Instructions to use Guspard-ew/BeanSLM-Instruct-278M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Guspard-ew/BeanSLM-Instruct-278M with Transformers:

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

pipe = pipeline("text-generation", model="Guspard-ew/BeanSLM-Instruct-278M")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Guspard-ew/BeanSLM-Instruct-278M", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Guspard-ew/BeanSLM-Instruct-278M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Guspard-ew/BeanSLM-Instruct-278M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Guspard-ew/BeanSLM-Instruct-278M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Guspard-ew/BeanSLM-Instruct-278M

SGLang

How to use Guspard-ew/BeanSLM-Instruct-278M 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 "Guspard-ew/BeanSLM-Instruct-278M" \
    --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": "Guspard-ew/BeanSLM-Instruct-278M",
		"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 "Guspard-ew/BeanSLM-Instruct-278M" \
        --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": "Guspard-ew/BeanSLM-Instruct-278M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Guspard-ew/BeanSLM-Instruct-278M with Docker Model Runner:
```
docker model run hf.co/Guspard-ew/BeanSLM-Instruct-278M
```

BeanSLM-Instruct-278M

BeanSLM-Instruct-278M is a 278M parameter English fully tuned language model trained from scratch.

Overview

This model was trained on a sequence length of 256 using a mixed dataset of about 130k instruction examples.
It is meant for text generation and simple instruction following.

Training Notes

Pretraining dataset: FineWebEdu
Instruction data: diverse_130k_better.txt
Vocabulary size: 32k
Sequence length: 256
Training status: trained from scratch
Final pretraining loss: 3.3
Final instruct loss: 1.7 (i dont know if this version could be overfit, i thought 1.7 was too low but after testing it didnt seem overfit)

What this model is good at

Short instruction following
Simple assistant text generation
Lightweight local experiments

Limitations

Small model size
Short context length
Will struggle with logic math and complex reasonong (bad at math !)

Downloads last month: -; Downloads are not tracked for this model. How to track