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

Vntl Llama3 8B 8.0bpw EXL2 by alac

 »  All LLMs  »  alac  »  Vntl Llama3 8B 8.0bpw EXL2   URL Share it on

  0   
  8-bit Base model:adapter:rinna/llama... Base model:rinna/llama-3-youko...   Dataset:lmg-anon/vntl-chat   Dataset:lmg-anon/vntl-v3.1-1k   En   Exl2   Ja   Llama   Peft   Quantized   Region:us   Safetensors   Translation
Model Card on HF 🤗: https://huggingface.co/alac/vntl-llama3-8b-8.0bpw-exl2 

Vntl Llama3 8B 8.0bpw EXL2 Benchmarks

LLME Score: 0.19174
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Vntl Llama3 8B 8.0bpw EXL2 (alac/vntl-llama3-8b-8.0bpw-exl2)

Vntl Llama3 8B 8.0bpw EXL2 Parameters and Internals

Model Type 
translation, chat
Additional Notes 
The model offers a new "chat mode" focused on Japanese grammar questions.
Supported Languages 
ja (Japanese), en (English)
Training Details 
Data Sources:
lmg-anon/VNTL-v3.1-1k, lmg-anon/VNTL-Chat
Methodology:
Quantization using exl2 technique at 8.0 bpw with the default exl2 calibration dataset at 2k tokens.
Input Output 
Input Format:
Expected input in prompt format described in the prompt examples.
Accepted Modalities:
text
Output Format:
Text translation or chat response.
LLM NameVntl Llama3 8B 8.0bpw EXL2
Repository 🤗https://huggingface.co/alac/vntl-llama3-8b-8.0bpw-exl2 
Base Model(s)  Llama 3 Youko 8B   rinna/llama-3-youko-8b
Model Size8b
Required VRAM8.3 GB
Updated2025-03-13
Maintaineralac
Model Typellama
Model Files  8.3 GB
Supported Languagesja en
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.41.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128263
Torch Data Typebfloat16

Best Alternatives to Vntl Llama3 8B 8.0bpw EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB142
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB81
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB132
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB90
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB1225
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB2117
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB123
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB121
...B Instruct 262k V2 EXL2 6.0bpw256K / 6.7 GB161
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB91
Note: green Score (e.g. "73.2") means that the model is better than alac/vntl-llama3-8b-8.0bpw-exl2.

Rank the Vntl Llama3 8B 8.0bpw EXL2 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? 44950 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