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

Blue Orchid 2x7b 6.0bpw H6 EXL2 by LoneStriker

What open-source LLMs or SLMs are you in search of? 18732 in total.

 ยป  All LLMs  ยป  LoneStriker  ยป  Blue Orchid 2x7b 6.0bpw H6 EXL2   URL Share it on

  Autotrain compatible   Endpoints compatible   Exl2   License:apache-2.0   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Rank the Blue Orchid 2x7b 6.0bpw 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  
Blue Orchid 2x7b 6.0bpw H6 EXL2 (LoneStriker/Blue-Orchid-2x7b-6.0bpw-h6-exl2)

Best Alternatives to Blue Orchid 2x7b 6.0bpw H6 EXL2

Best Alternatives
HF Rank
Multimaster 7B V273.3332K / 142.5 GB3230
Amadeus V0.171.428K / 48.3 GB20475
...ixtral 2x7b DPO 3.0bpw H6 EXL232K / 5.1 GB50
...ixtral 2x7b DPO 5.0bpw H6 EXL232K / 8.3 GB61
...ixtral 2x7b DPO 6.0bpw H6 EXL232K / 9.8 GB11
...t V0.2 2x7B MoE 6.0bpw H6 EXL232K / 9.9 GB11
Buttercup 4x7B 4bpw EXL232K / 12.4 GB60
...ixtral 2x7b DPO 8.0bpw H8 EXL232K / 13 GB31
Buttercup 4x7B 6bpw EXL232K / 18.4 GB32
BurningBruce 003 EXL2 B8.032K / 24.3 GB11
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Blue-Orchid-2x7b-6.0bpw-h6-exl2.

Blue Orchid 2x7b 6.0bpw H6 EXL2 Parameters and Internals

LLM NameBlue Orchid 2x7b 6.0bpw H6 EXL2
RepositoryOpen on ๐Ÿค— 
Model Size7b
Required VRAM9.8 GB
Model Typemixtral
Model Files  8.6 GB: 1-of-2   1.2 GB: 2-of-2
Quantization Typeexl2
Model ArchitectureMixtralForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Initializer Range0.02
Torch Data Typebfloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003