Instructions to use pbhaskar/full_ft_safety_vector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pbhaskar/full_ft_safety_vector with Transformers:

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

pipe = pipeline("text-generation", model="pbhaskar/full_ft_safety_vector")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pbhaskar/full_ft_safety_vector")
model = AutoModelForCausalLM.from_pretrained("pbhaskar/full_ft_safety_vector")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pbhaskar/full_ft_safety_vector with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/pbhaskar/full_ft_safety_vector

SGLang

How to use pbhaskar/full_ft_safety_vector 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 "pbhaskar/full_ft_safety_vector" \
    --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": "pbhaskar/full_ft_safety_vector",
		"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 "pbhaskar/full_ft_safety_vector" \
        --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": "pbhaskar/full_ft_safety_vector",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pbhaskar/full_ft_safety_vector with Docker Model Runner:
```
docker model run hf.co/pbhaskar/full_ft_safety_vector
```

pbhaskar commited on Apr 3, 2025

Commit

1830f45

verified ·

1 Parent(s): 041c0ca

Upload Gemma3ForCausalLM

Browse files

Files changed (2) hide show

config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -27,7 +27,7 @@
   "rope_theta": 1000000,
   "sliding_window": 512,
   "sliding_window_pattern": 6,
-  "torch_dtype": "float32",
   "transformers_version": "4.50.3",
   "use_cache": true,
   "vocab_size": 262144

   "rope_theta": 1000000,
   "sliding_window": 512,
   "sliding_window_pattern": 6,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.50.3",
   "use_cache": true,
   "vocab_size": 262144

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b11434dd55c290e6cbd2531dca913f9f9577977efe62e78751f331456848905
-size 3999582960

 version https://git-lfs.github.com/spec/v1
+oid sha256:29dfca2837a793363d565602bc5d2ad8e1f0a3a694c7f1ed908902b791cf3356
+size 1999811208