Instructions to use Amirhossein75/clip-vit-base-mmhs150k-mtl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Amirhossein75/clip-vit-base-mmhs150k-mtl with Transformers:

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

pipe = pipeline("image-text-to-text", model="Amirhossein75/clip-vit-base-mmhs150k-mtl", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Amirhossein75/clip-vit-base-mmhs150k-mtl", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Amirhossein75/clip-vit-base-mmhs150k-mtl with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Amirhossein75/clip-vit-base-mmhs150k-mtl"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Amirhossein75/clip-vit-base-mmhs150k-mtl",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Amirhossein75/clip-vit-base-mmhs150k-mtl

SGLang

How to use Amirhossein75/clip-vit-base-mmhs150k-mtl 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 "Amirhossein75/clip-vit-base-mmhs150k-mtl" \
    --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": "Amirhossein75/clip-vit-base-mmhs150k-mtl",
		"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 "Amirhossein75/clip-vit-base-mmhs150k-mtl" \
        --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": "Amirhossein75/clip-vit-base-mmhs150k-mtl",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Amirhossein75/clip-vit-base-mmhs150k-mtl with Docker Model Runner:
```
docker model run hf.co/Amirhossein75/clip-vit-base-mmhs150k-mtl
```

Amirhossein75 commited on Dec 27, 2025

Commit

5fe86f6

verified ·

1 Parent(s): 93f0f2c

Upload inference_config.json with huggingface_hub

Browse files

Files changed (1) hide show

inference_config.json +22 -0

inference_config.json ADDED Viewed

	@@ -0,0 +1,22 @@

+{
+  "encoder_name": "openai/clip-vit-base-patch32",
+  "backend": "clip",
+  "head": "mtl",
+  "fusion_dim": 512,
+  "threshold": 0.5,
+  "thresholds": [
+    0.3,
+    0.7,
+    0.49999999999999994,
+    0.3,
+    0.5499999999999999
+  ],
+  "class_names": [
+    "racist",
+    "sexist",
+    "homophobe",
+    "religion",
+    "otherhate"
+  ],
+  "best_checkpoint_dir": "runs/clip_mtl_mmhshateful\\checkpoint-11236"
+}