HuggingFaceH4/ultrachat_200k
Viewer • Updated • 515k • 58.3k • 738
How to use Jksaw/Pxled with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Jksaw/Pxled") # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Jksaw/Pxled", dtype="auto")How to use Jksaw/Pxled with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jksaw/Pxled"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Jksaw/Pxled",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/Jksaw/Pxled
How to use Jksaw/Pxled with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Jksaw/Pxled" \
--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": "Jksaw/Pxled",
"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 "Jksaw/Pxled" \
--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": "Jksaw/Pxled",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use Jksaw/Pxled with Docker Model Runner:
docker model run hf.co/Jksaw/Pxled
A fine-tuned version of Meta-Llama-3-8B trained on the Ultrachat dataset.
from transformers import pipeline
pipe = pipeline(
"text-generation",
model="Jksaw/Pxled",
device="cuda" # remove if no GPU
)
print(pipe("Hello, how are you?", max_new_tokens=256)[0]['generated_text'])
Base model
meta-llama/Meta-Llama-3-8B