SmolLM2 360M by HuggingFaceTB

 ยป  All LLMs  ยป  HuggingFaceTB  ยป  SmolLM2 360M   URL Share it on

  Arxiv:2502.02737   Autotrain compatible   En   Endpoints compatible   Llama   Region:us   Safetensors

SmolLM2 360M Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SmolLM2 360M (HuggingFaceTB/SmolLM2-360M)

SmolLM2 360M Parameters and Internals

Model Type 
language model, instruction model
Use Cases 
Primary Use Cases:
text rewriting, summarization, function calling
Limitations:
Primarily understands and generates content in English, Generated content may not be factually accurate or logically consistent, Bias may be present in the training data
Considerations:
Use as assistive tools, always verify critical information
Supported Languages 
en (High proficiency)
Training Details 
Data Sources:
FineWeb-Edu, DCLM, The Stack
Data Volume:
4 trillion tokens
Methodology:
Supervised fine-tuning and Direct Preference Optimization (DPO)
Hardware Used:
64 H100 GPUs
Model Architecture:
Transformer decoder
Input Output 
Accepted Modalities:
text
LLM NameSmolLM2 360M
Repository ๐Ÿค—https://huggingface.co/HuggingFaceTB/SmolLM2-360M 
Model Size360m
Required VRAM0.7 GB
Updated2025-03-13
MaintainerHuggingFaceTB
Model Typellama
Model Files  0.7 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassGPT2Tokenizer
Vocabulary Size49152
Torch Data Typebfloat16

Best Alternatives to SmolLM2 360M

Best Alternatives
Context / RAM
Downloads
Likes
SmolLM2 360M Instruct8K / 0.7 GB269794102
SmolLM2 360M Grpo R9998K / 1.4 GB31511
Smol Hub Tldr8K / 0.7 GB13739
...rtis SmolLM2 360M Instruct DPO8K / 1.4 GB4390
SmolLM2 CoT 360M8K / 1.4 GB18818
SmolLM2 360M8K / 0.7 GB69860
SmolLM2 360M Instruct8K / 0.7 GB41311
...0M Japanese Base Phase 1 110008K / 0 GB380
D SmolLM2 360M8K / 0.7 GB831
Smol 360M Ft8K / 0 GB280
Note: green Score (e.g. "73.2") means that the model is better than HuggingFaceTB/SmolLM2-360M.

Rank the SmolLM2 360M 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? 44950 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227