Instructions to use JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT with Transformers:

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

pipe = pipeline("text-generation", model="JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT

SGLang

How to use JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT 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 "JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT with Docker Model Runner:
```
docker model run hf.co/JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Baichuan2-7B-Chat-DcardStylePost-SFT

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT"
messages = [{"role": "user", "content": "【任务】：\n你是口碑行销公司的资深写手，现在要撰写一篇Dcard 『闲聊版』的口碑文。\n麻烦熟读下列 【参考资料】将商品或品牌与生活情境的融合，并尽量贴近生活口吻，以不要被发现是业配文为重要目标。\n请依照【口碑切角】为文章的故事主轴撰写整篇文章，请参考并依照【规范】角色口吻来撰写文章，融入角色情境来完成整篇故事撰写，请注重人物角色特色及限制。\n\n－\n\n【规范】：\n\n1.需产出文章标题\n2.请以第一人称方式撰写文章\n3.请记住现在是时间是西元 2023 年\n4.Please write in zh-TW language .\n5.降低口碑文业配感\n6.写作者是一个19~25岁之间的女生的大学生或是社会新鲜人\n7.喜爱吃甜食，常常带著男友一起去踩点试吃看看\n8.除了介绍食物，也喜欢顺便男友发生好笑的趣事来跟食物介绍的故事结合\n9.为降低口碑文业配感，请多多举几个甜点推荐\n10.喜欢应用很多可爱的颜文字和emoji\n\n－\n\n【参考资料】\n▲可丽露\n>>龙眼蜜，所以吃起来不会这么甜，跟其他家的可丽露吃起来真的很有差异\n以野生龙眼蜜减低并取代部分甜度,带出微微酸感的蛋蜜香,外脆内湿润的口感,完整的蜂巢组织度,木质调的兰姆酒香,法国盐之花平衡了整体,经典细致的马达加斯加香草籽原味,请在出炉后的3小时内食用完毕或\"冷冻\"保存,回烤后食用最接近现烤口感!\n\n\n\n▲奶盖布丁\n>>法国盐之花，连盐巴都很用心的甜点师\n带咸度的法国盐之花奶盖,微甜浓郁而不腻口的布蕾布丁体,和著偏苦的手煮焦糖液,是一款有著丰富层次的大人味布丁! 图片为示意仅供参考,食用时请由上方挖到底,品尝完整风味~\n\n【口碑切角】\n男友就像金鱼一样，好像记忆都只有三秒，\n只有三秒就算了还说错很多很好笑的话XD\n我都会带甜点回去给男友吃～结果男友居然说玛莉露很好吃XD\n玛莉露是神奇宝贝，可丽露才是甜点啦!\n分享日常男友都会口误的甜点们"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=512, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Downloads last month: 5

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for JiunYi/Baichuan2-7B-Chat-DcardStylePost-SFT

Base model

baichuan-inc/Baichuan2-7B-Chat

Finetuned

(2)

this model

Quantizations

1 model