Instructions to use psp-dada/LLaVA-v1.5-13B-SENTINEL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use psp-dada/LLaVA-v1.5-13B-SENTINEL with Transformers:

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

pipe = pipeline("image-text-to-text", model="psp-dada/LLaVA-v1.5-13B-SENTINEL")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("psp-dada/LLaVA-v1.5-13B-SENTINEL", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use psp-dada/LLaVA-v1.5-13B-SENTINEL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "psp-dada/LLaVA-v1.5-13B-SENTINEL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "psp-dada/LLaVA-v1.5-13B-SENTINEL",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/psp-dada/LLaVA-v1.5-13B-SENTINEL

SGLang

How to use psp-dada/LLaVA-v1.5-13B-SENTINEL 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 "psp-dada/LLaVA-v1.5-13B-SENTINEL" \
    --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": "psp-dada/LLaVA-v1.5-13B-SENTINEL",
		"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 "psp-dada/LLaVA-v1.5-13B-SENTINEL" \
        --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": "psp-dada/LLaVA-v1.5-13B-SENTINEL",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use psp-dada/LLaVA-v1.5-13B-SENTINEL with Docker Model Runner:
```
docker model run hf.co/psp-dada/LLaVA-v1.5-13B-SENTINEL
```

psp_dada commited on Jul 9, 2025

Commit

ceea9a1

1 Parent(s): f6b9b57

add file

Browse files

Files changed (2) hide show

adapter_config.json +1 -1
config.json +1 -1

adapter_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "/psp/llm/utils/models/repo/llava-v1.5-13b",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

 {
   "alpha_pattern": {},
   "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "_attn_implementation_autoset": true,
-  "_name_or_path": "/psp/llm/utils/models/repo/llava-v1.5-13b",
   "architectures": [
     "LlavaLlamaForCausalLM"
   ],

 {
   "_attn_implementation_autoset": true,
+  "_name_or_path": "liuhaotian/llava-v1.5-13b",
   "architectures": [
     "LlavaLlamaForCausalLM"
   ],