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

Yi 6B 200K 8.0bpw H8 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Yi 6B 200K 8.0bpw H8 EXL2   URL Share it on

  8   
  Arxiv:2311.16502   Arxiv:2401.11944   Arxiv:2403.04652   8-bit   Autotrain compatible   Endpoints compatible   Exl2   Llama   Pytorch   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/LoneStriker/Yi-6B-200K-8.0bpw-h8-exl2 

Yi 6B 200K 8.0bpw H8 EXL2 Benchmarks

LLME Score: 0.144
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Yi 6B 200K 8.0bpw H8 EXL2 (LoneStriker/Yi-6B-200K-8.0bpw-h8-exl2)

Yi 6B 200K 8.0bpw H8 EXL2 Parameters and Internals

Model Type 
text-generation, chatbot
Use Cases 
Areas:
Personal, Academic, Commercial use for small-medium enterprises
Applications:
Language understanding, Commonsense reasoning, Reading comprehension
Primary Use Cases:
Chatbots, Language models for apps
Limitations:
Possibility of generating non-factual content
Considerations:
Adjust generation parameters for more coherent responses
Additional Notes 
Yi models adopt Llama architecture but are independently trained without its weights.
Supported Languages 
English (High), Chinese (High), Multilingual (Supported but less proficient)
Training Details 
Data Sources:
3T multilingual corpus
Data Volume:
3 Trillion tokens
Methodology:
Supervised Fine-Tuning (SFT)
Context Length:
4000
Training Time:
Not specified
Hardware Used:
NVIDIA A800 80GB and consumer-grade GPUs for quantized versions
Model Architecture:
Transformer-based, adopting Llama structure
Safety Evaluation 
Methodologies:
Not specified
Input Output 
Input Format:
text input
Accepted Modalities:
text
Output Format:
text output
Performance Tips:
Adjust parameters like temperature, top_p for better coherency
Release Notes 
Version:
Yi-34B-Chat
Date:
2023-11-23
Notes:
Open-sourced chat model with diverse response capability
Version:
Yi-34B
Date:
2023-11-02
Notes:
Base model for various applications, bilingual support.
LLM NameYi 6B 200K 8.0bpw H8 EXL2
Repository 🤗https://huggingface.co/LoneStriker/Yi-6B-200K-8.0bpw-h8-exl2 
Model Size6b
Required VRAM6.3 GB
Updated2025-02-05
MaintainerLoneStriker
Model Typellama
Model Files  6.3 GB
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length200000
Model Max Length200000
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to Yi 6B 200K 8.0bpw H8 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...i 6B 200K AEZAKMI V2 6bpw EXL2195K / 4.9 GB83
Yi 6B 200K 6.0bpw H6 EXL2195K / 4.9 GB71
...ma Llama 3 6B V0.1 2 2bpw EXL28K / 2.9 GB70
Yi 1.5 6B Bnb 4bit4K / 3.9 GB1262
Docllm Yi 6B4K / 13.5 GB71
Yi 6B Bnb 4bit4K / 3.9 GB761
Yi 6B Chat 6bpw H8 EXL2 Cnen4K / 4.9 GB81
Yi Ko 1.22K / 24.6 GB22950
Yi Ko 3 1 72K / 24.6 GB22910
Electus Yiko DPO2K / 12.4 GB640
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Yi-6B-200K-8.0bpw-h8-exl2.

Rank the Yi 6B 200K 8.0bpw H8 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? 42565 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