Instructions to use Xianjun/PLLaMa-7b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Xianjun/PLLaMa-7b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="Xianjun/PLLaMa-7b-instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Xianjun/PLLaMa-7b-instruct")
model = AutoModelForMultimodalLM.from_pretrained("Xianjun/PLLaMa-7b-instruct")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Xianjun/PLLaMa-7b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Xianjun/PLLaMa-7b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Xianjun/PLLaMa-7b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Xianjun/PLLaMa-7b-instruct

SGLang

How to use Xianjun/PLLaMa-7b-instruct 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 "Xianjun/PLLaMa-7b-instruct" \
    --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": "Xianjun/PLLaMa-7b-instruct",
		"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 "Xianjun/PLLaMa-7b-instruct" \
        --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": "Xianjun/PLLaMa-7b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Xianjun/PLLaMa-7b-instruct with Docker Model Runner:
```
docker model run hf.co/Xianjun/PLLaMa-7b-instruct
```

模型表现不理想，并且出现显存过高的情况

by lippepetain - opened Jul 18, 2024

Discussion

lippepetain

Jul 18, 2024

这是我的代码：
from transformers import LlamaTokenizer, LlamaForCausalLM
import torch

tokenizer = LlamaTokenizer.from_pretrained("/home/zwfeng4/PLL/LLM")
model = LlamaForCausalLM.from_pretrained("/home/zwfeng4/PLL/LLM").half().to("cuda")

instruction = "介绍一下你自己"
batch = tokenizer(instruction, return_tensors="pt", add_special_tokens=False).to("cuda")
with torch.no_grad():
output = model.generate(**batch, max_new_tokens=1024, temperature=0.7, do_sample=True)
response = tokenizer.decode(output[0], skip_special_tokens=True)
print(response)
请问是哪里出问题了吗？模型表现出只会重复输入的语句，我用的是V100-32G显存

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment