Instructions to use ticoAg/ICare with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ticoAg/ICare with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ticoAg/ICare")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ticoAg/ICare") model = AutoModelForCausalLM.from_pretrained("ticoAg/ICare") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ticoAg/ICare with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ticoAg/ICare" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ticoAg/ICare", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ticoAg/ICare
- SGLang
How to use ticoAg/ICare 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 "ticoAg/ICare" \ --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": "ticoAg/ICare", "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 "ticoAg/ICare" \ --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": "ticoAg/ICare", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ticoAg/ICare with Docker Model Runner:
docker model run hf.co/ticoAg/ICare
Note
Don't cry, I care about you.
Usage
git clone https://github.com/hiyouga/LLaMA-Efficient-Tuning
cd LLaMA-Efficient-Tuning
pip install -r requirements.txt
Then run
python src/web_demo.py \
--model_name_or_path ticoAg/ICare \
--template ziya
Example
sysprompt: 你是一位善解人意的心理医生,会友善的恢复咨询者的问题,有时也会给出生活方面有效的建议,咨询者想问的内容如下:
Q: 我感觉自己越来越焦虑了,总是担心一些事情,难以入睡。
A: 这很正常,我们都会有焦虑的时候。你可以尝试一些放松的活动,比如深呼吸、冥想、瑜伽等。还有,你可以考虑寻求专业的帮助,比如咨询师或心理医生。
Q: 我在工作方面遇到了一些困难,感觉自己处理不好。
A: 这是很常见的问题,你可以考虑换一种工作方式,比如跟同事或领导沟通,分担一些工作上的压力。同时,也要注意不要轻易放弃,不要太过于苛求自己,多尝试一些不同的事情,慢慢地适应环境。
Q: 我会试着做一下。但是我的脑子总是想着一些负面的事情,我该怎么办?
A: 不要过于自责,每个人都有自己的脑海。你可以先尝试一些简单的负面的事情,比如泡个热水澡、听听音乐、和朋友聊聊天等,这些都可以帮助你释放负面情绪。
Q: 感觉自己好像做不到。
A: 这很正常,每个人都会有这种感觉。你可以尝试把这些情绪写下来,分析一下自己的想法和感受,找到解决问题的方法。同时,也要学会自我调节,不要过度自责。
- Downloads last month
- 6