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

Taiwan LLM 8x7B DPO by yentinglin

 »  All LLMs  »  yentinglin  »  Taiwan LLM 8x7B DPO   URL Share it on

  9   

Taiwan LLM 8x7B DPO is an open-source language model by yentinglin. Features: 46.7b LLM, VRAM: 90GB, Context: 32K, License: apache-2.0, MoE, HF Score: 73.1, LLM Explorer Score: 0.13, Arc: 71, HellaSwag: 87.2, MMLU: 72.4, TruthfulQA: 54.9, WinoGrande: 81.9, GSM8K: 71.1.

  Arxiv:2311.17487   Autotrain compatible   Conversational   Endpoints compatible   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/yentinglin/Taiwan-LLM-8x7B-DPO 

Taiwan LLM 8x7B DPO Benchmarks

ARC: 70.99 vs 96.7 (so35)-26.6%
HellaSwag: 87.21 vs 95.3 (gpt4)-8.5%
MMLU: 72.43 vs 88.3 (so35)-18%
TruthfulQA: 54.87 vs 59 (gpt4)-7%
WinoGrande: 81.93 vs 87.5 (gpt4)-6.4%
GSM8K: 71.11 vs 96.4 (so35)-26.2%
LLME Score: 0.12821
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Taiwan LLM 8x7B DPO (yentinglin/Taiwan-LLM-8x7B-DPO)
🌟 Advertise your project 🚀

Taiwan LLM 8x7B DPO Parameters and Internals

Model Type 
Mixtral MoE, text generation, fine-tuned
Supported Languages 
Traditional Chinese (primary (zh-tw))
LLM NameTaiwan LLM 8x7B DPO
Repository 🤗https://huggingface.co/yentinglin/Taiwan-LLM-8x7B-DPO 
Model Size46.7b
Required VRAM90 GB
Updated2025-11-11
Maintaineryentinglin
Model Typemixtral
Model Files  2.0 GB: 1-of-48   2.0 GB: 2-of-48   2.0 GB: 3-of-48   2.0 GB: 4-of-48   2.0 GB: 5-of-48   2.0 GB: 6-of-48   2.0 GB: 7-of-48   2.0 GB: 8-of-48   2.0 GB: 9-of-48   2.0 GB: 10-of-48   2.0 GB: 11-of-48   2.0 GB: 12-of-48   2.0 GB: 13-of-48   2.0 GB: 14-of-48   2.0 GB: 15-of-48   2.0 GB: 16-of-48   2.0 GB: 17-of-48   2.0 GB: 18-of-48   2.0 GB: 19-of-48   2.0 GB: 20-of-48   2.0 GB: 21-of-48   2.0 GB: 22-of-48   2.0 GB: 23-of-48   2.0 GB: 24-of-48   2.0 GB: 25-of-48   2.0 GB: 26-of-48   2.0 GB: 27-of-48   2.0 GB: 28-of-48   2.0 GB: 29-of-48   2.0 GB: 30-of-48   2.0 GB: 31-of-48   2.0 GB: 32-of-48   2.0 GB: 33-of-48   2.0 GB: 34-of-48   2.0 GB: 35-of-48   2.0 GB: 36-of-48   2.0 GB: 37-of-48   2.0 GB: 38-of-48   2.0 GB: 39-of-48   2.0 GB: 40-of-48   2.0 GB: 41-of-48   2.0 GB: 42-of-48   2.0 GB: 43-of-48   2.0 GB: 44-of-48   2.0 GB: 45-of-48
Supported Languageszh
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Vocabulary Size32002
Torch Data Typebfloat16

Best Alternatives to Taiwan LLM 8x7B DPO

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral 8x7B Instruct V0.132K / 93.6 GB4629634650
Nous Hermes 2 Mixtral 8x7B DPO32K / 93.6 GB14686451
Mixtral 8x7B V0.132K / 93.6 GB1405571798
Sensualize Mixtral Bf1632K / 93.6 GB00
Skadi Mixtral V132K / 93.5 GB00
Franziska Mixtral V132K / 93.5 GB00
Typhon Mixtral V132K / 93.4 GB00
GritLM 8x7B KTO32K / 93.6 GB82893
Smaug Mixtral V0.132K / 187.7 GB854812
XLAM 8x7b R32K / 93.6 GB6870815
Note: green Score (e.g. "73.2") means that the model is better than yentinglin/Taiwan-LLM-8x7B-DPO.

Rank the Taiwan LLM 8x7B DPO 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? 52221 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