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

Vicuna 7B V1.3 SuperHOT 8K Fp16 by TheBloke

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

 ยป  All LLMs  ยป  TheBloke  ยป  Vicuna 7B V1.3 SuperHOT 8K Fp16   URL Share it on

  Arxiv:2302.13971   Arxiv:2306.05685   Autotrain compatible   Custom code   Ext 8k   Fp16   License:other   Llama   Pytorch   Quantized   Region:us   Sharded

Rank the Vicuna 7B V1.3 SuperHOT 8K Fp16 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  
Vicuna 7B V1.3 SuperHOT 8K Fp16 (TheBloke/Vicuna-7B-v1-3-SuperHOT-8K-fp16)

Best Alternatives to Vicuna 7B V1.3 SuperHOT 8K Fp16

Best Alternatives
HF Rank
Bagel DPO 7B V0.167.9532K / 14.4 GB234740
Internlm2 7B Llama66.9432K / 15.5 GB15998
Llama2 Init Mistral60.984K / 14.4 GB25510
A I 0xtom 7B Slerp60.4632K / 14.4 GB2580
AIRIC The Mistral59.9532K / 14.4 GB20673
Synatra RP Orca 2 7B V0.159.554K / 13.5 GB32026
Deepseek Llm 7B Chat59.274K / 13.9 GB726458
UltraQwen 7B59.1732K / 15.4 GB17712
...rnlm2 20B Llama 4.0bpw H6 EXL258.532K / 11 GB51
Mistral 7B Guanaco1k Ep258.1332K / 29 GB32713
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Vicuna-7B-v1-3-SuperHOT-8K-fp16.

Vicuna 7B V1.3 SuperHOT 8K Fp16 Parameters and Internals

LLM NameVicuna 7B V1.3 SuperHOT 8K Fp16
RepositoryOpen on ๐Ÿค— 
Model Size7b
Required VRAM13.5 GB
Model Typellama
Model Files  10.0 GB: 1-of-2   3.5 GB: 2-of-2
Context Length8k
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.30.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Initializer Range0.02
Torch Data Typefloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003