Llama3 Crab DPO by THU-KEG

 »  All LLMs  »  THU-KEG  »  Llama3 Crab DPO   URL Share it on

Llama3 Crab DPO is an open-source language model by THU-KEG. Features: LLM, VRAM: 16.1GB, Context: 8K, License: apache-2.0, LLM Explorer Score: 0.16.

  Arxiv:2410.24175   En   Llama   Pytorch   Region:us   Sharded

Llama3 Crab DPO Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Llama3 Crab DPO Parameters and Internals

LLM NameLlama3 Crab DPO
Repository 🤗https://huggingface.co/THU-KEG/Llama3-Crab-DPO 
Required VRAM16.1 GB
Updated2026-05-26
MaintainerTHU-KEG
Model Typellama
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.44.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size128257
Torch Data Typebfloat16

Best Alternatives to Llama3 Crab DPO

Best Alternatives
Context / RAM
Downloads
Likes
LWM Text 512K512K / 13.5 GB132
LWM Text Chat 512K512K / 13.5 GB112
LWM Text 256K256K / 13.5 GB123
LWM Text Chat 256K256K / 13.5 GB103
Pallas 0.5 LASER 0.1195K / 68.9 GB10402
Veena128K / 7.6 GB3406232
SnorTTS Indic V0128K / 9.5 GB85921
Llama 3.1 Medprm Reward V1.0128K / 16.1 GB66716
Orpheus AUS128K /  GB50
Finetuning Health Ci128K / 6.5 GB32
Note: green Score (e.g. "73.2") means that the model is better than THU-KEG/Llama3-Crab-DPO.

Rank the Llama3 Crab 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? 53999 in total.

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