Downloads · 30 days
8
6% of all-time downloads
HDFlow-Llama-3-8B-Instruct
wenlinyao/HDFlow-Llama-3-8B-Instruct
HDFlow-Llama-3-8B-Instruct is a machine learning model from wenlinyao. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama3.
This is the code and data repo of paper HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows. If you think this repo is useful, please cite us!
All-time downloads
133
Public
Repo size
16.1 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin16.1 GB · 100%
At a glance
- License
- llama3
- Model type
- llama
- Access
- Public
- Created
- Oct 3, 2024
- Updated
- Oct 4, 2024
- SHA
- 4e2a771f
Model card
From the Hugging Face model README
This is the code and data repo of paper HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows. If you think this repo is useful, please cite us!
@article{yao2024hdflow,
title={HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows},
author={Yao, Wenlin and Mi, Haitao and Yu, Dong},
journal={arXiv preprint arXiv:2409.17433},
year={2024}
}
Download our model into the dir /xxxx/checkpoints/wenlinyao/HDFlow-Llama-3-8B-Instruct/. Next, use vllm to host the model service. Here provides an example to host two models at the same time (using different ports).
CUDA_VISIBLE_DEVICES=0 python -m vllm.entrypoints.openai.api_server --model /xxxx/checkpoints/wenlinyao/HDFlow-Llama-3-8B-Instruct/ --tensor-parallel-size 1 --max-num-batched-tokens 8192 --dtype bfloat16 --port 4231
Refer to https://github.com/wenlinyao/HDFlow for more details.
- Type
- llama
- License
- llama3
- Created
- Oct 3, 2024
- Updated
- Oct 4, 2024