Instructions to use zjunlp/zhixi-13b-diff-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zjunlp/zhixi-13b-diff-fp16 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="zjunlp/zhixi-13b-diff-fp16")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zjunlp/zhixi-13b-diff-fp16")
model = AutoModelForCausalLM.from_pretrained("zjunlp/zhixi-13b-diff-fp16")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use zjunlp/zhixi-13b-diff-fp16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zjunlp/zhixi-13b-diff-fp16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zjunlp/zhixi-13b-diff-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/zjunlp/zhixi-13b-diff-fp16

SGLang

How to use zjunlp/zhixi-13b-diff-fp16 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 "zjunlp/zhixi-13b-diff-fp16" \
    --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": "zjunlp/zhixi-13b-diff-fp16",
		"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 "zjunlp/zhixi-13b-diff-fp16" \
        --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": "zjunlp/zhixi-13b-diff-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use zjunlp/zhixi-13b-diff-fp16 with Docker Model Runner:
```
docker model run hf.co/zjunlp/zhixi-13b-diff-fp16
```

liangxz commited on Jun 22, 2023

Commit

85d0002

1 Parent(s): bd24730

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -35,6 +35,9 @@ The project's `initial phase` introduced a knowledge extraction LLM based on LLa
 All weights have been uploaded to Hugging Face. The ZhiXi differential weights can be found [here](https://huggingface.co/zjunlp/zhixi-13B-Diff), and the LoRA weights can be found [here](https://huggingface.co/zjunlp/zhixi-13B-LoRA).
 ## Contents
 - [Cases](#1)

 All weights have been uploaded to Hugging Face. The ZhiXi differential weights can be found [here](https://huggingface.co/zjunlp/zhixi-13B-Diff), and the LoRA weights can be found [here](https://huggingface.co/zjunlp/zhixi-13B-LoRA).
+## Why it's called ZhiXi (智析)?
+In Chinese, "Zhi" (智) signifies intelligence, referencing the AI's advanced language understanding capabilities. "Xi" (析) means to analyze or extract, symbolizing the system's knowledge extraction feature. Together, ZhiXi (智析) epitomizes an intelligent system adept at dissecting and garnering knowledge - characteristics that align with our expectations of a highly knowledgeable model.
 ## Contents
 - [Cases](#1)