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

Smol Llama 220M GQA by BEE-spoke-data

 »  All LLMs  »  BEE-spoke-data  »  Smol Llama 220M GQA   URL Share it on

  3623   
  Autotrain compatible Dataset:bee-spoke-data/knowled...   Dataset:jeankaddour/minipile Dataset:mattymchen/refinedweb-... Dataset:pszemraj/simple wikipe...   En   Endpoints compatible   Llama   Llama2   Model-index   Region:us   Safetensors   Smol llama
Model Card on HF 🤗: https://huggingface.co/BEE-spoke-data/smol_llama-220M-GQA 

Smol Llama 220M GQA Benchmarks

MMLU Pro: 1.66
GPQA: 0.78
MUSR: 9.07
BBH: 3.04
IFEval: 23.86 vs 88 (so35)-72.9%
ARC: 24.83 vs 96.7 (so35)-74.3%
HellaSwag: 29.76 vs 95.3 (gpt4)-68.8%
MMLU: 25.85 vs 88.3 (so35)-70.7%
TruthfulQA: 44.55 vs 59 (gpt4)-24.5%
WinoGrande: 50.99 vs 87.5 (gpt4)-41.7%
GSM8K: 0.68 vs 96.4 (so35)-99.3%
MATH Lvl 5: 1.06
LLME Score: 0.21864
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Smol Llama 220M GQA (BEE-spoke-data/smol_llama-220M-GQA)
🌟 Advertise your project 🚀

Smol Llama 220M GQA Parameters and Internals

Model Type 
decoder
Additional Notes 
This is the first version of a small 220M parameter model. Fine-tuning options are available for further customization.
Training Details 
Data Sources:
JeanKaddour/minipile, pszemraj/simple_wikipedia_LM, mattymchen/refinedweb-3m, BEE-spoke-data/knowledge-inoc-concat-v1
Context Length:
2048
Hardware Used:
one GPU
Model Architecture:
1024 hidden size, 10 layers, GQA (32 heads, 8 key-value)
LLM NameSmol Llama 220M GQA
Repository 🤗https://huggingface.co/BEE-spoke-data/smol_llama-220M-GQA 
Model Size220m
Required VRAM0.4 GB
Updated2025-09-23
MaintainerBEE-spoke-data
Model Typellama
Model Files  0.4 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32128
Torch Data Typebfloat16

Best Alternatives to Smol Llama 220M GQA

Best Alternatives
Context / RAM
Downloads
Likes
...l Llama 220M GQA 32K Theta Sft32K / 0.4 GB102
Smol Llama 220M GQA 32K Theta32K / 0.4 GB71
Saily 220B4K / 417 GB106020
Smol Llama 220M Openhermes2K / 0.4 GB18475
Smol Llama 220M Open Instruct2K / 0.4 GB52
...mol Llama 220M GQA Fineweb Edu2K / 0.4 GB131
Smol Llama 220M Bees Internal2K / 0.4 GB71
Beecoder 220M Python2K / 0.4 GB93
Saily 220B GPTQ4K / 105.2 GB91
Saily 220B AWQ4K / 109.1 GB60

Rank the Smol Llama 220M GQA 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? 51544 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 v20241124
  Support LLM Explorer