Instructions to use ICBU-NPU/FashionGPT-70B-V1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ICBU-NPU/FashionGPT-70B-V1.1 with Transformers:

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

pipe = pipeline("text-generation", model="ICBU-NPU/FashionGPT-70B-V1.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ICBU-NPU/FashionGPT-70B-V1.1")
model = AutoModelForCausalLM.from_pretrained("ICBU-NPU/FashionGPT-70B-V1.1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ICBU-NPU/FashionGPT-70B-V1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ICBU-NPU/FashionGPT-70B-V1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ICBU-NPU/FashionGPT-70B-V1.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ICBU-NPU/FashionGPT-70B-V1.1

SGLang

How to use ICBU-NPU/FashionGPT-70B-V1.1 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 "ICBU-NPU/FashionGPT-70B-V1.1" \
    --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": "ICBU-NPU/FashionGPT-70B-V1.1",
		"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 "ICBU-NPU/FashionGPT-70B-V1.1" \
        --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": "ICBU-NPU/FashionGPT-70B-V1.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ICBU-NPU/FashionGPT-70B-V1.1 with Docker Model Runner:
```
docker model run hf.co/ICBU-NPU/FashionGPT-70B-V1.1
```

How about Chinese support?

by obtion - opened Sep 19, 2023

Discussion

obtion

Sep 19, 2023

How about Chinese support?

Yhyu13

Sep 19, 2023

LLaMa2 models should support Chinese natively. But I don't thinik this model is fine-tuned on Chinese dataset

obtion

Sep 20, 2023

LLaMa2 models should support Chinese natively. But I don't thinik this model is fine-tuned on Chinese dataset

Thank you very much. Have you tried comparing wizard70b with the current model? Which one has better Chinese support?

Martinichigo

ICBU-NPU org Sep 22, 2023

Sorry for the late reply. This model does support Chinese but it was trained mainly on English datasets and not fine-tuned on massive Chinese datasets intentionally.

How about Chinese support?

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