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

Ichigo Llama3.1 S Instruct V0.3 Phase 2 by jan-hq

 »  All LLMs  »  jan-hq  »  Ichigo Llama3.1 S Instruct V0.3 Phase 2   URL Share it on

  16   
  Arxiv:2406.16020   Audio-text-to-text Dataset:homebrewltd/instructio...   En   Instruct   Llama   Region:us   Safetensors   Sharded   Sound language model   Tensorflow
Model Card on HF 🤗: https://huggingface.co/homebrewltd/Ichigo-llama3.1-s-instruct-v0.3-phase-2 

Ichigo Llama3.1 S Instruct V0.3 Phase 2 Benchmarks

LLME Score: 0.20372
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ichigo Llama3.1 S Instruct V0.3 Phase 2 (homebrewltd/Ichigo-llama3.1-s-instruct-v0.3-phase-2)

Ichigo Llama3.1 S Instruct V0.3 Phase 2 Parameters and Internals

Model Type 
sound language model
Use Cases 
Areas:
research applications
Primary Use Cases:
improve sound understanding capabilities
Limitations:
use in any manner that violates laws or regulations
Supported Languages 
en (English)
Training Details 
Data Sources:
Instruction Speech WhisperVQ v3
Data Volume:
nearly 1B tokens
Methodology:
Semantic tokens experiment using WhisperVQ as a tokenizer
Context Length:
4096
Training Time:
12 hours
Hardware Used:
Cluster of 8x NVIDIA H100-SXM-80GB
Model Architecture:
Llama-3
Input Output 
Input Format:
Text and sound
Accepted Modalities:
text, sound
Output Format:
Text
LLM NameIchigo Llama3.1 S Instruct V0.3 Phase 2
Repository 🤗https://huggingface.co/homebrewltd/Ichigo-llama3.1-s-instruct-v0.3-phase-2 
Model Size8b
Required VRAM16.1 GB
Updated2025-03-27
Maintainerjan-hq
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128771
Torch Data Typebfloat16

Best Alternatives to Ichigo Llama3.1 S Instruct V0.3 Phase 2

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB4363104
UltraLong Thinking4192K / 16.1 GB692
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB129215
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB402540
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB312
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB22337679
A4.21024K / 16.1 GB1350
Note: green Score (e.g. "73.2") means that the model is better than homebrewltd/Ichigo-llama3.1-s-instruct-v0.3-phase-2.

Rank the Ichigo Llama3.1 S Instruct V0.3 Phase 2 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? 46792 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 v20241227
  Support LLM Explorer