Llama3 Crab DPO by THU-KEG

 ยป  All LLMs  ยป  THU-KEG  ยป  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
Model Card on HF ๐Ÿค—: https://huggingface.co/THU-KEG/Llama3-Crab-DPO 

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 (THU-KEG/Llama3-Crab-DPO)
๐ŸŒŸ Advertise your project ๐Ÿš€

Llama3 Crab DPO Parameters and Internals

LLM NameLlama3 Crab DPO
Repository ๐Ÿค—https://huggingface.co/THU-KEG/Llama3-Crab-DPO 
Required VRAM16.1 GB
Updated2026-03-29
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 Chat 512K512K / 13.5 GB72
LWM Text 512K512K / 13.5 GB52
LWM Text 256K256K / 13.5 GB113
LWM Text Chat 256K256K / 13.5 GB63
Pallas 0.5 LASER 0.1195K / 68.9 GB18882
SnorTTS Indic V0128K / 9.5 GB81721
Orpheus AUS128K /  GB50
Llama 3.1 Medprm Reward V1.0128K / 16.1 GB11016
Finetuning Health Ci128K / 6.5 GB22
LLaMA Mesh128K / 16.1 GB452181
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

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 52721 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260328a