Instructions to use p208p2002/llama-keyword-generator-zh2zh-120M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use p208p2002/llama-keyword-generator-zh2zh-120M with Transformers:

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

pipe = pipeline("text-generation", model="p208p2002/llama-keyword-generator-zh2zh-120M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("p208p2002/llama-keyword-generator-zh2zh-120M")
model = AutoModelForMultimodalLM.from_pretrained("p208p2002/llama-keyword-generator-zh2zh-120M")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use p208p2002/llama-keyword-generator-zh2zh-120M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "p208p2002/llama-keyword-generator-zh2zh-120M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "p208p2002/llama-keyword-generator-zh2zh-120M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/p208p2002/llama-keyword-generator-zh2zh-120M

SGLang

How to use p208p2002/llama-keyword-generator-zh2zh-120M 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 "p208p2002/llama-keyword-generator-zh2zh-120M" \
    --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": "p208p2002/llama-keyword-generator-zh2zh-120M",
		"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 "p208p2002/llama-keyword-generator-zh2zh-120M" \
        --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": "p208p2002/llama-keyword-generator-zh2zh-120M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use p208p2002/llama-keyword-generator-zh2zh-120M with Docker Model Runner:
```
docker model run hf.co/p208p2002/llama-keyword-generator-zh2zh-120M
```

LLaMA based chinese keyword generator

基於高品質中文資料訓練的中文關鍵字產生器。

Base Model: p208p2002/llama-traditional-chinese-120M

使用方式

範例

輸入

國內車市旺，10月單月掛 牌量衝上4萬台佳績，為40,540台，月增9%、年增11%；累計前十個月掛牌量逾39萬台，改寫近18年來新高紀錄，這樣的熱度將旺到年底。</s>

輸出

汽車行業、車市、熱度</s>

OpenLLM

支援OpenLLM部署使用。

$ openllm start opt --model-id p208p2002/llama-keyword-generator-zh2zh-120M

$ openllm query CONTEXT</s>

Downloads last month: 4

Safetensors

Model size

0.1B params

Tensor type

F32

Collections including p208p2002/llama-keyword-generator-zh2zh-120M

LLaMA-zhtw

Collection

6 items • Updated Jun 11, 2024

Useful Models

Collection

3 items • Updated Mar 26, 2024