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 GPTQ by dahara1

 »  All LLMs  »  dahara1  »  Weblab 10B Instruction Sft GPTQ   URL Share it on

  1794   
  4bit   Autotrain compatible   Gpt neox   Gptq   Instruct   Ja   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/dahara1/weblab-10b-instruction-sft-GPTQ 

Weblab 10B Instruction Sft GPTQ 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: 0.15982
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 GPTQ (dahara1/weblab-10b-instruction-sft-GPTQ)
🌟 Advertise your project 🚀

Weblab 10B Instruction Sft GPTQ Parameters and Internals

Model Type 
GPT-NeoX, quantized
Use Cases 
Areas:
research, commercial applications
Applications:
language generation, instruction following
Primary Use Cases:
Text generation in Japanese
Limitations:
Requires GPU due to dependencies., Inference might be slower than original model for long texts.
Supported Languages 
ja (Japanese (primary)), other (Multilingual support)
Training Details 
Methodology:
Quantization (miniaturization) of the original weblab-10b-instruction-sft model.
Model Architecture:
GPT-NeoX architecture
Input Output 
Input Format:
Text-based prompts
Accepted Modalities:
text
Output Format:
Text
Performance Tips:
Instruction prompts may not work on Colab.
Release Notes 
Version:
Third tuning
Date:
2023-08-26
Notes:
Replaced with current model, reflect tuning improvements.
Version:
Fifth tuning
Notes:
Abandoned
Version:
Fourth tuning
Notes:
Abandoned
LLM NameWeblab 10B Instruction Sft GPTQ
Repository 🤗https://huggingface.co/dahara1/weblab-10b-instruction-sft-GPTQ 
Base Model(s)  Weblab 10B Instruction Sft   matsuo-lab/weblab-10b-instruction-sft
Model Size10b
Required VRAM6.3 GB
Updated2025-09-16
Maintainerdahara1
Model Typegpt_neox
Instruction-BasedYes
Model Files  6.3 GB   6.3 GB
Supported Languagesja
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureGPTNeoXForCausalLM
Licensecc-by-nc-4.0
Context Length2048
Model Max Length2048
Transformers Version4.35.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|padding|>
Vocabulary Size50277
Torch Data Typefloat16

Best Alternatives to Weblab 10B Instruction Sft GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Weblab 10B Instruction Sft2K / 21.4 GB176673
Note: green Score (e.g. "73.2") means that the model is better than dahara1/weblab-10b-instruction-sft-GPTQ.

Rank the Weblab 10B Instruction Sft GPTQ 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