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 101M GQA by BEE-spoke-data

 »  All LLMs  »  BEE-spoke-data  »  Smol Llama 101M GQA   URL Share it on

  3822   
  Autotrain compatible Dataset:bee-spoke-data/wikiped...   Dataset:jeankaddour/minipile Dataset:mattymchen/refinedweb-... Dataset:pszemraj/simple wikipe...   Doi:10.57967/hf/1440   En   Endpoints compatible   Llama   Llama2   Region:us   Safetensors   Smol llama
Model Card on HF 🤗: https://huggingface.co/BEE-spoke-data/smol_llama-101M-GQA 

Smol Llama 101M GQA Benchmarks

MMLU Pro: 1.19
GPQA: 1.01
MUSR: 4.28
BBH: 3.2
IFEval: 13.84 vs 88 (so35)-84.3%
ARC: 23.46 vs 96.7 (so35)-75.7%
HellaSwag: 28.73 vs 95.3 (gpt4)-69.9%
MMLU: 24.35 vs 88.3 (so35)-72.4%
TruthfulQA: 45.8 vs 59 (gpt4)-22.4%
WinoGrande: 50.67 vs 87.5 (gpt4)-42.1%
GSM8K: 0.76 vs 96.4 (so35)-99.2%
LLME Score: 0.23323
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Smol Llama 101M GQA (BEE-spoke-data/smol_llama-101M-GQA)

Smol Llama 101M GQA Parameters and Internals

Model Type 
text-generation
Use Cases 
Considerations:
Fine-tuning is recommended for specific tasks.
Additional Notes 
The checkpoint is the 'raw' pre-trained model and has not been tuned to a more specific task, indicating it should be fine-tuned before use in most cases.
Supported Languages 
en (English)
Training Details 
Data Sources:
JeanKaddour/minipile, pszemraj/simple_wikipedia_LM, BEE-spoke-data/wikipedia-20230901.en-deduped, mattymchen/refinedweb-3m
Methodology:
train-from-scratch
Context Length:
1024
Training Time:
5 compute-days
Hardware Used:
one GPU
Model Architecture:
768 hidden size, 6 layers, GQA (24 heads, 8 key-value)
Release Notes 
Version:
Revision 9c9c090
Date:
2023
Notes:
smol_llama-101M-GQA (First version), a small 101M param decoder model.
LLM NameSmol Llama 101M GQA
Repository 🤗https://huggingface.co/BEE-spoke-data/smol_llama-101M-GQA 
Model Size101m
Required VRAM0.4 GB
Updated2025-02-05
MaintainerBEE-spoke-data
Model Typellama
Model Files  0.4 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length1024
Model Max Length1024
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32128
Torch Data Typefloat32

Best Alternatives to Smol Llama 101M GQA

Best Alternatives
Context / RAM
Downloads
Likes
Smol Llama 101M Chat V11K / 0.4 GB2319
...ephyr Smol Llama 100M Sft Full1K / 0.2 GB12961
...Llama 101M Midjourney Messages1K / 0.4 GB131
Smol Llama 101M GQA Python1K / 0.4 GB601

Rank the Smol Llama 101M 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? 42625 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