KAI 7B Instruct GPTQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  KAI 7B Instruct GPTQ   URL Share it on

  4-bit   Autotrain compatible Base model:keynote-technology/...   Code   Conversational   Finetuned   Gptq   Instruct   License:apache-2.0   Mistral   Quantized   Region:us   Safetensors

Rank the KAI 7B Instruct GPTQ 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  
KAI 7B Instruct GPTQ (TheBloke/KAI-7B-Instruct-GPTQ)

Best Alternatives to KAI 7B Instruct GPTQ

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
Maxine 7B 0401 Stock76.7332K / 14.4 GB8911
CalmExperiment 7B Slerp76.6732K / 14.4 GB9020
Myriad 7B Slerp76.6632K / 14.4 GB9160
Versatile 7B76.6632K / 14.5 GB7780
Calme 7B Instruct V0.976.6232K / 14.4 GB14839
Calme 7B Instruct V0.276.6132K / 14.5 GB112811
Calme 7B Instruct V0.376.532K / 14.4 GB8465
Calme 7B Instruct V0.1.176.4932K / 14.4 GB7610
Calme 7B Instruct V0.576.0532K / 14.4 GB91711
Metis Chat Instruct 7B74.6632K / 14.4 GB9180
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/KAI-7B-Instruct-GPTQ.

KAI 7B Instruct GPTQ Parameters and Internals

LLM NameKAI 7B Instruct GPTQ
RepositoryOpen on ๐Ÿค— 
Model NameKai 7B Instruct
Model CreatorKeynote Technology
Base Model(s)  Keynote-Technology/KAI-7B-Instruct   Keynote-Technology/KAI-7B-Instruct
Model Size7b
Required VRAM4.2 GB
Updated2024-07-01
MaintainerTheBloke
Model Typemistral
Instruction-BasedYes
Model Files  4.2 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Initializer Range0.02
Torch Data Typebfloat16

What open-source LLMs or SLMs are you in search of? 34238 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801