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 HF by TheBloke

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

  2050   
  Autotrain compatible Dataset:h2oai/h2ogpt-oig-oasst...   En   Gpt   Instruct   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/TheBloke/h2ogpt-oasst1-512-30B-HF 

H2ogpt Oasst1 512 30B HF Benchmarks

LLME Score: 0.11967
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 HF (TheBloke/h2ogpt-oasst1-512-30B-HF)

H2ogpt Oasst1 512 30B HF Parameters and Internals

Model Type 
instruction-following, large language model
Use Cases 
Areas:
research
Limitations:
The model may produce incorrect, nonsensical, or irrelevant responses., Trained data may contain biases or inappropriate content
Additional Notes 
Only for research purposes. Users must ensure critical evaluation of generated content.
Supported Languages 
English (High)
Training Details 
Data Sources:
h2oai/h2ogpt-oig-oasst1-instruct-cleaned-v2, h2oai/openassistant_oasst1_h2ogpt
Methodology:
LORA fine-tuning on base LLaMa 30B model
Context Length:
512
Model Architecture:
LlamaForCausalLM with LoRA additions
Release Notes 
Notes:
The model is a 30 billion parameter instruction-following large language model merged with base LLaMa 30B using LoRA.
LLM NameH2ogpt Oasst1 512 30B HF
Repository 🤗https://huggingface.co/TheBloke/h2ogpt-oasst1-512-30B-HF 
Model Size30b
Required VRAM65 GB
Updated2025-02-22
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  7.9 GB: 1-of-9   7.8 GB: 2-of-9   8.0 GB: 3-of-9   8.0 GB: 4-of-9   7.8 GB: 5-of-9   8.0 GB: 6-of-9   7.8 GB: 7-of-9   8.0 GB: 8-of-9   1.7 GB: 9-of-9
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.28.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the H2ogpt Oasst1 512 30B HF

Model
Likes
Downloads
VRAM
H2ogpt Oasst1 512 30B GPTQ52316 GB

Best Alternatives to H2ogpt Oasst1 512 30B HF

Best Alternatives
Context / RAM
Downloads
Likes
Llama 30B Instruct 20482K / 65.2 GB3789102
...ct 2048 Open Platypus 100steps2K / 65.2 GB18810
...azarus Instruct PL Lora Unload2K / 65.2 GB18970
...B 2048 Instruct PL Lora Unload2K / 65.2 GB19011
...lama 30B Instruct 2048 PL Lora2K / 65.2 GB19010
Llama 30B Instruct2K / 65.2 GB191623
...pt Research Oig Oasst1 512 30B2K / 81.1 GB19663
Open Instruct Human Mix 30B2K / 130.5 GB151
Manticore 30B Chat Pyg Alpha0K / 65.2 GB199313
...nsored Instruct PL Lora Unload2K / 65.2 GB19050
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/h2ogpt-oasst1-512-30B-HF.

Rank the H2ogpt Oasst1 512 30B HF 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? 43508 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 v20241227
  Support LLM Explorer