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

MagpieLM 4B Chat V0.1 by Magpie-Align

 »  All LLMs  »  Magpie-Align  »  MagpieLM 4B Chat V0.1   URL Share it on

  104   
  Arxiv:2406.08464   Arxiv:2411.07133   Alignment-handbook   Autotrain compatible Base model:finetune:magpie-ali... Base model:magpie-align/magpie...   Conversational Dataset:magpie-align/magpielm-... Dataset:magpie-align/magpielm-...   Dpo   Endpoints compatible   Generated from trainer   Llama   Region:us   Safetensors   Sharded   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/Magpie-Align/MagpieLM-4B-Chat-v0.1 

MagpieLM 4B Chat V0.1 Benchmarks

LLME Score: 0.22763
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
MagpieLM 4B Chat V0.1 (Magpie-Align/MagpieLM-4B-Chat-v0.1)

MagpieLM 4B Chat V0.1 Parameters and Internals

Model Type 
text-generation
Use Cases 
Primary Use Cases:
friendly AI assistant
Limitations:
primarily understands and generates content in English, outputs may contain factual errors or logical inconsistencies, may reflect biases present in the training data, not specifically designed for complex reasoning tasks, may produce unsafe or inappropriate content
Additional Notes 
This model was developed using the transformers library.
Training Details 
Data Sources:
Magpie-Align/MagpieLM-SFT-Data-v0.1, Magpie-Align/MagpieLM-DPO-Data-v0.1
Methodology:
SFT and DPO
Context Length:
8192
Model Architecture:
Llama3.1
Input Output 
Input Format:
Llama 3 chat template
Accepted Modalities:
text
Performance Tips:
Please use the Llama 3 chat template for the best performance.
Release Notes 
Version:
v0.1
Notes:
Initial release of Llama3.1-MagpieLM-4B-Chat-v0.1.
LLM NameMagpieLM 4B Chat V0.1
Repository 🤗https://huggingface.co/Magpie-Align/MagpieLM-4B-Chat-v0.1 
Base Model(s)  Magpie-Align/MagpieLM-4B-SFT-v0.1   Magpie-Align/MagpieLM-4B-SFT-v0.1
Model Size4b
Required VRAM9 GB
Updated2025-02-05
MaintainerMagpie-Align
Model Typellama
Model Files  5.0 GB: 1-of-2   4.0 GB: 2-of-2   0.0 GB
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version4.45.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to MagpieLM 4B Chat V0.1

Best Alternatives
Context / RAM
Downloads
Likes
SJT 4B146K / 7.6 GB630
Loxa 4B128K / 16 GB530
Aura 4B128K / 9 GB1910
...ama 3.1 Minitron 4B Depth Base128K / 9.1 GB520
....5 MINI 4B SFTxORPO HESSIAN AI128K / 7.7 GB160
....5 MINI 4B ORPOxSFT HESSIAN AI128K / 7.7 GB150
....5 MINI 4B ORPOxSFT HESSIAN AI128K / 7.7 GB150
....5 MINI 4B SFTxORPO HESSIAN AI128K / 7.7 GB130
...ama 3.1 Minitron 4B Width Base128K / 9 GB11187
... Minitron 4B Width Base Chatml128K / 9 GB4442
Note: green Score (e.g. "73.2") means that the model is better than Magpie-Align/MagpieLM-4B-Chat-v0.1.

Rank the MagpieLM 4B Chat V0.1 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? 42577 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 v20241227
  Support LLM Explorer