theblackcat102/evol-codealpaca-v1
Viewer • Updated • 111k • 10.8k • 181
How to use Pasta009/IF-CL-34B with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Pasta009/IF-CL-34B") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Pasta009/IF-CL-34B")
model = AutoModelForCausalLM.from_pretrained("Pasta009/IF-CL-34B")How to use Pasta009/IF-CL-34B with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pasta009/IF-CL-34B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Pasta009/IF-CL-34B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/Pasta009/IF-CL-34B
How to use Pasta009/IF-CL-34B with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Pasta009/IF-CL-34B" \
--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": "Pasta009/IF-CL-34B",
"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 "Pasta009/IF-CL-34B" \
--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": "Pasta009/IF-CL-34B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use Pasta009/IF-CL-34B with Docker Model Runner:
docker model run hf.co/Pasta009/IF-CL-34B
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Pasta009/IF-CL-34B")
model = AutoModelForCausalLM.from_pretrained("Pasta009/IF-CL-34B")Trained with data generated by the Instruction Fusion method.
BibTeX:
@misc{guo2024instruction,
title={Instruction Fusion: Advancing Prompt Evolution through Hybridization},
author={Weidong Guo and Jiuding Yang and Kaitong Yang and Xiangyang Li and Zhuwei Rao and Yu Xu and Di Niu},
year={2024},
eprint={2312.15692},
archivePrefix={arXiv},
primaryClass={cs.AI}
}
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Pasta009/IF-CL-34B")