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

Weblab 10B Instruction Sft by matsuo-lab

 »  All LLMs  »  matsuo-lab  »  Weblab 10B Instruction Sft   URL Share it on

  1766   
  Autotrain compatible   Endpoints compatible   Gpt neox   Instruct   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/matsuo-lab/weblab-10b-instruction-sft 

Weblab 10B Instruction Sft Benchmarks

ARC: 40.1 vs 96.7 (so35)-58.5%
HellaSwag: 65.3 vs 95.3 (gpt4)-31.5%
MMLU: 26.66 vs 88.3 (so35)-69.8%
TruthfulQA: 36.79 vs 59 (gpt4)-37.6%
WinoGrande: 64.09 vs 87.5 (gpt4)-26.8%
GSM8K: 1.82 vs 96.4 (so35)-98.1%
LLME Score: 0.1601
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Weblab 10B Instruction Sft (matsuo-lab/weblab-10b-instruction-sft)
🌟 Advertise your project 🚀

Weblab 10B Instruction Sft Parameters and Internals

Model Type 
text generation, multilingual
Use Cases 
Applications:
Research, Natural Language Processing tasks
Supported Languages 
primary (Japanese), additional ()
Training Details 
Data Sources:
Japanese C4, The Pile, Alpaca (English), Alpaca (Japanese translation), Flan 2021 (English), Flan CoT (English), Flan Dialog (English)
Data Volume:
600B tokens
Methodology:
Instruction-supervised-finetuning
Model Architecture:
36-layer, 4864-hidden-size transformer-based language model
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Utilize a GPU with at least float16 precision for optimal performance.
LLM NameWeblab 10B Instruction Sft
Repository 🤗https://huggingface.co/matsuo-lab/weblab-10b-instruction-sft 
Model Size10b
Required VRAM21.4 GB
Updated2025-09-16
Maintainermatsuo-lab
Model Typegpt_neox
Instruction-BasedYes
Model Files  9.9 GB: 1-of-3   10.0 GB: 2-of-3   1.5 GB: 3-of-3
Model ArchitectureGPTNeoXForCausalLM
Licensecc-by-nc-4.0
Context Length2048
Model Max Length2048
Transformers Version4.28.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size50277
Torch Data Typefloat16

Quantized Models of the Weblab 10B Instruction Sft

Model
Likes
Downloads
VRAM
...eblab 10B Instruction Sft GPTQ1317946 GB

Best Alternatives to Weblab 10B Instruction Sft

Best Alternatives
Context / RAM
Downloads
Likes
...eblab 10B Instruction Sft GPTQ2K / 6.3 GB179413

Rank the Weblab 10B Instruction Sft 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? 51408 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 v20241124
  Support LLM Explorer