LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Llama 3 Typhoon V1.5 8B Audio Preview by scb10x

 »  All LLMs  »  scb10x  »  Llama 3 Typhoon V1.5 8B Audio Preview   URL Share it on

  486   
  Arxiv:2409.10999   Custom code   En   Feature-extraction   Lora   Pytorch   Region:us   Sharded   Th   Typhoonaudio
Model Card on HF 🤗: https://huggingface.co/scb10x/llama-3-typhoon-v1.5-8b-audio-preview 

Llama 3 Typhoon V1.5 8B Audio Preview Benchmarks

LLME Score: 0.24412
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 Typhoon V1.5 8B Audio Preview (scb10x/llama-3-typhoon-v1.5-8b-audio-preview)

Llama 3 Typhoon V1.5 8B Audio Preview Parameters and Internals

Model Type 
audio-language, multimodal
Use Cases 
Areas:
research, multimodal applications
Limitations:
The model may not accurately follow human instructions., Prone to generating hallucinations., Lacks moderation mechanisms, potentially producing harmful or inappropriate responses.
Considerations:
Developers should assess risks based on specific applications.
Supported Languages 
languages_supported (Thai, English), proficiency_level (native)
Training Details 
Methodology:
Incorporates Whisper's encoder and BEATs
Model Architecture:
Based on Typhoon-1.5-8b-instruct architecture
Input Output 
Accepted Modalities:
text, audio
Output Format:
text
LLM NameLlama 3 Typhoon V1.5 8B Audio Preview
Repository 🤗https://huggingface.co/scb10x/llama-3-typhoon-v1.5-8b-audio-preview 
Model Size8b
Required VRAM17.6 GB
Updated2024-12-08
Maintainerscb10x
Model Typetyphoonaudio
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   4.9 GB: 3-of-4   2.9 GB: 4-of-4
Supported Languagesth en
Model ArchitectureTyphoonAudio
Licensellama3
Transformers Version4.43.3
LoRA ModelYes
LoRA Alpha32
LoRA Dropout0
Torch Data Typefloat16

Rank the Llama 3 Typhoon V1.5 8B Audio Preview Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 39016 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer