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

Bloom 7b1 by bigscience

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

  9136   

Bloom 7b1 is an open-source language model by bigscience. Features: 7.1b LLM, VRAM: 14.2GB, License: bigscience-bloom-rail-1.0, HF Score: 39.2, LLM Explorer Score: 0.1, Arc: 41.1, HellaSwag: 62, MMLU: 26.3, TruthfulQA: 38.9, WinoGrande: 65.4, GSM8K: 1.4.

  Arxiv:1909.08053   Arxiv:2108.12409   Arxiv:2110.02861   Ak   Ar   As   Bloom   Bm   Bn   Ca   Code   Deploy:azure   Doi:10.57967/hf/2655   En   Endpoints compatible   Es   Eu   Fon   Fr   Gu   Hi   Id   Ig   Jax   Ki   Kn   Lg   Ln   Ml   Mr   Ne   Nso   Ny   Or   Pa   Pt   Pytorch   Region:us   Rn   Rw   Safetensors   Sharded   Sn   St   Sw   Ta   Te   Tensorflow   Tn   Ts   Tum   Tw   Ur   Vi   Wo   Xh   Yo   Zh   Zhs   Zht   Zu
Model Card on HF 🤗: https://huggingface.co/bigscience/bloom-7b1 

Bloom 7b1 Benchmarks

MMLU Pro: 1.16
GPQA: 1.9
MUSR: 1.92
BBH: 4.04
IFEval: 13.22 vs 88 (so35)-85%
ARC: 41.13 vs 96.7 (so35)-57.5%
HellaSwag: 62 vs 95.3 (gpt4)-34.9%
MMLU: 26.25 vs 88.3 (so35)-70.3%
TruthfulQA: 38.9 vs 59 (gpt4)-34.1%
WinoGrande: 65.43 vs 87.5 (gpt4)-25.2%
GSM8K: 1.36 vs 96.4 (so35)-98.6%
MATH Lvl 5: 0.53
LLME Score: 0.09921
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Bloom 7b1 (bigscience/bloom-7b1)
🌟 Advertise your project 🚀

Bloom 7b1 Parameters and Internals

Model Type 
Transformer-based Language Model, text generation
Use Cases 
Areas:
Public research on large language models
Applications:
Text generation, language exploration, information extraction, question answering, summarization
Primary Use Cases:
Pretrained base model for fine-tuning
Limitations:
Not intended for high-stakes settings or critical decisions.
Considerations:
Include appropriate disclaimers and obtain feedback for affected individuals.
Additional Notes 
Model trained on Jean Zay Supercomputer primarily powered by nuclear energy with emission and electricity usage reports forthcoming.
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 (Luganda), ln (Lingala), ml (Malayalam), mr (Marathi), ne (Nepali), nso (Northern Sotho), ny (Nyanja), or (Odia), pa (Punjabi), pt (Portuguese), rn (Kirundi), rw (Kinyarwanda), sn (Shona), st (Southern 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), zhs (Simplified Chinese), zht (Traditional Chinese), zu (Zulu)
Training Details 
Data Sources:
45 natural languages, 12 programming languages
Data Volume:
1.5TB (350B unique tokens)
Methodology:
Modified from Megatron-LM GPT2
Context Length:
2048
Training Time:
11th March 2022 to 5th July 2022
Hardware Used:
Jean Zay Supercomputer with 384 A100 80GB GPUs
Model Architecture:
Decoder-only architecture with layer normalization applied to word embeddings, 30 layers, 32 attention heads, ALiBI positional encodings with GeLU activation functions
Responsible Ai Considerations 
Fairness:
Model may overrepresent some viewpoints and underrepresent others.
Input Output 
Input Format:
Byte-level Byte Pair Encoding (BPE) algorithm
Accepted Modalities:
text
Output Format:
Standard natural language outputs
Performance Tips:
None specified
Release Notes 
Version:
1.0.0
Date:
11 July 2022
Notes:
Initial release for public research on large language models.
LLM NameBloom 7b1
Repository 🤗https://huggingface.co/bigscience/bloom-7b1 
Model Size7.1b
Required VRAM14.2 GB
Updated2026-03-15
Maintainerbigscience
Model Typebloom
Model Files  10.0 GB: 1-of-2   4.2 GB: 2-of-2   10.0 GB: 1-of-2   4.2 GB: 2-of-2
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 Version4.22.2
Tokenizer ClassBloomTokenizerFast
Padding Token<pad>
Vocabulary Size250880
Torch Data Typefloat16

Quantized Models of the Bloom 7b1

Model
Likes
Downloads
VRAM
Bloom 7b1 GPTQ 4bit G128287 GB
Bloom 7b1 Gptq 4bit2277 GB

Best Alternatives to Bloom 7b1

Best Alternatives
Context / RAM
Downloads
Likes
Bloomz 7b1 Mt Sft Chat0K / 14.2 GB77216
...ft Fpft Multilingual Bloom 7b10K / 28.2 GB101
Bloomz 7b10K / 14.1 GB2864147
Bloomz 7b1 Mt0K / 14.1 GB2399143
Bloomz 7b1 P30K / 14.1 GB1356
Note: green Score (e.g. "73.2") means that the model is better than bigscience/bloom-7b1.

Rank the Bloom 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? 52473 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer