From a540cc5b39f617f8effda7e5011bad94f683e476 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 24 Oct 2026 06:05:17 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mistralai/Voxtral-Mini-3B-2507 Source: Original Platform --- .gitattributes | 36 ++ README.md | 526 +++++++++++++++++++++ config.json | 53 +++ consolidated.safetensors | 3 + generation_config.json | 6 + model-00001-of-00002.safetensors | 3 + model-00002-of-00002.safetensors | 3 + model.safetensors.index.json | 770 +++++++++++++++++++++++++++++++ params.json | 34 ++ preprocessor_config.json | 15 + tekken.json | 3 + 11 files changed, 1452 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 consolidated.safetensors create mode 100644 generation_config.json create mode 100644 model-00001-of-00002.safetensors create mode 100644 model-00002-of-00002.safetensors create mode 100644 model.safetensors.index.json create mode 100644 params.json create mode 100644 preprocessor_config.json create mode 100644 tekken.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ed18453 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tekken.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..141e13d --- /dev/null +++ b/README.md @@ -0,0 +1,526 @@ +--- +library_name: mistral-common +language: +- en +- fr +- de +- es +- it +- pt +- nl +- hi +license: apache-2.0 +inference: false +extra_gated_description: >- + If you want to learn more about how we process your personal data, please read + our Privacy Policy. +tags: +- vllm +--- +# Voxtral Mini 1.0 (3B) - 2507 + +Voxtral Mini is an enhancement of [Ministral 3B](https://mistral.ai/news/ministraux), 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) and our [research paper](https://arxiv.org/abs/2507.13264). + +## Key Features + +Voxtral builds upon Ministral-3B 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, Ministral-3B + +## 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/puASxtajF1lDeGYPrRK5y.png) + +### Text + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/5dfcb1aada6d0311fd3d5448/iH9V8JVtMoaGlqJd6FIri.png) + +## 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 +- System prompts are not yet supported + +### vLLM (recommended) + +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`: + +``` +uv pip install -U "vllm[audio]" --system +``` + +Doing so should automatically install [`mistral_common >= 1.8.1`](https://github.com/mistralai/mistral-common/releases/tag/v1.8.1). + +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 +``` + +#### Serve + +We recommend that you use Voxtral-Small-24B-2507 in a server/client setting. + +1. Spin up a server: + +``` +vllm serve mistralai/Voxtral-Mini-3B-2507 --tokenizer_mode mistral --config_format mistral --load_format mistral +``` + +**Note:** Running Voxtral-Mini-3B-2507 on GPU requires ~9.5 GB of GPU RAM in bf16 or fp16. + + +2. To ping the client you can use a simple Python snippet. See the following examples. + + +### Audio Instruct + +Leverage the audio capabilities of Voxtral-Mini-3B-2507 to chat. + +Make sure that your client has `mistral-common` with audio installed: + +```sh +pip install --upgrade mistral_common\[audio\] +``` + +
+ Python snippet + +```py +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 + +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://:8000/v1" + +client = OpenAI( + api_key=openai_api_key, + base_url=openai_api_base, +) + +models = client.models.list() +model = models.data[0].id + +obama_file = hf_hub_download("patrickvonplaten/audio_samples", "obama.mp3", repo_type="dataset") +bcn_file = hf_hub_download("patrickvonplaten/audio_samples", "bcn_weather.mp3", repo_type="dataset") + +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?") +user_msg = UserMessage(content=[file_to_chunk(obama_file), file_to_chunk(bcn_file), text_chunk]).to_openai() + +print(30 * "=" + "USER 1" + 30 * "=") +print(text_chunk.text) +print("\n\n") + +response = client.chat.completions.create( + model=model, + messages=[user_msg], + temperature=0.2, + top_p=0.95, +) +content = response.choices[0].message.content + +print(30 * "=" + "BOT 1" + 30 * "=") +print(content) +print("\n\n") +# The speaker who is more inspiring is the one who delivered the farewell address, as they express +# gratitude, optimism, and a strong commitment to the nation and its citizens. They emphasize the importance of +# self-government and active citizenship, encouraging everyone to participate in the democratic process. In contrast, +# the other speaker provides a factual update on the weather in Barcelona, which is less inspiring as it +# lacks the emotional and motivational content of the farewell address. + +# **Differences:** +# - The farewell address speaker focuses on the values and responsibilities of citizenship, encouraging active participation in democracy. +# - The weather update speaker provides factual information about the temperature in Barcelona, without any emotional or motivational content. + + +messages = [ + user_msg, + AssistantMessage(content=content).to_openai(), + UserMessage(content="Ok, now please summarize the content of the first audio.").to_openai() +] +print(30 * "=" + "USER 2" + 30 * "=") +print(messages[-1]["content"]) +print("\n\n") + +response = client.chat.completions.create( + model=model, + messages=messages, + temperature=0.2, + top_p=0.95, +) +content = response.choices[0].message.content +print(30 * "=" + "BOT 2" + 30 * "=") +print(content) +``` +
+ +#### Transcription + +Voxtral-Mini-3B-2507 has powerful transcription capabilities! + +Make sure that your client has `mistral-common` with audio installed: + +```sh +pip install --upgrade mistral_common\[audio\] +``` + +
+ Python snippet + +```python +from mistral_common.protocol.transcription.request import TranscriptionRequest +from mistral_common.protocol.instruct.messages import RawAudio +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://:8000/v1" + +client = OpenAI( + api_key=openai_api_key, + base_url=openai_api_base, +) + +models = client.models.list() +model = models.data[0].id + +obama_file = hf_hub_download("patrickvonplaten/audio_samples", "obama.mp3", repo_type="dataset") +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")) + +response = client.audio.transcriptions.create(**req) +print(response) +``` +
+ +### 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 + +
+ ➡️ multi-audio + text instruction + +```python +from transformers import VoxtralForConditionalGeneration, AutoProcessor +import torch + +device = "cuda" +repo_id = "mistralai/Voxtral-Mini-3B-2507" + +processor = AutoProcessor.from_pretrained(repo_id) +model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device) + +conversation = [ + { + "role": "user", + "content": [ + { + "type": "audio", + "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/mary_had_lamb.mp3", + }, + { + "type": "audio", + "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3", + }, + {"type": "text", "text": "What sport and what nursery rhyme are referenced?"}, + ], + } +] + +inputs = processor.apply_chat_template(conversation) +inputs = inputs.to(device, dtype=torch.bfloat16) + +outputs = model.generate(**inputs, max_new_tokens=500) +decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True) + +print("\nGenerated response:") +print("=" * 80) +print(decoded_outputs[0]) +print("=" * 80) +``` +
+ + +
+ ➡️ multi-turn + +```python +from transformers import VoxtralForConditionalGeneration, AutoProcessor +import torch + +device = "cuda" +repo_id = "mistralai/Voxtral-Mini-3B-2507" + +processor = AutoProcessor.from_pretrained(repo_id) +model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device) + +conversation = [ + { + "role": "user", + "content": [ + { + "type": "audio", + "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3", + }, + { + "type": "audio", + "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3", + }, + {"type": "text", "text": "Describe briefly what you can hear."}, + ], + }, + { + "role": "assistant", + "content": "The audio begins with the speaker delivering a farewell address in Chicago, reflecting on his eight years as president and expressing gratitude to the American people. The audio then transitions to a weather report, stating that it was 35 degrees in Barcelona the previous day, but the temperature would drop to minus 20 degrees the following day.", + }, + { + "role": "user", + "content": [ + { + "type": "audio", + "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3", + }, + {"type": "text", "text": "Ok, now compare this new audio with the previous one."}, + ], + }, +] + +inputs = processor.apply_chat_template(conversation) +inputs = inputs.to(device, dtype=torch.bfloat16) + +outputs = model.generate(**inputs, max_new_tokens=500) +decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True) + +print("\nGenerated response:") +print("=" * 80) +print(decoded_outputs[0]) +print("=" * 80) +``` +
+ + +
+ ➡️ text only + +```python +from transformers import VoxtralForConditionalGeneration, AutoProcessor +import torch + +device = "cuda" +repo_id = "mistralai/Voxtral-Mini-3B-2507" + +processor = AutoProcessor.from_pretrained(repo_id) +model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device) + +conversation = [ + { + "role": "user", + "content": [ + { + "type": "text", + "text": "Why should AI models be open-sourced?", + }, + ], + } +] + +inputs = processor.apply_chat_template(conversation) +inputs = inputs.to(device, dtype=torch.bfloat16) + +outputs = model.generate(**inputs, max_new_tokens=500) +decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True) + +print("\nGenerated response:") +print("=" * 80) +print(decoded_outputs[0]) +print("=" * 80) +``` +
+ + +
+ ➡️ audio only + +```python +from transformers import VoxtralForConditionalGeneration, AutoProcessor +import torch + +device = "cuda" +repo_id = "mistralai/Voxtral-Mini-3B-2507" + +processor = AutoProcessor.from_pretrained(repo_id) +model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device) + +conversation = [ + { + "role": "user", + "content": [ + { + "type": "audio", + "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3", + }, + ], + } +] + +inputs = processor.apply_chat_template(conversation) +inputs = inputs.to(device, dtype=torch.bfloat16) + +outputs = model.generate(**inputs, max_new_tokens=500) +decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True) + +print("\nGenerated response:") +print("=" * 80) +print(decoded_outputs[0]) +print("=" * 80) +``` +
+ + +
+ ➡️ batched inference + +```python +from transformers import VoxtralForConditionalGeneration, AutoProcessor +import torch + +device = "cuda" +repo_id = "mistralai/Voxtral-Mini-3B-2507" + +processor = AutoProcessor.from_pretrained(repo_id) +model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device) + +conversations = [ + [ + { + "role": "user", + "content": [ + { + "type": "audio", + "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3", + }, + { + "type": "audio", + "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3", + }, + { + "type": "text", + "text": "Who's speaking in the speach and what city's weather is being discussed?", + }, + ], + } + ], + [ + { + "role": "user", + "content": [ + { + "type": "audio", + "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3", + }, + {"type": "text", "text": "What can you tell me about this audio?"}, + ], + } + ], +] + +inputs = processor.apply_chat_template(conversations) +inputs = inputs.to(device, dtype=torch.bfloat16) + +outputs = model.generate(**inputs, max_new_tokens=500) +decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True) + +print("\nGenerated responses:") +print("=" * 80) +for decoded_output in decoded_outputs: + print(decoded_output) + print("=" * 80) +``` +
+ +#### Transcription + +
+ ➡️ transcribe + +```python +from transformers import VoxtralForConditionalGeneration, AutoProcessor +import torch + +device = "cuda" +repo_id = "mistralai/Voxtral-Mini-3B-2507" + +processor = AutoProcessor.from_pretrained(repo_id) +model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device) + +inputs = processor.apply_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) +``` +
\ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..6f871b8 --- /dev/null +++ b/config.json @@ -0,0 +1,53 @@ +{ + "architectures": [ + "VoxtralForConditionalGeneration" + ], + "audio_config": { + "activation_dropout": 0.0, + "activation_function": "gelu", + "attention_dropout": 0.0, + "dropout": 0.0, + "head_dim": 64, + "hidden_size": 1280, + "initializer_range": 0.02, + "intermediate_size": 5120, + "layerdrop": 0.0, + "max_source_positions": 1500, + "model_type": "voxtral_encoder", + "num_attention_heads": 20, + "num_hidden_layers": 32, + "num_key_value_heads": 20, + "num_mel_bins": 128, + "scale_embedding": false, + "vocab_size": 51866 + }, + "audio_token_id": 24, + "hidden_size": 3072, + "model_type": "voxtral", + "projector_hidden_act": "gelu", + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 30, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 100000000.0, + "sliding_window": null, + "use_cache": true, + "vocab_size": 131072 + }, + "torch_dtype": "bfloat16", + "transformers_version": "4.54.0.dev0", + "vocab_size": 131072 +} diff --git a/consolidated.safetensors b/consolidated.safetensors new file mode 100644 index 0000000..5ad363b --- /dev/null +++ b/consolidated.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec4dda59bfd9956e71347530d62168cee564c2caf72986c8727355758691eaa7 +size 9348806528 diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..252746d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 11, + "transformers_version": "4.54.0.dev0" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..164e173 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1facdc4c5a0e84f2881a59c4756441b7030a1f1036b2124c117540408d0e5fe9 +size 4977385976 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..84b397d --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a103ba715bc0d656e94bf79d637d4f8f0f4fe6d76fb1d4db7ee46c6b940f631 +size 4379088336 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..2aad354 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,770 @@ +{ + "metadata": { + "total_parameters": 4676271104, + "total_size": 9356382208 + }, + "weight_map": { + "audio_tower.conv1.bias": "model-00001-of-00002.safetensors", + "audio_tower.conv1.weight": "model-00001-of-00002.safetensors", + "audio_tower.conv2.bias": "model-00001-of-00002.safetensors", + "audio_tower.conv2.weight": "model-00001-of-00002.safetensors", + "audio_tower.embed_positions.weight": "model-00001-of-00002.safetensors", + "audio_tower.layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.30.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.31.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.fc1.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.fc1.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.fc2.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.fc2.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors", + "audio_tower.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors", + "language_model.lm_head.weight": "model-00002-of-00002.safetensors", + "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "language_model.model.norm.weight": "model-00002-of-00002.safetensors", + "multi_modal_projector.linear_1.weight": "model-00002-of-00002.safetensors", + "multi_modal_projector.linear_2.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/params.json b/params.json new file mode 100644 index 0000000..f3d0c4a --- /dev/null +++ b/params.json @@ -0,0 +1,34 @@ +{ + "dim": 3072, + "n_layers": 30, + "head_dim": 128, + "hidden_dim": 8192, + "n_heads": 32, + "n_kv_heads": 8, + "rope_theta": 100000000.0, + "norm_eps": 1e-05, + "vocab_size": 131072, + "max_position_embeddings": 32768, + "multimodal": { + "whisper_model_args": { + "encoder_args": { + "dim": 1280, + "n_layers": 32, + "head_dim": 64, + "hidden_dim": 5120, + "n_heads": 20, + "vocab_size": 51866, + "max_source_positions": 1500, + "audio_encoding_args": { + "sampling_rate": 16000, + "num_mel_bins": 128, + "hop_length": 160, + "window_size": 400 + } + }, + "downsample_args": { + "downsample_factor": 4 + } + } + } +} \ No newline at end of file diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..a9f84a0 --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,15 @@ +{ + "chunk_length": 30, + "dither": 0.0, + "feature_extractor_type": "WhisperFeatureExtractor", + "feature_size": 128, + "hop_length": 160, + "n_fft": 400, + "n_samples": 480000, + "nb_max_frames": 3000, + "padding_side": "right", + "padding_value": 0.0, + "processor_class": "VoxtralProcessor", + "return_attention_mask": false, + "sampling_rate": 16000 +} diff --git a/tekken.json b/tekken.json new file mode 100644 index 0000000..dc72fbe --- /dev/null +++ b/tekken.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aaf3836c2a5332f029ce85a7a62255c966f47b6797ef81dedd0ade9c862e4a8 +size 14894206