LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

OpenAssistant SFT 7 Llama 30B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  OpenAssistant SFT 7 Llama 30B GPTQ   URL Share it on

  726   
  Arxiv:2304.07327   4-bit   Autotrain compatible   Gptq   Llama   Quantized   Region:us   Safetensors

OpenAssistant SFT 7 Llama 30B GPTQ Benchmarks

ARC: 60.58 vs 96.7 (so35)-37.4%
HellaSwag: 82.17 vs 95.3 (gpt4)-13.8%
MMLU: 57.93 vs 88.3 (so35)-34.4%
TruthfulQA: 46.94 vs 59 (gpt4)-20.4%
WinoGrande: 78.61 vs 87.5 (gpt4)-10.2%
GSM8K: 29.8 vs 96.4 (so35)-69.1%
LLME Score: 0.1503
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

OpenAssistant SFT 7 Llama 30B GPTQ Parameters and Internals

LLM NameOpenAssistant SFT 7 Llama 30B GPTQ
Repository 🤗https://huggingface.co/TheBloke/OpenAssistant-SFT-7-Llama-30B-GPTQ 
Base Model(s)  ...enAssistant SFT 7 Llama 30B HF   TheBloke/OpenAssistant-SFT-7-Llama-30B-HF
Model Size30b
Required VRAM16.9 GB
Updated2024-09-19
MaintainerTheBloke
Model Typellama
Model Files  16.9 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.29.0.dev0
Tokenizer ClassLlamaTokenizer
End of Sentence Token</s>
Unk Token</s>
Vocabulary Size32016
Torch Data Typefloat16
OpenAssistant SFT 7 Llama 30B GPTQ (TheBloke/OpenAssistant-SFT-7-Llama-30B-GPTQ)

Best Alternatives to OpenAssistant SFT 7 Llama 30B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
GPlatty 30B SuperHOT 8K GPTQ8K / 16.9 GB97
Platypus 30B SuperHOT 8K GPTQ8K / 16.9 GB154
... 30B Supercot SuperHOT 8K GPTQ8K / 16.9 GB105
Tulu 30B SuperHOT 8K GPTQ8K / 16.9 GB205
Yayi2 30B Llama GPTQ4K / 17 GB82
WizardLM 30B GPTQ2K / 16.9 GB72819
Llama 30B FINAL MODEL MINI2K / 19.4 GB41
...2 Llama 30B 7K Steps Gptq 2bit2K / 9.5 GB62
WizardLM 30B V1.0 GPTQ2K / 16.9 GB91
...2 Llama 30B 7K Steps Gptq 4bit2K / 17.5 GB93
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/OpenAssistant-SFT-7-Llama-30B-GPTQ.

Rank the OpenAssistant SFT 7 Llama 30B GPTQ Capabilities

🆘 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! 🌟

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? 36073 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803
  Support LLM Explorer