Instructions to use tatsu-lab/alpaca-7b-wdiff with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tatsu-lab/alpaca-7b-wdiff with Transformers:

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

pipe = pipeline("text-generation", model="tatsu-lab/alpaca-7b-wdiff")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tatsu-lab/alpaca-7b-wdiff")
model = AutoModelForCausalLM.from_pretrained("tatsu-lab/alpaca-7b-wdiff", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tatsu-lab/alpaca-7b-wdiff with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tatsu-lab/alpaca-7b-wdiff

SGLang

How to use tatsu-lab/alpaca-7b-wdiff 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 "tatsu-lab/alpaca-7b-wdiff" \
    --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": "tatsu-lab/alpaca-7b-wdiff",
		"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 "tatsu-lab/alpaca-7b-wdiff" \
        --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": "tatsu-lab/alpaca-7b-wdiff",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tatsu-lab/alpaca-7b-wdiff with Docker Model Runner:
```
docker model run hf.co/tatsu-lab/alpaca-7b-wdiff
```

alpaca-7b-wdiff

Commit History

license specified in model card tag

8648f73

rtaori commited on May 22, 2023

Update README.md

b51a819

rtaori commited on May 22, 2023

Update README.md

95c7d4b

rtaori commited on Apr 16, 2023

Update README.md

899b904

Xuechen Li commited on Apr 16, 2023

Update LICENSE

12b6fd7

rtaori commited on Apr 16, 2023

add license.

554c419

Xuechen Li commited on Apr 13, 2023

add weight diff and tokenizer.

4c7d23a

Xuechen Li commited on Apr 13, 2023

initial commit

5a971b9

Xuechen Li commited on Apr 13, 2023

Commit History

license specified in model card tag 8648f73

Update README.md b51a819

Update README.md 95c7d4b

Update README.md 899b904

Update LICENSE 12b6fd7

add license. 554c419

add weight diff and tokenizer. 4c7d23a

initial commit 5a971b9

license specified in model card tag

8648f73

Update README.md

b51a819

Update README.md

95c7d4b

Update README.md

899b904

Update LICENSE

12b6fd7

add license.

554c419

add weight diff and tokenizer.

4c7d23a

initial commit

5a971b9