LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

CT LLM SFT DPO by m-a-p

 »  All LLMs  »  m-a-p  »  CT LLM SFT DPO   URL Share it on

  57   
  Arxiv:2404.04167   Autotrain compatible   Endpoints compatible   Llama   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/m-a-p/CT-LLM-SFT-DPO 

CT LLM SFT DPO Benchmarks

LLME Score: 0.14559
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CT LLM SFT DPO (m-a-p/CT-LLM-SFT-DPO)
🌟 Advertise your project 🚀

CT LLM SFT DPO Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
Academic research
Additional Notes 
Developed for academic use, rigorous data compliance maintained. Disclaimer warns of potential liability for misuse.
Supported Languages 
Chinese (High), English (Moderate)
Training Details 
Data Sources:
cvalues_rlhf, comparison_gpt4_data_zh, oaast_rm_zh, huozi, zhihu, comparison_gpt4_data_en, beavertails, alpaca-gpt4, baichuan-6B
Data Volume:
183k Chinese pairs and 46k English pairs
Methodology:
Direct preference-based learning using DPO, aligned and enhanced over CT-LLM-SFT
Hardware Used:
8 H800 GPUs
Input Output 
Input Format:
Chat conversation with user and system roles
Accepted Modalities:
text
Output Format:
Generated text responses
LLM NameCT LLM SFT DPO
Repository 🤗https://huggingface.co/m-a-p/CT-LLM-SFT-DPO 
Model Size2.1b
Required VRAM0 GB
Updated2025-10-18
Maintainerm-a-p
Model Typellama
Model Files  4.3 GB   0.0 GB   0.0 GB
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.37.2
Tokenizer ClassBaichuanTokenizer
Padding Token<unk>
Vocabulary Size125824
Torch Data Typebfloat16

Best Alternatives to CT LLM SFT DPO

Best Alternatives
Context / RAM
Downloads
Likes
Kanana 1.5 2.1B Instruct 250532K / 4.6 GB766431
Fc Reasoning 2.1B32K / 4.2 GB1170
Kanana 1.5 2.1B Base32K / 4.2 GB10248
Kanana Nano 2.1B Instruct8K / 4.2 GB484168
Kanana Nano 2.1B Base8K / 4.2 GB298738
Kanana Safeguard Prompt 2.1B8K / 4.2 GB11012
DAMI Base Merge 04088K / 4.6 GB50
EcomGen 0.0.2v8K / 8.4 GB50
Phi 3 Orpo V9.44K / 2.3 GB171
CT LLM Base4K / 4.3 GB8811
Note: green Score (e.g. "73.2") means that the model is better than m-a-p/CT-LLM-SFT-DPO.

Rank the CT LLM SFT 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? 51547 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