LLM Explorer: A Curated Large Language Model Directory and Analytics  // 

Yi 34B 200K RPMerge EXL2 40bpw by brucethemoose

What open-source LLMs or SLMs are you in search of? 18857 in total.

 ยป  All LLMs  ยป  brucethemoose  ยป  Yi 34B 200K RPMerge EXL2 40bpw   URL Share it on

  Merged Model   Arxiv:2306.01708   Arxiv:2311.03099   Autotrain compatible   En   Endpoints compatible   Exl2   Exllama   Exllamav2   License:other   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Yi

Rank the Yi 34B 200K RPMerge EXL2 40bpw 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  
Yi 34B 200K RPMerge EXL2 40bpw (brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw)

Best Alternatives to Yi 34B 200K RPMerge EXL2 40bpw

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
UNA SimpleSmaug 34B V1beta77.4132K / 69.2 GB19410
Smaug 34B V0.177.29195K / 69.2 GB572337
Luminex 32B V0.277.1932K / 68.9 GB798
Luminex 34B V0.177.06195K / 68.9 GB1598
Pearl 34B Ties75.48195K / 67.8 GB1271
Bagel Hermes 34B Slerp75.24195K / 68.9 GB39450
HermesBagel 34B V0.175.154K / 68.9 GB17501
Yi 34B X275.02195K / 68.9 GB13440
MetaMath Bagel DPO 34B74.8195K / 69.2 GB225411
Nontoxic Bagel 34B V0.274.69195K / 68.7 GB226634
Note: green Score (e.g. "73.2") means that the model is better than brucethemoose/Yi-34B-200K-RPMerge-exl2-40bpw.

Yi 34B 200K RPMerge EXL2 40bpw Parameters and Internals

LLM NameYi 34B 200K RPMerge EXL2 40bpw
RepositoryOpen on ๐Ÿค— 
Merged ModelYes
Model Size34b
Required VRAM18.1 GB
Updated2024-02-28
Maintainerbrucethemoose
Model Typellama
Model Files  4.3 GB: 1-of-5   4.3 GB: 2-of-5   4.3 GB: 3-of-5   4.3 GB: 4-of-5   0.9 GB: 5-of-5
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length200000
Model Max Length200000
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64002
Initializer Range0.02
Torch Data Typebfloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003