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

SmolLM 360M Instruct by HuggingFaceTB

 »  All LLMs  »  HuggingFaceTB  »  SmolLM 360M Instruct   URL Share it on

  11629   
  Alignment-handbook   Autotrain compatible Base model:huggingfacetb/smoll... Base model:quantized:huggingfa...   Conversational Dataset:bigcode/self-oss-instr... Dataset:huggingfacetb/everyday... Dataset:magpie-align/magpie-pr...   Dataset:teknium/openhermes-2.5   En   Endpoints compatible   Instruct   Llama   Onnx   Region:us   Safetensors   Sft   Trl
Model Card on HF 🤗: https://huggingface.co/HuggingFaceTB/SmolLM-360M-Instruct 

SmolLM 360M Instruct Benchmarks

MMLU Pro: 1.85
GPQA: 1.9
MUSR: 2.9
BBH: 2.08
IFEval: 19.52 vs 88 (so35)-77.8%
LLME Score: 0.28602
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SmolLM 360M Instruct (HuggingFaceTB/SmolLM-360M-Instruct)

SmolLM 360M Instruct Parameters and Internals

Model Type 
Causal LM, Instruction-tuned
Use Cases 
Areas:
Research, Commercial applications
Applications:
General knowledge, Creative writing, Basic Python programming
Primary Use Cases:
Handling general inquiries, AI assistant applications
Limitations:
English only, Difficulty with arithmetics, Editing tasks, Complex reasoning
Supported Languages 
en (Proficient)
Training Details 
Data Sources:
Magpie-Align/Magpie-Pro-300K-Filtered, bigcode/self-oss-instruct-sc2-exec-filter-50k, teknium/OpenHermes-2.5, HuggingFaceTB/everyday-conversations-llama3.1-2k
Methodology:
Finetuned using DPO (Direct Preference Optimization).
Model Architecture:
Based on SmolLM, a series of language models for instruction-based tasks.
Input Output 
Input Format:
Chat messages structured with roles.
Accepted Modalities:
Text
Output Format:
Text-based responses
Performance Tips:
Suggested parameters: temperature 0.2, top-p 0.9
Release Notes 
Version:
v0.1
Notes:
Initial release, finetuned on permissive subset.
Version:
v0.2
Notes:
Finetuning on datasets more suitable for smaller models, better topic adherence.
LLM NameSmolLM 360M Instruct
Repository 🤗https://huggingface.co/HuggingFaceTB/SmolLM-360M-Instruct 
Base Model(s)  SmolLM 360M   HuggingFaceTB/SmolLM-360M
Model Size360m
Required VRAM0.7 GB
Updated2025-02-05
MaintainerHuggingFaceTB
Model Typellama
Instruction-BasedYes
Model Files  0.7 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.42.3
Tokenizer ClassGPT2Tokenizer
Padding Token<|im_end|>
Vocabulary Size49152
Torch Data Typebfloat16

Best Alternatives to SmolLM 360M Instruct

Best Alternatives
Context / RAM
Downloads
Likes
SmolLM2 360M Instruct8K / 0.7 GB123027377
SmolLM2 CoT 360M8K / 1.4 GB74014
SmolLM2 360M Instruct8K / 0.7 GB77870
SmolLM2 360M Instruct Ita8K / 0.7 GB1360
Kurtis SmolLM2 360M Instruct8K / 1.4 GB1910
SmolLM2 360M Instruct FT8K / 1.4 GB2002
SmolLCoder 360M Instruct8K / 0.7 GB110
SmolLM 360M Instruct2K / 0.7 GB87960
SmolLM 360M2K / 0.7 GB71180
SmolLM 360M Instruct2K / 0.7 GB1342
Note: green Score (e.g. "73.2") means that the model is better than HuggingFaceTB/SmolLM-360M-Instruct.

Rank the SmolLM 360M Instruct 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