MagpieLM 4B SFT V0.1 by Magpie-Align

 ยป  All LLMs  ยป  Magpie-Align  ยป  MagpieLM 4B SFT V0.1   URL Share it on

  Arxiv:2406.08464   Autotrain compatible   Axolotl Base model:finetune:nvidia/lla... Base model:nvidia/llama-3.1-mi...   Conversational Dataset:magpie-align/magpielm-...   En   Endpoints compatible   Generated from trainer   Llama   Pytorch   Region:us   Safetensors   Sharded   Tensorflow

MagpieLM 4B SFT V0.1 Benchmarks

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

MagpieLM 4B SFT V0.1 Parameters and Internals

LLM NameMagpieLM 4B SFT V0.1
Repository ๐Ÿค—https://huggingface.co/Magpie-Align/MagpieLM-4B-SFT-v0.1 
Base Model(s)  nvidia/Llama-3.1-Minitron-4B-Width-Base   nvidia/Llama-3.1-Minitron-4B-Width-Base
Model Size4b
Required VRAM9 GB
Updated2024-10-07
MaintainerMagpie-Align
Model Typellama
Model Files  5.0 GB: 1-of-2   4.0 GB: 2-of-2   5.0 GB: 1-of-2   4.0 GB: 2-of-2   0.0 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.45.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16
MagpieLM 4B SFT V0.1 (Magpie-Align/MagpieLM-4B-SFT-v0.1)

Best Alternatives to MagpieLM 4B SFT V0.1

Best Alternatives
Context / RAM
Downloads
Likes
...ama 3.1 Minitron 4B Width Base128K / 9 GB109182
MagpieLM 4B Chat V0.1128K / 9 GB61218
...ama 3.1 Minitron 4B Depth Base128K / 9.1 GB2619
Magnum V2 4B128K / 9 GB30617
... Minitron 4B Width Base Chatml128K / 9 GB16771
Llama 3.1 Minitron 4B Chat128K / 9 GB2873
Nuggies 4B128K / 9 GB111
Hubble 4B V1128K / 9 GB498
Nuggiespoe128K / 9.1 GB120
Neurodeed128K / 9.1 GB100
Note: green Score (e.g. "73.2") means that the model is better than Magpie-Align/MagpieLM-4B-SFT-v0.1.

Rank the MagpieLM 4B SFT V0.1 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? 36599 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803