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

Bloomz 7b1 by bigscience

 »  All LLMs  »  bigscience  »  Bloomz 7b1   URL Share it on

  11727   
  Arxiv:2211.01786   Ak   Ar   As   Autotrain compatible   Bloom   Bm   Bn   Ca   Code   Dataset:bigscience/xp3   En   Endpoints compatible   Es   Eu   Fon   Fr   Gu   Hi   Id   Ig   Ki   Kn   Lg   Ln   Ml   Model-index   Mr   Ne   Nso   Ny   Or   Pa   Pt   Pytorch   Region:us   Rn   Rw   Safetensors   Sn   St   Sw   Ta   Te   Tn   Ts   Tum   Tw   Ur   Vi   Wo   Xh   Yo   Zh   Zu
Model Card on HF 🤗: https://huggingface.co/bigscience/bloomz-7b1 

Bloomz 7b1 Benchmarks

ARC: 42.49 vs 96.7 (so35)-56.1%
HellaSwag: 63.01 vs 95.3 (gpt4)-33.9%
MMLU: 37.85 vs 88.3 (so35)-57.1%
TruthfulQA: 45.2 vs 59 (gpt4)-23.4%
WinoGrande: 64.64 vs 87.5 (gpt4)-26.1%
GSM8K: 0.08 vs 96.4 (so35)-99.9%
LLME Score: 0.13799
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Bloomz 7b1 (bigscience/bloomz-7b1)

Bloomz 7b1 Parameters and Internals

Model Type 
Multilingual Language Model, Text Generation
Use Cases 
Areas:
Text Translation, Text Sentiment Analysis, Sentence Completion
Primary Use Cases:
Coreference Resolution, Natural Language Inference, Program Synthesis, Sentence Completion
Limitations:
Performance may vary depending on prompt clarity
Considerations:
Prompt engineering is crucial for optimal performance.
Additional Notes 
Multitask finetuned on xP3mt for non-English prompting
Supported Languages 
ak (Akan), ar (Arabic), as (Assamese), bm (Bambara), bn (Bengali), ca (Catalan), code (Programming Languages), en (English), es (Spanish), eu (Basque), fon (Fon), fr (French), gu (Gujarati), hi (Hindi), id (Indonesian), ig (Igbo), ki (Kikuyu), kn (Kannada), lg (Ganda), ln (Lingala), ml (Malayalam), mr (Marathi), ne (Nepali), nso (Northern Sotho), ny (Nyanja), or (Odia), pa (Punjabi), pt (Portuguese), rn (Rundi), rw (Kinyarwanda), sn (Shona), st (Sotho), sw (Swahili), ta (Tamil), te (Telugu), tn (Tswana), ts (Tsonga), tum (Tumbuka), tw (Twi), ur (Urdu), vi (Vietnamese), wo (Wolof), xh (Xhosa), yo (Yoruba), zh (Chinese), zu (Zulu)
Training Details 
Data Sources:
bigscience/xP3 dataset
Data Volume:
4.19 billion tokens
Methodology:
Finetuned on multilingual crosslingual task mixture (xP3)
Hardware Used:
64 A100 80GB GPUs, AMD CPUs with 512GB memory per node
Model Architecture:
Same as bloom-7b1
Input Output 
Input Format:
Natural language prompts
Accepted Modalities:
Text, Programming Languages
Output Format:
Text-based responses
Performance Tips:
Consider including full-stop punctuation in prompts to clarify end
LLM NameBloomz 7b1
Repository 🤗https://huggingface.co/bigscience/bloomz-7b1 
Model Size7.1b
Required VRAM14.1 GB
Updated2024-12-22
Maintainerbigscience
Model Typebloom
Model Files  14.1 GB   14.1 GB
Supported Languagesak ar as bm bn ca code en es eu fr gu hi id ig ki kn lg ln ml mr ne ny or pa pt rn rw sn st sw ta te tn ts tw ur vi wo xh yo zh zu
Model ArchitectureBloomForCausalLM
Licensebigscience-bloom-rail-1.0
Transformers Version4.21.0.dev0
Tokenizer ClassBloomTokenizerFast
Padding Token<pad>
Vocabulary Size250880

Best Alternatives to Bloomz 7b1

Best Alternatives
Context / RAM
Downloads
Likes
Bloomz 7b1 Mt Sft Chat0K / 14.2 GB118416
Bloom 7b10K / 14.2 GB76626201
Bloomz 7b1 Mt0K / 14.1 GB2599140
Note: green Score (e.g. "73.2") means that the model is better than bigscience/bloomz-7b1.

Rank the Bloomz 7b1 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? 40066 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 v20241217
  Support LLM Explorer