yahma/alpaca-cleaned
Viewer • Updated • 51.8k • 32.7k • 825
How to use jeiku/Foundation_3B with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="jeiku/Foundation_3B", trust_remote_code=True) # Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("jeiku/Foundation_3B", trust_remote_code=True, dtype="auto")How to use jeiku/Foundation_3B with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jeiku/Foundation_3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "jeiku/Foundation_3B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/jeiku/Foundation_3B
How to use jeiku/Foundation_3B with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "jeiku/Foundation_3B" \
--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": "jeiku/Foundation_3B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "jeiku/Foundation_3B" \
--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": "jeiku/Foundation_3B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use jeiku/Foundation_3B with Docker Model Runner:
docker model run hf.co/jeiku/Foundation_3B
This is a big step forward for 3B class models. Trained on smol PIPPA, alpaca-cleaned, and two custom datasets, and based on https://huggingface.co/jeiku/Rosa_v3_3B
This should serve as a decent fiction model, though it also excels at roleplaying, but is not an ideal model for logical queries or riddles.
docker model run hf.co/jeiku/Foundation_3B