Instructions to use OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO with Transformers:

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

pipe = pipeline("text-generation", model="OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO")
model = AutoModelForCausalLM.from_pretrained("OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO

SGLang

How to use OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO 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 "OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO" \
    --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": "OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO",
		"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 "OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO" \
        --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": "OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO with Docker Model Runner:
```
docker model run hf.co/OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO
```

ToolAlpaca_unlearn_ToolDelete-DPO / README.md

Mingyi-Hong

Replace ToolDelete-DPO with verified paper checkpoint (epoch 7)

a1e04bf verified 10 days ago

preview code

Raw History Blame Contribute Delete

717 Bytes

	---
	base_model: TangQiaoYu/ToolAlpaca-7B
	library_name: transformers
	pipeline_tag: text-generation
	---

	# ToolAlpaca unlearning: ToolDelete-DPO (paper checkpoint)

	ToolDelete-DPO model continued to epoch 7. This checkpoint matches the ToolAlpaca paper-table results below, evaluated on 100 forget and 100 retain tasks with GPT-3.5-turbo as simulator and GPT-4-0613 as judge. The assisted condition uses the original ToolAlpaca-13B Thought planner.

	\| Condition \| Forget process correctness \| Retain process correctness \|
	\|---\|---:\|---:\|
	\| Default \| 45% \| 55% \|
	\| Assisted \| 53% \| 64% \|

	Paired harness recovery rate: 10/55 (18.18%).

	Weight SHA-256: `59dbd76f187fe619c0e4c55640d8db0df508c559a67ad1d677d7943c44b5aa99`.