MNLP M3 DPO Sft200k CME by Mahlia

 ยป  All LLMs  ยป  Mahlia  ยป  MNLP M3 DPO Sft200k CME   URL Share it on

  Arxiv:1910.09700   Autotrain compatible   Conversational   Dpo   Endpoints compatible   Qwen3   Region:us   Safetensors   Trl

MNLP M3 DPO Sft200k CME Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MNLP M3 DPO Sft200k CME (Mahlia/MNLP_M3_dpo_sft200k_CME)
๐ŸŒŸ Advertise your project ๐Ÿš€

MNLP M3 DPO Sft200k CME Parameters and Internals

LLM NameMNLP M3 DPO Sft200k CME
Repository ๐Ÿค—https://huggingface.co/Mahlia/MNLP_M3_dpo_sft200k_CME 
Model Size596m
Required VRAM2.4 GB
Updated2025-06-10
MaintainerMahlia
Model Typeqwen3
Model Files  2.4 GB
Model ArchitectureQwen3ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat32
Errorsreplace

Best Alternatives to MNLP M3 DPO Sft200k CME

Best Alternatives
Context / RAM
Downloads
Likes
Sam Reason A140K / 2.4 GB691
SFT Nochat FULL DATA32K / 1.2 GB12690
Sft Scp Epoch132K / 1.2 GB12550
Full Dataset Instruction V432K / 1.2 GB2090
MNLP M3 Mcqa Model32K / 1.2 GB2290
Fft Qwen32K / 0 GB2170
CS552 M3 SFT Model32K / 1.2 GB2590
MNLP M3 DPO Model32K / 1.2 GB740
MNLP M3 DPO Model Smoltalk All32K / 1.2 GB810
MNLP M3 Mcqa Model32K / 1.2 GB680
Note: green Score (e.g. "73.2") means that the model is better than Mahlia/MNLP_M3_dpo_sft200k_CME.

Rank the MNLP M3 DPO Sft200k CME 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? 48137 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124