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

StableBeluga2 70B AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  StableBeluga2 70B AWQ   URL Share it on

  7   
  Arxiv:2306.02707   Arxiv:2307.09288   4-bit   Autotrain compatible   Awq Base model:quantized:stability... Base model:stabilityai/stableb... Dataset:conceptofmind/cot subm... Dataset:conceptofmind/flan2021... Dataset:conceptofmind/niv2 sub... Dataset:conceptofmind/t0 submi...   En   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/StableBeluga2-70B-AWQ 

StableBeluga2 70B AWQ Benchmarks

LLME Score: 0.11194
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
StableBeluga2 70B AWQ (TheBloke/StableBeluga2-70B-AWQ)
🌟 Advertise your project 🚀

StableBeluga2 70B AWQ Parameters and Internals

Model Type 
llama
Training Details 
Data Sources:
conceptofmind/cot_submix_original, conceptofmind/flan2021_submix_original, conceptofmind/t0_submix_original, conceptofmind/niv2_submix_original
Methodology:
Supervised fine-tuning on an Orca-style Dataset.
LLM NameStableBeluga2 70B AWQ
Repository 🤗https://huggingface.co/TheBloke/StableBeluga2-70B-AWQ 
Model NameStableBeluga2
Model CreatorStability AI
Base Model(s)  StableBeluga2   stabilityai/StableBeluga2
Model Size70b
Required VRAM36.6 GB
Updated2025-08-20
MaintainerTheBloke
Model Typellama
Model Files  9.9 GB: 1-of-4   9.9 GB: 2-of-4   9.9 GB: 3-of-4   6.9 GB: 4-of-4
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.32.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to StableBeluga2 70B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...0B Instruct Gradient 1048K AWQ1024K / 39.9 GB31
...70B Instruct Gradient 262K AWQ256K / 39.9 GB60
Llama 3.3 70B Instruct AWQ128K / 39.9 GB2512716
Llama 3.3 70B Instruct AWQ128K / 39.9 GB1704235
...lama 3.3 70B Instruct AWQ INT4128K / 39.9 GB385025
... SauerkrautLM 70B Instruct AWQ128K / 39.9 GB265
MultiVerse 70B AWQ32K / 41.3 GB32
Opus V1.2 70B AWQ32K / 36.7 GB31
QuartetAnemoi 70B T0.0001 AWQ31K / 36.7 GB31
Senku 70B AWQ 4bit GEMM31K / 36.7 GB31
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/StableBeluga2-70B-AWQ.

Rank the StableBeluga2 70B AWQ 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? 50767 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