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 Sft Chat by cmarkea

 »  All LLMs  »  cmarkea  »  Bloomz 7b1 Mt Sft Chat   URL Share it on

  23   
  Arxiv:2001.09977   Arxiv:2012.15613   Autotrain compatible   Bloom Dataset:ehartford/wizard vicun...   Dataset:laion/oig   Dataset:shahules786/orca-chat Dataset:timdettmers/openassist...   En   Endpoints compatible   Fr   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cmarkea/bloomz-7b1-mt-sft-chat 

Bloomz 7b1 Mt Sft Chat Benchmarks

ARC: 44.03 vs 96.7 (so35)-54.5%
HellaSwag: 62.6 vs 95.3 (gpt4)-34.3%
MMLU: 38.64 vs 88.3 (so35)-56.2%
TruthfulQA: 44.34 vs 59 (gpt4)-24.8%
WinoGrande: 63.3 vs 87.5 (gpt4)-27.7%
GSM8K: 0.53 vs 96.4 (so35)-99.5%
LLME Score: 0.15555
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 Sft Chat (cmarkea/bloomz-7b1-mt-sft-chat)

Bloomz 7b1 Mt Sft Chat Parameters and Internals

Model Type 
text generation, chatbot
Use Cases 
Areas:
research, commercial applications
Applications:
chatbots, text generation tasks
Primary Use Cases:
chatbot context
Limitations:
Performance in languages other than French and English is not guaranteed., Degradation in performance due to change in datatype from float16 to bfloat16.
Additional Notes 
The tokenizer designed for multilingual contexts improves efficiency.
Supported Languages 
French (fluent), English (fluent)
Training Details 
Data Sources:
ehartford/wizard_vicuna_70k_unfiltered, shahules786/orca-chat, timdettmers/openassistant-guanaco, laion/OIG
Data Volume:
0.9 billion tokens
Methodology:
Fine-tuned on French and English data
Context Length:
2048
Hardware Used:
1 x A100 40GB, 4 x A100 40GB
Model Architecture:
Transposition from float16 to bfloat16 for improved efficiency
Input Output 
Input Format:
~~[human prompt] ~~
Accepted Modalities:
text
Output Format:
Text response with chatbot capabilities
Performance Tips:
Precede individual prompt by EOS token (</s>) and generated part by BOS token (<s>).
Release Notes 
Version:
bloomz-7b1-mt-sft-chat
Date:
2023
Notes:
Fine-tuned model for chatbot applications in French and English.
LLM NameBloomz 7b1 Mt Sft Chat
Repository 🤗https://huggingface.co/cmarkea/bloomz-7b1-mt-sft-chat 
Model Size7.1b
Required VRAM14.2 GB
Updated2025-06-01
Maintainercmarkea
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 Languagesfr en
Model ArchitectureBloomForCausalLM
Licensebigscience-bloom-rail-1.0
Transformers Version4.32.0
Tokenizer ClassBloomTokenizer
Padding Token<pad>
Vocabulary Size250880
Torch Data Typebfloat16

Best Alternatives to Bloomz 7b1 Mt Sft Chat

Best Alternatives
Context / RAM
Downloads
Likes
...ft Fpft Multilingual Bloom 7b10K / 28.2 GB181
Bloomz 7b1 Mt0K / 14.1 GB25759140
Bloomz 7b10K / 14.1 GB6139144
Bloom 7b10K / 14.2 GB9048204
Bloomz 7b1 P30K / 14.1 GB396
Note: green Score (e.g. "73.2") means that the model is better than cmarkea/bloomz-7b1-mt-sft-chat.

Rank the Bloomz 7b1 Mt Sft Chat 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? 47753 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