Instructions to use foo-barrr/saferpaca-7b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use foo-barrr/saferpaca-7b-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-fp16")
model = PeftModel.from_pretrained(base_model, "foo-barrr/saferpaca-7b-lora")

Transformers

How to use foo-barrr/saferpaca-7b-lora with Transformers:

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

pipe = pipeline("text-generation", model="foo-barrr/saferpaca-7b-lora")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("foo-barrr/saferpaca-7b-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use foo-barrr/saferpaca-7b-lora with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/foo-barrr/saferpaca-7b-lora

SGLang

How to use foo-barrr/saferpaca-7b-lora 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 "foo-barrr/saferpaca-7b-lora" \
    --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": "foo-barrr/saferpaca-7b-lora",
		"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 "foo-barrr/saferpaca-7b-lora" \
        --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": "foo-barrr/saferpaca-7b-lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use foo-barrr/saferpaca-7b-lora with Docker Model Runner:
```
docker model run hf.co/foo-barrr/saferpaca-7b-lora
```

foo-barrr commited on Jul 23, 2025

Commit

7feda8e

verified ·

1 Parent(s): 0b719f1

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -1

README.md CHANGED Viewed

@@ -18,8 +18,20 @@ tags:
 ### Model Description
-<!-- Provide a longer summary of what this model is. -->
 - **Developed by:** [More Information Needed]

 ### Model Description
+LoRA finetuned Llama-2-7B-Chat on the Alpaca dataset, mixed with safety data.
+Dataset : https://github.com/vinid/safety-tuned-llamas/blob/main/data/training/saferpaca_Instructions_500.json
+Base model : https://huggingface.co/TheBloke/Llama-2-7B-Chat-fp16
+https://github.com/rahuln32/LLMs-Finetuning-Safety-Drift-Fixes/tree/main/llama2
+Params :
+Batch size : 64
+Gradient accumulation steps : 1
+LR : 5e-5
+Epochs : 1
 - **Developed by:** [More Information Needed]