Yi 34B 200K DARE Megamerge V8 GGUF by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Yi 34B 200K DARE Megamerge V8 GGUF   URL Share it on

  Arxiv:2306.01708   Arxiv:2311.03099 Base model:brucethemoose/yi-34... Base model:quantized:brucethem...   En   Gguf   Merge   Mergekit   Quantized   Region:us   Yi

Yi 34B 200K DARE Megamerge V8 GGUF Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Yi 34B 200K DARE Megamerge V8 GGUF Parameters and Internals

Model Type 
yi
Additional Notes 
It includes a unique merging method for better context performance without finetuning. Considerations for running this model include special quantization methods and context limitations.
Supported Languages 
en (English)
Input Output 
Input Format:
SYSTEM: {system_message} USER: {prompt} ASSISTANT:
Accepted Modalities:
text
Output Format:
text
LLM NameYi 34B 200K DARE Megamerge V8 GGUF
Repository ๐Ÿค—https://huggingface.co/TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF 
Model NameYi 34B 200K DARE MegaMerge V8
Model Creatorbrucethemoose
Base Model(s)  Yi 34B 200K DARE Megamerge V8   brucethemoose/Yi-34B-200K-DARE-megamerge-v8
Model Size34b
Required VRAM9.3 GB
Updated2024-11-21
MaintainerTheBloke
Model Typeyi
Model Files  10.3 GB   9.3 GB   12.8 GB   11.8 GB   18.1 GB   16.7 GB   15.0 GB   19.5 GB   20.7 GB   19.6 GB   23.7 GB   24.3 GB   23.7 GB   28.2 GB   36.5 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licenseother
Yi 34B 200K DARE Megamerge V8 GGUF (TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF)

Best Alternatives to Yi 34B 200K DARE Megamerge V8 GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Mergekit Slerp Fecxcxs GGUF0K / 8.4 GB440
...gekit Passthrough Zpfenfn GGUF0K / 8.7 GB340
CodeLlama 34B GGUF0K / 14.2 GB15232756
Yi 1.5 34B Chat GGUF0K / 12.8 GB1535
Nous Capybara 34B GGUF0K / 14.6 GB2792162
Nous Hermes 2 Yi 34B GGUF0K / 14.6 GB182641
...ous Capybara Limarpv3 34B GGUF0K / 14.6 GB97928
CodeFuse CodeLlama 34B GGUF0K / 14.2 GB1984720
34B Beta GGUF0K / 12.8 GB1243
Yi 34B Chat GGUF0K / 14.6 GB150265
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Yi-34B-200K-DARE-megamerge-v8-GGUF.

Rank the Yi 34B 200K DARE Megamerge V8 GGUF 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? 38149 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110