Instructions to use BEE-spoke-data/smol_llama-101M-GQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BEE-spoke-data/smol_llama-101M-GQA with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="BEE-spoke-data/smol_llama-101M-GQA")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BEE-spoke-data/smol_llama-101M-GQA")
model = AutoModelForCausalLM.from_pretrained("BEE-spoke-data/smol_llama-101M-GQA")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BEE-spoke-data/smol_llama-101M-GQA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BEE-spoke-data/smol_llama-101M-GQA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BEE-spoke-data/smol_llama-101M-GQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BEE-spoke-data/smol_llama-101M-GQA

SGLang

How to use BEE-spoke-data/smol_llama-101M-GQA with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "BEE-spoke-data/smol_llama-101M-GQA" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BEE-spoke-data/smol_llama-101M-GQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "BEE-spoke-data/smol_llama-101M-GQA" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BEE-spoke-data/smol_llama-101M-GQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BEE-spoke-data/smol_llama-101M-GQA with Docker Model Runner:
```
docker model run hf.co/BEE-spoke-data/smol_llama-101M-GQA
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

smol_llama-101M-GQA

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

Downloads last month: 797

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for BEE-spoke-data/smol_llama-101M-GQA

Finetunes

3 models

Quantizations

1 model

Datasets used to train BEE-spoke-data/smol_llama-101M-GQA

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

smol llama

Collection

🚧"raw" pretrained smol_llama checkpoints - WIP 🚧 • 4 items • Updated Apr 29, 2024 • 6