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

Truthful DPO MoE 19B by yunconglong

 »  All LLMs  »  yunconglong  »  Truthful DPO MoE 19B   URL Share it on

  1731   

Truthful DPO MoE 19B is an open-source language model by yunconglong. Features: 19.2b LLM, VRAM: 38.4GB, Context: 4K, License: other, MoE, HF Score: 74.3, LLM Explorer Score: 0.14, Arc: 71.1, HellaSwag: 88.5, MMLU: 66.1, TruthfulQA: 72.3, WinoGrande: 83.4, GSM8K: 64.5.

  Autotrain compatible   Conversational   Dpo   Endpoints compatible   Mixtral   Moe   Region:us   Rl-tuned   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/yunconglong/Truthful_DPO_MOE_19B 

Truthful DPO MoE 19B Benchmarks

ARC: 71.08 vs 96.7 (so35)-26.5%
HellaSwag: 88.46 vs 95.3 (gpt4)-7.2%
MMLU: 66.13 vs 88.3 (so35)-25.1%
TruthfulQA: 72.29 vs 59 (gpt4)22.5%
WinoGrande: 83.35 vs 87.5 (gpt4)-4.7%
GSM8K: 64.52 vs 96.4 (so35)-33.1%
LLME Score: 0.13895
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Truthful DPO MoE 19B (yunconglong/Truthful_DPO_MOE_19B)
🌟 Advertise your project 🚀

Truthful DPO MoE 19B Parameters and Internals

Model Type 
language model, reward model
Additional Notes 
The model utilizes the DPO Trainer for training language models based on preference data, as outlined in the related paper.
LLM NameTruthful DPO MoE 19B
Repository 🤗https://huggingface.co/yunconglong/Truthful_DPO_MOE_19B 
Model Size19.2b
Required VRAM38.4 GB
Updated2025-09-23
Maintaineryunconglong
Model Typemixtral
Model Files  5.0 GB: 1-of-8   4.9 GB: 2-of-8   5.0 GB: 3-of-8   5.0 GB: 4-of-8   4.9 GB: 5-of-8   5.0 GB: 6-of-8   5.0 GB: 7-of-8   3.6 GB: 8-of-8
Model ArchitectureMixtralForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Truthful DPO MoE 19B

Best Alternatives
Context / RAM
Downloads
Likes
MixTAO 19B Pass32K / 38.1 GB32
Lorge 2x7B UAMM32K / 38.2 GB160
Multimerge 19B Pass32K / 38 GB100
Mistralmath 15B Pass32K / 38.5 GB110
TaoPassthrough 15B S32K / 38.4 GB50
Raccoon Small32K / 38.4 GB741
Mixtral 11Bx2 MoE 19B4K / 38.4 GB117938
SOLAR Math 2x10.7B4K / 38.4 GB17420
SOLAR Math 2x10.7B V0.24K / 38.4 GB11614
...oundary Solar Chat 2x10.7B MoE4K / 38 GB1231
Note: green Score (e.g. "73.2") means that the model is better than yunconglong/Truthful_DPO_MOE_19B.

Rank the Truthful DPO MoE 19B 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? 52628 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