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 Mt by bigscience

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

  2599   
  Arxiv:2211.01786   Ak   Ar   As   Autotrain compatible   Bloom   Bm   Bn   Ca   Code   Dataset:bigscience/xp3mt   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   Tensorboard   Tn   Ts   Tum   Tw   Ur   Vi   Wo   Xh   Yo   Zh   Zu
Model Card on HF 🤗: https://huggingface.co/bigscience/bloomz-7b1-mt 

Bloomz 7b1 Mt Benchmarks

ARC: 43.86 vs 96.7 (so35)-54.6%
HellaSwag: 62.91 vs 95.3 (gpt4)-34%
MMLU: 37.35 vs 88.3 (so35)-57.7%
TruthfulQA: 45.65 vs 59 (gpt4)-22.6%
WinoGrande: 63.06 vs 87.5 (gpt4)-27.9%
LLME Score: 0.1187
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Bloomz 7b1 Mt (bigscience/bloomz-7b1-mt)

Bloomz 7b1 Mt Parameters and Internals

Model Type 
text-generation, multilingual
Use Cases 
Areas:
Research, Commercial applications
Applications:
Text generation, Machine translation
Primary Use Cases:
Translation detection, Sentiment analysis
Additional Notes 
Model capable of crosslingual generalization.
Supported Languages 
ak (Available), ar (Available), as (Available), bm (Available), bn (Available), ca (Available), code (Special), en (Available), es (Available), eu (Available), fon (Available), fr (Available), gu (Available), hi (Available), id (Available), ig (Available), ki (Available), kn (Available), lg (Available), ln (Available), ml (Available), mr (Available), ne (Available), nso (Available), ny (Available), or (Available), pa (Available), pt (Available), rn (Available), rw (Available), sn (Available), st (Available), sw (Available), ta (Available), te (Available), tn (Available), ts (Available), tum (Available), tw (Available), ur (Available), vi (Available), wo (Available), xh (Available), yo (Available), zh (Available), zu (Available)
Training Details 
Data Sources:
bigscience/xP3
Data Volume:
4.19 billion tokens
Methodology:
Fine-tuned using multitask learning
Hardware Used:
64 A100 80GB GPUs with 8 GPUs per node using NVLink 4 inter-gpu connects, 4 OmniPath links
Model Architecture:
GPT-style architecture
Input Output 
Input Format:
Multilingual natural language prompts
Accepted Modalities:
text
Output Format:
Generated text completion or translation
Performance Tips:
Clearly define where inputs end and outputs begin in prompts.
LLM NameBloomz 7b1 Mt
Repository 🤗https://huggingface.co/bigscience/bloomz-7b1-mt 
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 Mt

Best Alternatives
Context / RAM
Downloads
Likes
Bloomz 7b1 Mt Sft Chat0K / 14.2 GB118416
Bloom 7b10K / 14.2 GB76626201
Bloomz 7b10K / 14.1 GB11727137
Note: green Score (e.g. "73.2") means that the model is better than bigscience/bloomz-7b1-mt.

Rank the Bloomz 7b1 Mt 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