LLM EXPLORER 63,407 MODELS INDEXED

Yi 9B 200K 6.0bpw H6 EXL2 by LoneStriker

By LoneStriker · 3 downloads
HF Repo ↗ Copy URL

Yi 9B 200K 6.0bpw H6 EXL2 is an open-source language model by LoneStriker. Features: 9b LLM, VRAM: 7GB, Context: 256K, License: other, Quantized, LLM Explorer Score: 0.11.

  Arxiv:2311.16502   Arxiv:2401.11944   Arxiv:2403.04652   6-bit   Endpoints compatible   Exl2   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/LoneStriker/Yi-9B-200K-6.0bpw-h6-exl2 

Yi 9B 200K 6.0bpw H6 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 9B 200K 6.0bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/Yi-9B-200K-6.0bpw-h6-exl2 
Model Size9b
Required VRAM7 GB
Updated2026-08-08
MaintainerLoneStriker
Model Typellama
Model Files  7.0 GB
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to Yi 9B 200K 6.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
Yi 9B 200K 3.0bpw H6 EXL2256K / 3.9 GB61
Faro Yi 9B DPO 6bpw EXL232K / 7 GB31
Faro Yi 9B DPO 8bpw EXL232K / 8.3 GB21
...5 9B Chat Quantized Merge 4Bit7K / 34 GB60
Master Yi 9B 8.0bpw H8 EXL24K / 8.7 GB32
Master Yi 9B 3.0bpw H6 EXL24K / 3.9 GB41
Master Yi 9B 5.0bpw H6 EXL24K / 5.9 GB41
Master Yi 9B 4.0bpw H6 EXL24K / 4.9 GB31
Master Yi 9B 6.0bpw H6 EXL24K / 7 GB31
Yi 1.5 9B 8bit4K / 9.3 GB71
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Yi-9B-200K-6.0bpw-h6-exl2.