Instructions to use BEE-spoke-data/smol_llama-220M-GQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BEE-spoke-data/smol_llama-220M-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-220M-GQA")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BEE-spoke-data/smol_llama-220M-GQA")
model = AutoModelForCausalLM.from_pretrained("BEE-spoke-data/smol_llama-220M-GQA")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BEE-spoke-data/smol_llama-220M-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-220M-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-220M-GQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/BEE-spoke-data/smol_llama-220M-GQA

SGLang

How to use BEE-spoke-data/smol_llama-220M-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-220M-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-220M-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-220M-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-220M-GQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use BEE-spoke-data/smol_llama-220M-GQA with Docker Model Runner:
```
docker model run hf.co/BEE-spoke-data/smol_llama-220M-GQA
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

smol_llama: 220M GQA

A small 220M param (total) decoder model. This is the first version of the model.

1024 hidden size, 10 layers
GQA (32 heads, 8 key-value), context length 2048
train-from-scratch on one GPU :)

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	29.44
AI2 Reasoning Challenge (25-Shot)	24.83
HellaSwag (10-Shot)	29.76
MMLU (5-Shot)	25.85
TruthfulQA (0-shot)	44.55
Winogrande (5-shot)	50.99
GSM8k (5-shot)	0.68

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	6.62
IFEval (0-Shot)	23.86
BBH (3-Shot)	3.04
MATH Lvl 5 (4-Shot)	0.00
GPQA (0-shot)	0.78
MuSR (0-shot)	9.07
MMLU-PRO (5-shot)	1.66

Downloads last month: 593

Safetensors

Model size

0.2B params

Tensor type

BF16

Model tree for BEE-spoke-data/smol_llama-220M-GQA

Finetunes

5 models

Merges

1 model

Quantizations

1 model

Datasets used to train BEE-spoke-data/smol_llama-220M-GQA

Collection including BEE-spoke-data/smol_llama-220M-GQA

smol llama

Collection

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

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

24.830
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

29.760
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

25.850
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

44.550
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

50.990
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

0.680
strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

23.860
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

3.040

BEE-spoke-data
/

smol_llama-220M-GQA

smol_llama: 220M GQA

Links

Open LLM Leaderboard Evaluation Results

Open LLM Leaderboard Evaluation Results

Model tree for BEE-spoke-data/smol_llama-220M-GQA

Datasets used to train BEE-spoke-data/smol_llama-220M-GQA

Collection including BEE-spoke-data/smol_llama-220M-GQA

smol llama

Evaluation results