,290 @@ req = TranscriptionRequest(model=model, audio=audio, language="en", temperature=
 response = client.audio.transcriptions.create(**req)
 print(response)
 ```
+</details>
+
+### Transformers 🤗
+
+Voxtral is supported in Transformers natively!
+
+Install Transformers from source:
+```bash
+pip install git+https://github.com/huggingface/transformers
+```
+
+Make sure to have `mistral-common >= 1.8.1` installed with audio dependencies:
+```bash
+pip install --upgrade "mistral-common[audio]"
+```
+
+#### Audio Instruct
+
+<details>
+  <summary>➡️ multi-audio + text instruction</summary>
+
+```python
+from transformers import VoxtralForConditionalGeneration, AutoProcessor
+import torch
+
+device = "cuda"
+repo_id = "mistralai/Voxtral-Mini-3B-2507"
+
+processor = AutoProcessor.from_pretrained(repo_id)
+model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
+
+conversation = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "audio",
+                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/mary_had_lamb.mp3",
+            },
+            {
+                "type": "audio",
+                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
+            },
+            {"type": "text", "text": "What sport and what nursery rhyme are referenced?"},
+        ],
+    }
+]
+
+inputs = processor.apply_chat_template(conversation)
+inputs = inputs.to(device, dtype=torch.bfloat16)
+
+outputs = model.generate(**inputs, max_new_tokens=500)
+decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
+
+print("\nGenerated response:")
+print("=" * 80)
+print(decoded_outputs[0])
+print("=" * 80)
+```
+</details>
+
+
+<details>
+  <summary>➡️ multi-turn</summary>
+
+```python
+from transformers import VoxtralForConditionalGeneration, AutoProcessor
+import torch
+
+device = "cuda"
+repo_id = "mistralai/Voxtral-Mini-3B-2507"
+
+processor = AutoProcessor.from_pretrained(repo_id)
+model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
+
+conversation = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "audio",
+                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3",
+            },
+            {
+                "type": "audio",
+                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3",
+            },
+            {"type": "text", "text": "Describe briefly what you can hear."},
+        ],
+    },
+    {
+        "role": "assistant",
+        "content": "The audio begins with the speaker delivering a farewell address in Chicago, reflecting on his eight years as president and expressing gratitude to the American people. The audio then transitions to a weather report, stating that it was 35 degrees in Barcelona the previous day, but the temperature would drop to minus 20 degrees the following day.",
+    },
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "audio",
+                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
+            },
+            {"type": "text", "text": "Ok, now compare this new audio with the previous one."},
+        ],
+    },
+]
+
+inputs = processor.apply_chat_template(conversation)
+inputs = inputs.to(device, dtype=torch.bfloat16)
+
+outputs = model.generate(**inputs, max_new_tokens=500)
+decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
+
+print("\nGenerated response:")
+print("=" * 80)
+print(decoded_outputs[0])
+print("=" * 80)
+```
+</details>
+
+
+<details>
+  <summary>➡️ text only</summary>
+
+```python
+from transformers import VoxtralForConditionalGeneration, AutoProcessor
+import torch
+
+device = "cuda"
+repo_id = "mistralai/Voxtral-Mini-3B-2507"
+
+processor = AutoProcessor.from_pretrained(repo_id)
+model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
+
+conversation = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "text",
+                "text": "Why should AI models be open-sourced?",
+            },
+        ],
+    }
+]
+
+inputs = processor.apply_chat_template(conversation)
+inputs = inputs.to(device, dtype=torch.bfloat16)
+
+outputs = model.generate(**inputs, max_new_tokens=500)
+decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
+
+print("\nGenerated response:")
+print("=" * 80)
+print(decoded_outputs[0])
+print("=" * 80)
+```
+</details>
+
+
+<details>
+  <summary>➡️ audio only</summary>
+
+```python
+from transformers import VoxtralForConditionalGeneration, AutoProcessor
+import torch
+
+device = "cuda"
+repo_id = "mistralai/Voxtral-Mini-3B-2507"
+
+processor = AutoProcessor.from_pretrained(repo_id)
+model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
+
+conversation = [
+    {
+        "role": "user",
+        "content": [
+            {
+                "type": "audio",
+                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
+            },
+        ],
+    }
+]
+
+inputs = processor.apply_chat_template(conversation)
+inputs = inputs.to(device, dtype=torch.bfloat16)
+
+outputs = model.generate(**inputs, max_new_tokens=500)
+decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
+
+print("\nGenerated response:")
+print("=" * 80)
+print(decoded_outputs[0])
+print("=" * 80)
+```
+</details>
+
+
+<details>
+  <summary>➡️ batched inference</summary>
+
+```python
+from transformers import VoxtralForConditionalGeneration, AutoProcessor
+import torch
+
+device = "cuda"
+repo_id = "mistralai/Voxtral-Mini-3B-2507"
+
+processor = AutoProcessor.from_pretrained(repo_id)
+model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
+
+conversations = [
+    [
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "audio",
+                    "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3",
+                },
+                {
+                    "type": "audio",
+                    "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3",
+                },
+                {
+                    "type": "text",
+                    "text": "Who's speaking in the speach and what city's weather is being discussed?",
+                },
+            ],
+        }
+    ],
+    [
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "audio",
+                    "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
+                },
+                {"type": "text", "text": "What can you tell me about this audio?"},
+            ],
+        }
+    ],
+]
+
+inputs = processor.apply_chat_template(conversations)
+inputs = inputs.to(device, dtype=torch.bfloat16)
+
+outputs = model.generate(**inputs, max_new_tokens=500)
+decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
+
+print("\nGenerated responses:")
+print("=" * 80)
+for decoded_output in decoded_outputs:
+    print(decoded_output)
+    print("=" * 80)
+```
+</details>
+
+#### Transcription
+
+<details>
+  <summary>➡️ transcribe</summary>
+
+```python
+from transformers import VoxtralForConditionalGeneration, AutoProcessor
+import torch
+
+device = "cuda"
+repo_id = "mistralai/Voxtral-Mini-3B-2507"
+
+processor = AutoProcessor.from_pretrained(repo_id)
+model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
+
+inputs = processor.apply_transcrition_request(language="en", audio="https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3", model_id=repo_id)
+inputs = inputs.to(device, dtype=torch.bfloat16)
+
+outputs = model.generate(**inputs, max_new_tokens=500)
+decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)
+
+print("\nGenerated responses:")
+print("=" * 80)
+for decoded_output in decoded_outputs:
+    print(decoded_output)
+    print("=" * 80)
+```
 </details>

config.json

@@ -0,0 +1,53 @@
+{
+  "architectures": [
+    "VoxtralForConditionalGeneration"
+  ],
+  "audio_config": {
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "head_dim": 64,
+    "hidden_size": 1280,
+    "initializer_range": 0.02,
+    "intermediate_size": 5120,
+    "layerdrop": 0.0,
+    "max_source_positions": 1500,
+    "model_type": "voxtral_encoder",
+    "num_attention_heads": 20,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 20,
+    "num_mel_bins": 128,
+    "scale_embedding": false,
+    "vocab_size": 51866
+  },
+  "audio_token_id": 24,
+  "hidden_size": 3072,
+  "model_type": "voxtral",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 3072,
+    "initializer_range": 0.02,
+    "intermediate_size": 8192,
+    "max_position_embeddings": 131072,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 30,
+    "num_key_value_heads": 8,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 100000000.0,
+    "sliding_window": null,
+    "use_cache": true,
+    "vocab_size": 131072
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.54.0.dev0",
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 11,
+  "transformers_version": "4.54.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1facdc4c5a0e84f2881a59c4756441b7030a1f1036b2124c117540408d0e5fe9
+size 4977385976

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a103ba715bc0d656e94bf79d637d4f8f0f4fe6d76fb1d4db7ee46c6b940f631
+size 4379088336

model.safetensors.index.json

@@ -0,0 +1,770 @@
+{
+  "metadata": {
+    "total_parameters": 4676271104,
+    "total_size": 9356382208
+  },
+  "weight_map": {
+    "audio_tower.conv1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.conv1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.conv2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.conv2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.embed_positions.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.30.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.31.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "audio_tower.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.lm_head.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00002-of-00002.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00002-of-00002.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,15 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "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": "VoxtralProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}