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

H2ogpt Oasst1 512 30B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  H2ogpt Oasst1 512 30B GPTQ   URL Share it on

  18   
  4-bit   Autotrain compatible Dataset:h2oai/h2ogpt-oig-oasst...   En   Gpt   Gptq   Instruct   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/h2ogpt-oasst1-512-30B-GPTQ 

H2ogpt Oasst1 512 30B GPTQ Benchmarks

LLME Score: 0.08624
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
H2ogpt Oasst1 512 30B GPTQ (TheBloke/h2ogpt-oasst1-512-30B-GPTQ)
🌟 Advertise your project 🚀

H2ogpt Oasst1 512 30B GPTQ Parameters and Internals

Model Type 
large language model, LLaMa
Use Cases 
Limitations:
Model may exhibit biases or produce content that is offensive or inappropriate., Model is not human and may produce incorrect or irrelevant responses.
Considerations:
Users should critically evaluate generated content.
Additional Notes 
Classical benchmarks align with base LLaMa 30B model.
Training Details 
Data Sources:
h2oai/h2ogpt-oig-oasst1-instruct-cleaned-v2
Model Architecture:
LlamaForCausalLM
Input Output 
Input Format:
Expected prompt format with : PROMPT :
Accepted Modalities:
text
Performance Tips:
A custom stopping string needs to be implemented as the model has no stopping token.
LLM NameH2ogpt Oasst1 512 30B GPTQ
Repository 🤗https://huggingface.co/TheBloke/h2ogpt-oasst1-512-30B-GPTQ 
Base Model(s)  H2ogpt Oasst1 512 30B HF   TheBloke/h2ogpt-oasst1-512-30B-HF
Model Size30b
Required VRAM16.9 GB
Updated2025-08-23
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  16.9 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.28.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to H2ogpt Oasst1 512 30B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...e Llama 30B Instruct 2048 GPTQ2K / 16.9 GB2322
WizardLM 30B Uncensored GPTQ2K / 16.9 GB57118
Llama 30B Instruct 20482K / 65.2 GB3074102
...ct 2048 Open Platypus 100steps2K / 65.2 GB18300
...azarus Instruct PL Lora Unload2K / 65.2 GB18630
...B 2048 Instruct PL Lora Unload2K / 65.2 GB18541
...lama 30B Instruct 2048 PL Lora2K / 65.2 GB18590
Llama 30B Instruct2K / 65.2 GB182823
...ge Llama 30B Instruct 2048 AWQ2K / 17.6 GB82
H2ogpt Oasst1 512 30B HF2K / 65 GB20342
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/h2ogpt-oasst1-512-30B-GPTQ.

Rank the H2ogpt Oasst1 512 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? 50836 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 v20241124
  Support LLM Explorer