Yi 6B Spicyboros 3.1 4.0bpw H6 EXL2 by LoneStriker

 ยป  All LLMs  ยป  LoneStriker  ยป  Yi 6B Spicyboros 3.1 4.0bpw H6 EXL2   URL Share it on

  Autotrain compatible   Base model:01-ai/yi-6b Base model:finetune:01-ai/yi-6...   Custom code   Dataset:unalignment/spicy-3.1   Exl2   Finetuned   Pytorch   Quantized   Region:us   Yi   Yi-6b

Yi 6B Spicyboros 3.1 4.0bpw H6 EXL2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Yi 6B Spicyboros 3.1 4.0bpw H6 EXL2 (LoneStriker/Yi-6B-Spicyboros-3.1-4.0bpw-h6-exl2)

Yi 6B Spicyboros 3.1 4.0bpw H6 EXL2 Parameters and Internals

Safety Evaluation 
Ethical Considerations:
The model is trained using data compliance checking algorithms to ensure compliance to the best of our ability, but there is still a risk of generating problematic outputs.
LLM NameYi 6B Spicyboros 3.1 4.0bpw H6 EXL2
Repository ๐Ÿค—https://huggingface.co/LoneStriker/Yi-6B-Spicyboros-3.1-4.0bpw-h6-exl2 
Base Model(s)  Yi 6B   01-ai/Yi-6B
Model Size6b
Required VRAM3.5 GB
Updated2024-12-22
MaintainerLoneStriker
Model TypeYi
Model Files  3.5 GB
Quantization Typeexl2
Model ArchitectureYiForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size64002
Torch Data Typefloat16

Best Alternatives to Yi 6B Spicyboros 3.1 4.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...o Claude Puffin 8.0bpw H8 EXL2195K / 6.3 GB51
... Spicyboros 3.1 3.0bpw H6 EXL24K / 2.8 GB141
Yi 6B 200K GPTQ195K / 3.9 GB662
Yi 6B 200K AWQ195K / 3.9 GB592
Yi 6B 200K Airo Claude Puffin195K / 12.1 GB81
Dragon Yi 6B V04K / 3.7 GB6060
Yi 6B GPTQ4K / 3.9 GB921
Dragon Yi 6B V0 AWQ4K / 3.9 GB292
01 Ai Yi 6B Openhermes4K / 12.1 GB94
Yi 6B AWQ4K / 3.9 GB321
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Yi-6B-Spicyboros-3.1-4.0bpw-h6-exl2.

Rank the Yi 6B Spicyboros 3.1 4.0bpw H6 EXL2 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217