Open Instruct Human Mix 65B GPTQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Open Instruct Human Mix 65B GPTQ   URL Share it on

  Arxiv:2302.13971   Arxiv:2304.07327   Arxiv:2306.04751   4-bit   Autotrain compatible Base model:allenai/open-instru... Base model:quantized:allenai/o... Dataset:databricks/databricks-...   Dataset:openassistant/oasst1   En   Fp16   Gptq   Instruct   Llama   Quantized   Region:us   Safetensors

Open Instruct Human Mix 65B GPTQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Open Instruct Human Mix 65B GPTQ Parameters and Internals

LLM NameOpen Instruct Human Mix 65B GPTQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/open-instruct-human-mix-65B-GPTQ 
Model NameOpen Instruct Human Mix 65B
Model CreatorAllen Institute for AI
Base Model(s)  Open Instruct Human Mix 65B   allenai/open-instruct-human-mix-65b
Model Size65b
Required VRAM33.5 GB
Updated2024-10-09
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  33.5 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typefp16|gptq
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.35.2
Vocabulary Size32001
Torch Data Typefloat16
Open Instruct Human Mix 65B GPTQ (TheBloke/open-instruct-human-mix-65B-GPTQ)

Best Alternatives to Open Instruct Human Mix 65B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...stage Llama1 65B Instruct GPTQ2K / 34.7 GB33
Lite Oute 1 65M Instruct2K / 0.3 GB710
...pen Instruct Human Mix 65B AWQ2K / 34.7 GB130
Llama 65B Instruct2K / 130.4 GB121512
...pstage Llama1 65B Instruct AWQ2K / 34.7 GB31
Open Instruct Human Mix 65B2K / 260.8 GB12364
Open Instruct Sharegpt 65B2K / 260.8 GB42
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/open-instruct-human-mix-65B-GPTQ.

Rank the Open Instruct Human Mix 65B 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  

What open-source LLMs or SLMs are you in search of? 36966 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803