Yi 34B 200K 5.0bpw H6 EXL2 by LoneStriker

 ยป  All LLMs  ยป  LoneStriker  ยป  Yi 34B 200K 5.0bpw H6 EXL2   URL Share it on

  Autotrain compatible   Custom code   Exl2   Pytorch   Quantized   Region:us   Sharded   Tensorflow   Yi

Yi 34B 200K 5.0bpw 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 34B 200K 5.0bpw H6 EXL2 (LoneStriker/Yi-34B-200K-5.0bpw-h6-exl2)

Yi 34B 200K 5.0bpw H6 EXL2 Parameters and Internals

Model Type 
Large Language Model
Supported Languages 
English (Bilingual), Chinese (Bilingual)
Release Notes 
Version:
Yi-6B-200K
Date:
2023/11/06
Notes:
Base model release with 200K context length
Version:
Yi-6B
Date:
2023/11/02
Notes:
Base model release
LLM NameYi 34B 200K 5.0bpw H6 EXL2
Repository ๐Ÿค—https://huggingface.co/LoneStriker/Yi-34B-200K-5.0bpw-h6-exl2 
Model Size34b
Required VRAM22.3 GB
Updated2024-12-26
MaintainerLoneStriker
Model TypeYi
Model Files  8.6 GB: 1-of-3   8.6 GB: 2-of-3   5.1 GB: 3-of-3
Quantization Typeexl2
Model ArchitectureYiForCausalLM
Licenseother
Context Length200000
Model Max Length200000
Transformers Version4.34.0
Tokenizer ClassYiTokenizer
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to Yi 34B 200K 5.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...lpaca Rpv3 Scipy 4bpw Hb6 EXL2195K / 18.7 GB152
...200K Alpaca Rpv3 4bpw Hb6 EXL2195K / 18.7 GB202
Yi 34B 200K 4.65bpw H6 EXL2195K / 20.8 GB116
Yi 34B 200K 4.0bpw H6 EXL2195K / 18.1 GB114
Yi 34B 200K 8.0bpw H8 EXL2195K / 34.8 GB113
Deepsex 34B 4bpw H8 EXL24K / 18.1 GB254
Deepsex 34B 4bpw H6 EXL24K / 18.1 GB113
Yi 34B 5.0bpw H6 EXL24K / 22.2 GB113
Yi 34B 4.0bpw H6 EXL24K / 18.1 GB102
Yi 34B 8.0bpw H8 EXL24K / 34.9 GB141
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Yi-34B-200K-5.0bpw-h6-exl2.

Rank the Yi 34B 200K 5.0bpw 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? 40248 in total.

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