BEE-spoke-data / smol_llama-101M-GQA

huggingface.co
Total runs: 614
24-hour runs: -5
7-day runs: 76
30-day runs: 39
Model's Last Updated: December 29 2025
text-generation

Introduction of smol_llama-101M-GQA

Model Details of smol_llama-101M-GQA

smol_llama-101M-GQA

banner

A small 101M param (total) decoder model. This is the first version of the model.

  • 768 hidden size, 6 layers
  • GQA (24 heads, 8 key-value), context length 1024
  • train-from-scratch
Features

Some cool anecdotes about this model:

  • this model was pretrained on one GPU for 5 compute-days. You can DIY pretrain too!
  • 0% of the training data (to our knowledge) comes from OpenAI synthetic generation
Notes

This checkpoint is the 'raw' pre-trained model and has not been tuned to a more specific task. It should be fine-tuned before use in most cases.

Checkpoints & Links
  • smol -er 81M parameter checkpoint with in/out embeddings tied: here
  • Fine-tuned on pypi to generate Python code - link
  • For the chat version of this model, please see here
Citation Info

If you find this experiment useful and would like to add some words to your .bib file, it would make us happy.

@misc {beespoke_data_2023,
    author       = { {Peter Szemraj and Vincent Haines} },
    title        = { smol_llama-101M-GQA (Revision 9c9c090) },
    year         = 2023,
    url          = { https://huggingface.co/BEE-spoke-data/smol_llama-101M-GQA },
    doi          = { 10.57967/hf/1440 },
    publisher    = { Hugging Face }
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 25.32
ARC (25-shot) 23.55
HellaSwag (10-shot) 28.77
MMLU (5-shot) 24.24
TruthfulQA (0-shot) 45.76
Winogrande (5-shot) 50.67
GSM8K (5-shot) 0.83
DROP (3-shot) 3.39

Runs of BEE-spoke-data smol_llama-101M-GQA on huggingface.co

614
Total runs
-5
24-hour runs
105
3-day runs
76
7-day runs
39
30-day runs

More Information About smol_llama-101M-GQA huggingface.co Model

More smol_llama-101M-GQA license Visit here:

https://choosealicense.com/licenses/apache-2.0

smol_llama-101M-GQA huggingface.co

smol_llama-101M-GQA huggingface.co is an AI model on huggingface.co that provides smol_llama-101M-GQA's model effect (), which can be used instantly with this BEE-spoke-data smol_llama-101M-GQA model. huggingface.co supports a free trial of the smol_llama-101M-GQA model, and also provides paid use of the smol_llama-101M-GQA. Support call smol_llama-101M-GQA model through api, including Node.js, Python, http.

BEE-spoke-data smol_llama-101M-GQA online free

smol_llama-101M-GQA huggingface.co is an online trial and call api platform, which integrates smol_llama-101M-GQA's modeling effects, including api services, and provides a free online trial of smol_llama-101M-GQA, you can try smol_llama-101M-GQA online for free by clicking the link below.

BEE-spoke-data smol_llama-101M-GQA online free url in huggingface.co:

https://huggingface.co/BEE-spoke-data/smol_llama-101M-GQA

smol_llama-101M-GQA install

smol_llama-101M-GQA is an open source model from GitHub that offers a free installation service, and any user can find smol_llama-101M-GQA on GitHub to install. At the same time, huggingface.co provides the effect of smol_llama-101M-GQA install, users can directly use smol_llama-101M-GQA installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

smol_llama-101M-GQA install url in huggingface.co:

https://huggingface.co/BEE-spoke-data/smol_llama-101M-GQA

Url of smol_llama-101M-GQA

Provider of smol_llama-101M-GQA huggingface.co

BEE-spoke-data
ORGANIZATIONS

Other API from BEE-spoke-data