Template Readme

README.md

@@ -1,5 +1,4 @@
 ---
-library_name: vllm
 language:
 - en
 - fr
@@ -10,59 +9,56 @@ language:
 - nl
 - hi
 license: apache-2.0
+library_name: vllm
 inference: false
 base_model:
 - mistralai/Mistral-Small-24B-Base-2501
 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>.
-tags:
-- vllm
 pipeline_tag: audio-text-to-text
 ---
 
-# Voxtral Small 1.0 (24B) - 2507
+# Voxtral Small 24B-2507
+
+Voxtral Small is an enhancement of [Mistral Small 3](https://huggingface.co/mistralai/Mistral-Small-24B-Base-2501), incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription and understanding.
 
-Voxtral Small is an enhancement of [Mistral Small 3](https://huggingface.co/mistralai/Mistral-Small-24B-Base-2501), incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.
+Learn more about Voxtral in our blog post [here](https://mistral.ai/news/voxtral-2507).
+
+Both Voxtral models go beyond transcription with capabilities that include:
 
-Learn more about Voxtral in our blog post [here](https://mistral.ai/news/voxtral) and our [research paper](https://arxiv.org/abs/2507.13264).
 
 ## Key Features
 
 Voxtral builds upon Mistral Small 3 with powerful audio understanding capabilities.
-- **Dedicated transcription mode**: Voxtral can operate in a pure speech transcription mode to maximize performance. By default, Voxtral automatically predicts the source audio language and transcribes the text accordingly
-- **Long-form context**: With a 32k token context length, Voxtral handles audios up to 30 minutes for transcription, or 40 minutes for understanding
-- **Built-in Q&A and summarization**: Supports asking questions directly through audio. Analyze audio and generate structured summaries without the need for separate ASR and language models
-- **Natively multilingual**: Automatic language detection and state-of-the-art performance in the world’s most widely used languages (English, Spanish, French, Portuguese, Hindi, German, Dutch, Italian)
-- **Function-calling straight from voice**: Enables direct triggering of backend functions, workflows, or API calls based on spoken user intents
-- **Highly capable at text**: Retains the text understanding capabilities of its language model backbone, Mistral Small 3.1
+- **Long-form context**: with a 32k token context length, Voxtral handles audios up to 30 minutes for transcription, or 40 minutes for understanding 
+- **Built-in Q&A and summarization**: Supports asking questions directly about the audio content or generating structured summaries, without the need to chain separate ASR and language models
+- **Natively multilingual**: Automatic language detection and state-of-the-art performance in the world’s most widely used languages (English, Spanish, French, Portuguese, Hindi, German, Dutch, Italian, to name a few), helping teams serve global audiences with a single system
+- **Function-calling straight from voice**: Enables direct triggering of backend functions, workflows, or API calls based on spoken user intents, turning voice interactions into actionable system commands without intermediate parsing steps.
+- **Highly capable at text**: Retains the text understanding capabilities of its language model backbone, Mistral Small 3
 
 ## Benchmark Results
 
 ### Audio
 
-Average word error rate (WER) over the FLEURS, Mozilla Common Voice and Multilingual LibriSpeech benchmarks:
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64161701107962562e9b1006/FKBy7KZAoTR52A_ht-ZpL.png)
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/64161701107962562e9b1006/puASxtajF1lDeGYPrRK5y.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64161701107962562e9b1006/-DcHsAjwuY6kbduC5XBH2.png)
 
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64161701107962562e9b1006/7tJgqCPczuJZ4cj2PZe59.png)
 
-### Text 
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64161701107962562e9b1006/puASxtajF1lDeGYPrRK5y.png)
 
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/5dfcb1aada6d0311fd3d5448/uDg3hKDwJowsNuj-yyt2T.png)
+### Text 
 
 ## Usage
 
 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**:
 
-- `temperature=0.2` and `top_p=0.95` for chat completion (*e.g. Audio Understanding*) and `temperature=0.0` for transcription
-- Multiple audios per message and multiple user turns with audio are supported
-- Function calling is supported
-- System prompts are not yet supported
+**Note 1**: We recommend using a relatively low temperature, such as `temperature=0.15`.
 
+**Note 2**: Make sure to add a system prompt to the model to best tailor it to your needs.
 
 ### vLLM (recommended)
 
@@ -70,32 +66,20 @@ We recommend using this model with [vLLM](https://github.com/vllm-project/vllm).
 
 #### Installation
 
-Make sure to install vllm >= `0.10.0`, we recommend using uv
+Make sure to install [`vLLM >= 0.#.#`](https://github.com/vllm-project/vllm/releases/tag/v0.#.#):
 
 ```
-uv pip install -U "vllm[audio]" --system
+pip install vllm --upgrade
 ```
 
-Doing so should automatically install [`mistral_common >= 1.8.1`](https://github.com/mistralai/mistral-common/releases/tag/v1.8.1).
+Doing so should automatically install [`mistral_common >= 1.#.#`](https://github.com/mistralai/mistral-common/releases/tag/v1.#.#).
 
 To check:
 ```
 python -c "import mistral_common; print(mistral_common.__version__)"
 ```
 
-#### Offline
-
-You can test that your vLLM setup works as expected by cloning the vLLM repo:
-
-```sh
-git clone https://github.com/vllm-project/vllm && cd vllm
-```
-
-and then running:
-
-```sh
-python examples/offline_inference/audio_language.py --num-audios 2 --model-type voxtral
-```
+You can also make use of a ready-to-go [docker image](https://github.com/vllm-project/vllm/blob/main/Dockerfile) or on the [docker hub](https://hub.docker.com/layers/vllm/vllm-openai/latest/images/sha256-de9032a92ffea7b5c007dad80b38fd44aac11eddc31c435f8e52f3b7404bbf39).
 
 #### Serve
 
@@ -104,7 +88,7 @@ We recommend that you use Voxtral-Small-24B-2507 in a server/client setting.
 1. Spin up a server:
 
 ```
-vllm serve mistralai/Voxtral-Small-24B-2507 --tokenizer_mode mistral --config_format mistral --load_format mistral --tensor-parallel-size 2 --tool-call-parser mistral --enable-auto-tool-choice
+vllm serve mistralai/Voxtral-Small-24B-2507 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2
 ```
 
 **Note:** Running Voxtral-Small-24B-2507 on GPU requires ~55 GB of GPU RAM in bf16 or fp16. 
@@ -117,16 +101,60 @@ vllm serve mistralai/Voxtral-Small-24B-2507 --tokenizer_mode mistral --config_fo
 
 Leverage the audio capabilities of Voxtral-Small-24B-2507 to chat.
 
-Make sure that your client has `mistral-common` with audio installed:
+<details>
+  <summary>Python snippet</summary>
 
-```sh
-pip install --upgrade mistral_common\[audio\]
+```py
+TODO
 ```
+</details>
+
+#### Transcription
+
+Voxtral-Small-24B-2507 has powerfull transcription capabilities! 
+
+<details>
+  <summary>Python snippet</summary>
+
+```python
+TODO
+```
+</details>
+
+#### Function calling
+
+Voxtral-Small-24B-2507 is excellent at function / tool calling tasks via vLLM. *E.g.:*
 
 <details>
   <summary>Python snippet</summary>
 
 ```py
+```
+
+</details>
+
+# ORIGINAL
+
+```
+VLLM_USE_PRECOMPILED=1 pip install --editable .\[audio\]
+```
+
+of: https://github.com/vllm-project/vllm/pull/20970#pullrequestreview-3019578541
+
+# Examples
+
+## Client/Server
+
+### Server
+
+```sh
+vllm serve mistralai/voxtral-small --tokenizer_mode mistral --config_format mistral --load_format mistral --max_model_len 32768
+```
+
+### Client - Chat
+
+```py
+#!/usr/bin/env python3
 from mistral_common.protocol.instruct.messages import TextChunk, AudioChunk, UserMessage, AssistantMessage, RawAudio
 from mistral_common.audio import Audio
 from huggingface_hub import hf_hub_download
@@ -135,7 +163,7 @@ from openai import OpenAI
 
 # Modify OpenAI's API key and API base to use vLLM's API server.
 openai_api_key = "EMPTY"
-openai_api_base = "http://<your-server-host>:8000/v1"
+openai_api_base = "http://slurm-h100-reserved-rno-199-087:8000/v1"
 
 client = OpenAI(
     api_key=openai_api_key,
@@ -152,7 +180,7 @@ def file_to_chunk(file: str) -> AudioChunk:
     audio = Audio.from_file(file, strict=False)
     return AudioChunk.from_audio(audio)
 
-text_chunk = TextChunk(text="Which speaker is more inspiring? Why? How are they different from each other? Answer in French.")
+text_chunk = TextChunk(text="Which speaker do you prefer between the two? Why? How are they different from each other?")
 user_msg = UserMessage(content=[file_to_chunk(obama_file), file_to_chunk(bcn_file), text_chunk]).to_openai()
 
 print(30 * "=" + "USER 1" + 30 * "=")
@@ -162,20 +190,16 @@ print("\n\n")
 response = client.chat.completions.create(
     model=model,
     messages=[user_msg],
-    temperature=0.2,
-    top_p=0.95,
+    temperature=0.0,
+    max_tokens=32768,
 )
 content = response.choices[0].message.content
 
 print(30 * "=" + "BOT 1" + 30 * "=")
 print(content)
 print("\n\n")
-# The model could give the following answer:
-# ```L'orateur le plus inspirant est le président.
-# Il est plus inspirant parce qu'il parle de ses expériences personnelles
-# et de son optimisme pour l'avenir du pays.
-# Il est différent de l'autre orateur car il ne parle pas de la météo,
-# mais plutôt de ses interactions avec les gens et de son rôle en tant que président.```
+# "The speaker who delivers the farewell address is more engaging and inspiring. They express gratitude and optimism, emphasizing the importance of self-government and citizenship. They also share personal experiences and observations, making the speech more relatable and heartfelt. In contrast, the second speaker provides factual information about the weather in Barcelona, which is less engaging and lacks the emotional depth of the first speaker's address."
+#
 
 messages = [
     user_msg,
@@ -190,28 +214,16 @@ response = client.chat.completions.create(
     model=model,
     messages=messages,
     temperature=0.2,
-    top_p=0.95,
+    max_tokens=32768,
 )
 content = response.choices[0].message.content
 print(30 * "=" + "BOT 2" + 30 * "=")
 print(content)
 ```
-</details>
 
-#### Transcription
-
-Voxtral-Small-24B-2507 has powerful transcription capabilities! 
-
-Make sure that your client has `mistral-common` with audio installed:
-
-```sh
-pip install --upgrade mistral_common\[audio\]
-```
+### Client - Transcribe
 
-<details>
-  <summary>Python snippet</summary>
-
-```python
+```py
 from mistral_common.protocol.transcription.request import TranscriptionRequest
 from mistral_common.protocol.instruct.messages import RawAudio
 from mistral_common.audio import Audio
@@ -221,7 +233,7 @@ from openai import OpenAI
 
 # Modify OpenAI's API key and API base to use vLLM's API server.
 openai_api_key = "EMPTY"
-openai_api_base = "http://<your-server-host>:8000/v1"
+openai_api_base = "http://slurm-h100-reserved-rno-199-087:8000/v1"
 
 client = OpenAI(
     api_key=openai_api_key,
@@ -235,385 +247,10 @@ obama_file = hf_hub_download("patrickvonplaten/audio_samples", "obama.mp3", repo
 audio = Audio.from_file(obama_file, strict=False)
 
 audio = RawAudio.from_audio(audio)
-req = TranscriptionRequest(model=model, audio=audio, language="en", temperature=0.0).to_openai(exclude=("top_p", "seed"))
+req = TranscriptionRequest(model=model, audio=audio, language="en").to_openai(exclude=("top_p", "seed"))
 
 response = client.audio.transcriptions.create(**req)
 print(response)
 ```
-</details>
-
-#### Function Calling
-
-Voxtral has some experimental function calling support. You can try as shown below.
-
-Make sure that your client has `mistral-common` with audio installed:
-
-```sh
-pip install --upgrade mistral_common\[audio\]
-```
-
-<details>
-  <summary>Python snippet</summary>
-
-```python
-from mistral_common.protocol.instruct.messages import AudioChunk, UserMessage, TextChunk
-from mistral_common.protocol.transcription.request import TranscriptionRequest
-from mistral_common.protocol.instruct.tool_calls import Function, Tool
-
-from mistral_common.audio import Audio
-from huggingface_hub import hf_hub_download
-
-from openai import OpenAI
-
-# Modify OpenAI's API key and API base to use vLLM's API server.
-openai_api_key = "EMPTY"
-openai_api_base = "http://<your-server-host>:8000/v1"
-
-client = OpenAI(
-    api_key=openai_api_key,
-    base_url=openai_api_base,
-)
-
-models = client.models.list()
-model = models.data[0].id
-
-tool = Tool(
-    function=Function(
-        name="get_current_weather",
-        description="Get the current weather",
-        parameters={
-            "type": "object",
-            "properties": {
-                "location": {
-                    "type": "string",
-                    "description": "The city and state, e.g. San Francisco, CA",
-                },
-                "format": {
-                    "type": "string",
-                    "enum": ["celsius", "fahrenheit"],
-                    "description": "The temperature unit to use. Infer this from the user's location.",
-                },
-            },
-            "required": ["location", "format"],
-        },
-    )
-)
-tools = [tool.to_openai()]
-
-
-weather_like = hf_hub_download("patrickvonplaten/audio_samples", "fn_calling.wav", repo_type="dataset")
-
-def file_to_chunk(file: str) -> AudioChunk:
-    audio = Audio.from_file(file, strict=False)
-    return AudioChunk.from_audio(audio)
-
-audio_chunk = file_to_chunk(weather_like)
-
-print(30 * "=" + "Transcription" + 30 * "=")
-req = TranscriptionRequest(model=model, audio=audio_chunk.input_audio, language="en", temperature=0.0).to_openai(exclude=("top_p", "seed"))
-response = client.audio.transcriptions.create(**req)
-print(response.text) # How is the weather in Madrid at the moment?
-print("\n")
-
-
-print(30 * "=" + "Function calling" + 30 * "=")
-audio_chunk = file_to_chunk(weather_like)
-user_msg = UserMessage(content=[audio_chunk]).to_openai()
-response = client.chat.completions.create(
-    model=model,
-    messages=[user_msg],
-    temperature=0.2,
-    top_p=0.95,
-    tools=[tool.to_openai()]
-)
-print(30 * "=" + "BOT 1" + 30 * "=")
-print(response.choices[0].message.tool_calls)
-print("\n\n")
-```
-</details>
-
-### Transformers 🤗
 
-Starting with `transformers >= 4.54.0` and above, you can run Voxtral natively!
 
-Install Transformers:
-```bash
-pip install -U 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-Small-24B-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-Small-24B-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-Small-24B-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-Small-24B-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-Small-24B-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-Small-24B-2507"
-
-processor = AutoProcessor.from_pretrained(repo_id)
-model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)
-
-inputs = processor.apply_transcription_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

@@ -1,53 +0,0 @@
-{
-  "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": 5120,
-  "model_type": "voxtral",
-  "projector_hidden_act": "gelu",
-  "text_config": {
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "head_dim": 128,
-    "hidden_act": "silu",
-    "hidden_size": 5120,
-    "initializer_range": 0.02,
-    "intermediate_size": 32768,
-    "max_position_embeddings": 131072,
-    "mlp_bias": false,
-    "model_type": "llama",
-    "num_attention_heads": 32,
-    "num_hidden_layers": 40,
-    "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

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

model-00001-of-00011.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e4c3fde4ef4a1141b4b06f2125c63bb2032f71a7985fafb4b3ae8243ca17be2
-size 4947893992

model-00002-of-00011.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6998429899fc08e533b7ef0bb65a66d0c744a490c31b5210ea5f61e62e8fb997
-size 4781593336

model-00003-of-00011.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b692e60c5d9acfd5b6e7fd2c0337349a421bb687c8cef14627469f744efa83df
-size 4781593344

model-00004-of-00011.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0c34b0b04a59f62c3d1f320803f421c45d51dbf917f4e3f90eda957640ae85da
-size 4886472248

model-00005-of-00011.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bcea8514dd1330b2478deeff5b48b6788c1e6fbd1c6d5034faeeee5c066b6288
-size 4781593376

model-00006-of-00011.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3e415b6a5cc6f266acdd8aeba526288abd8345ebaa4022ab0e26ea30eaaffa91
-size 4781593368

model-00007-of-00011.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:720bbe6314e0b69b97fd13e07ffdef4953dc5aec3b4b91c15a9c1d40d7b1c7fc
-size 4886472248

model-00008-of-00011.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:85c590b7d4d6c843dc083b3048f5b00cda7ee7ddfeb18a3732ff2db65926a6eb
-size 4781593376

model-00009-of-00011.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fc973532e7f8faea778ed22aac9867b84e1d4bb4ad9c9a50744fc1eeeb6c9115
-size 4781593368

model-00010-of-00011.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:365913969c7a5c93cc2d9e19b6f9d4128e675db8a1941c2436f0a2a2c64870e2
-size 3670112232

model-00011-of-00011.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2515d18911999b503000115208d6c5ae46777223227c18a170cbff3095aaf697
-size 1447035256

model.safetensors.index.json

@@ -1,860 +0,0 @@
-{
-  "metadata": {
-    "total_parameters": 24261800960,
-    "total_size": 48527441920
-  },
-  "weight_map": {
-    "audio_tower.conv1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.conv1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.conv2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.conv2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.embed_positions.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.0.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.1.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.10.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.11.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.12.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.13.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.14.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.15.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.16.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.17.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.18.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.19.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.2.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.20.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.21.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.22.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.23.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.24.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.25.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.26.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.27.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.28.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.29.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.3.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.30.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.31.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.4.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.5.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.6.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.7.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.8.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.fc1.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.fc1.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.fc2.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.fc2.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.final_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.final_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.self_attn.out_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.self_attn.out_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.self_attn.q_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.self_attn.v_proj.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.self_attn_layer_norm.bias": "model-00001-of-00011.safetensors",
-    "audio_tower.layers.9.self_attn_layer_norm.weight": "model-00001-of-00011.safetensors",
-    "language_model.lm_head.weight": "model-00011-of-00011.safetensors",
-    "language_model.model.embed_tokens.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.10.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.10.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.15.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.15.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
-    "language_model.model.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.16.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.16.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
-    "language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.2.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.2.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "language_model.model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.22.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.22.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
-    "language_model.model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.26.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.26.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.26.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.27.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.27.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
-    "language_model.model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.29.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.30.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.30.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.30.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.31.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.31.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.31.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.32.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.32.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.32.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
-    "language_model.model.layers.33.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.33.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.33.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.33.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.33.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.33.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.33.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.34.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.34.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.34.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.34.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.35.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.35.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.35.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.35.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.36.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.36.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.36.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.36.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.36.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.36.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.36.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
-    "language_model.model.layers.37.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.37.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.37.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.37.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.37.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.37.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.37.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.37.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.37.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.38.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.38.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.38.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.38.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.38.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.38.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.38.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.38.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.38.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.39.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.39.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.39.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.39.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.39.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.39.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.39.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.39.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.39.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
-    "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.6.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.6.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.6.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
-    "language_model.model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
-    "language_model.model.norm.weight": "model-00010-of-00011.safetensors",
-    "multi_modal_projector.linear_1.weight": "model-00011-of-00011.safetensors",
-    "multi_modal_projector.linear_2.weight": "model-00011-of-00011.safetensors"
-  }
-}

params.json

@@ -8,7 +8,6 @@
   "rope_theta": 100000000.0,
   "norm_eps": 1e-05,
   "vocab_size": 131072,
-  "max_position_embeddings": 32768,
   "multimodal": {
     "whisper_model_args": {
       "encoder_args": {
@@ -17,17 +16,35 @@
         "head_dim": 64,
         "hidden_dim": 5120,
         "n_heads": 20,
+        "n_kv_heads": 20,
+        "rope_theta": 1000000.0,
+        "norm_eps": 1e-05,
         "vocab_size": 51866,
+        "tied_embeddings": true,
+        "ffn_type": "gelu",
+        "conv_strides_str": "1,2",
         "max_source_positions": 1500,
+        "pos_embed": "learned",
+        "freeze_encoder": true,
         "audio_encoding_args": {
           "sampling_rate": 16000,
+          "frame_rate": 12.5,
           "num_mel_bins": 128,
           "hop_length": 160,
-          "window_size": 400
+          "window_size": 400,
+          "chunk_length_s": 30.0
         }
       },
+      "decoder_args": null,
+      "audio_token_id": 24,
+      "begin_audio_token_id": 25,
+      "audio_special_tokens_in_adapter": false,
+      "audio_special_token_ids": null,
+      "output_embedding_concat_type": "mlp",
       "downsample_args": {
-        "downsample_factor": 4
+        "downsample_factor": 4,
+        "num_blocks": 1,
+        "n_transformer_layers_per_block": 0
       }
     }
   }

preprocessor_config.json

@@ -1,15 +0,0 @@
-{
-  "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
-}