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

Openbuddy Zero 56B V21.2 32K by OpenBuddy

 »  All LLMs  »  OpenBuddy  »  Openbuddy Zero 56B V21.2 32K   URL Share it on

  3628   
  Autotrain compatible   Conversational   De   En   Endpoints compatible   Fi   Fr   It   Ja   Ko   Llama   Llama-3   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/OpenBuddy/openbuddy-zero-56b-v21.2-32k 

Openbuddy Zero 56B V21.2 32K Benchmarks

MMLU Pro: 37.77
GPQA: 9.06
MUSR: 12.78
BBH: 44.8
IFEval: 50.57 vs 88 (so35)-42.5%
MATH Lvl 5: 16.24
LLME Score: 0.30925
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Openbuddy Zero 56B V21.2 32K (OpenBuddy/openbuddy-zero-56b-v21.2-32k)

Openbuddy Zero 56B V21.2 32K Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
Chatbot, Customer service, Multilingual communication
Limitations:
Not suitable for critical or high-stakes situations
Considerations:
Users should be aware of the model's limitations and exercise caution in sensitive areas
Supported Languages 
zh (Proficient), en (Proficient), fr (Proficient), de (Proficient), ja (Proficient), ko (Proficient), it (Proficient), fi (Proficient)
Training Details 
Methodology:
Multilingual dataset training using the tokenizer from Yi-34B-32K
Input Output 
Input Format:
Uses special tokens like <|role|>, <|says|>
Accepted Modalities:
text
Output Format:
Text responses
Performance Tips:
Use fast tokenizer from `transformers` enabled by default
LLM NameOpenbuddy Zero 56B V21.2 32K
Repository 🤗https://huggingface.co/OpenBuddy/openbuddy-zero-56b-v21.2-32k 
Model Size56b
Required VRAM114.1 GB
Updated2025-02-22
MaintainerOpenBuddy
Model Typellama
Model Files  4.8 GB: 1-of-24   4.8 GB: 2-of-24   5.0 GB: 3-of-24   4.8 GB: 4-of-24   4.8 GB: 5-of-24   5.0 GB: 6-of-24   4.8 GB: 7-of-24   4.8 GB: 8-of-24   5.0 GB: 9-of-24   4.8 GB: 10-of-24   4.8 GB: 11-of-24   5.0 GB: 12-of-24   4.8 GB: 13-of-24   4.8 GB: 14-of-24   5.0 GB: 15-of-24   4.8 GB: 16-of-24   4.8 GB: 17-of-24   5.0 GB: 18-of-24   4.8 GB: 19-of-24   4.8 GB: 20-of-24   5.0 GB: 21-of-24   4.8 GB: 22-of-24   4.8 GB: 23-of-24   2.3 GB: 24-of-24
Supported Languageszh en fr de ja ko it fi
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version4.42.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<|pad0|>
Vocabulary Size64256
Torch Data Typebfloat16

Best Alternatives to Openbuddy Zero 56B V21.2 32K

Best Alternatives
Context / RAM
Downloads
Likes
Nyun C2 Llama3 56B8K / 111.7 GB476711

Rank the Openbuddy Zero 56B V21.2 32K 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? 43470 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