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

Openchat 3.5 16K GPTQ by TheBloke

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

 ยป  All LLMs  ยป  TheBloke  ยป  Openchat 3.5 16K GPTQ   URL Share it on

  Arxiv:2212.10560   Arxiv:2303.08774   Arxiv:2309.11235   4-bit   Autotrain compatible Base model:nurtureai/openchat ...   Gptq   License:apache-2.0   Mistral   Quantized   Region:us   Safetensors

Openchat 3.5 16K GPTQ Benchmarks

Rank the Openchat 3.5 16K 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  
Openchat 3.5 16K GPTQ (TheBloke/openchat_3.5-16k-GPTQ)

Best Alternatives to Openchat 3.5 16K GPTQ

Best Alternatives
HF Rank
Garrulus GPTQ65.932K / 4.2 GB1983
Garrulus AWQ65.932K / 4.2 GB582
Go Bruins V2.1.1 AWQ65.732K / 4.2 GB31
Turdus GPTQ65.532K / 4.2 GB773
Quantum V0.01 GPTQ65.532K / 4.2 GB52
Mistral Ft Optimized 1218 GPTQ63.132K / 4.2 GB83
Go Bruins V2 GPTQ63.132K / 4.2 GB32
Valkyrie V1 GPTQ63.132K / 4.2 GB60
Mistral Ft Optimized 1218 AWQ63.132K / 4.2 GB31
Go Bruins GPTQ6332K / 4.2 GB31
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/openchat_3.5-16k-GPTQ.

Openchat 3.5 16K GPTQ Parameters and Internals

LLM NameOpenchat 3.5 16K GPTQ
RepositoryOpen on ๐Ÿค— 
Model NameOpenchat 3.5 16K
Model CreatorNurtureAI
Base Model(s)  Openchat 3.5 16K   NurtureAI/openchat_3.5-16k
Model Size1.2b
Required VRAM4.2 GB
Model Typemistral
Model Files  4.2 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.35.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32002
Initializer Range0.02
Torch Data Typefloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003