Instructions to use ssingh22/LLAMIAFlux-7b-unprojector-inverted with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ssingh22/LLAMIAFlux-7b-unprojector-inverted with Transformers:

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

pipe = pipeline("text-generation", model="ssingh22/LLAMIAFlux-7b-unprojector-inverted")

# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("ssingh22/LLAMIAFlux-7b-unprojector-inverted", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ssingh22/LLAMIAFlux-7b-unprojector-inverted with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ssingh22/LLAMIAFlux-7b-unprojector-inverted"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ssingh22/LLAMIAFlux-7b-unprojector-inverted",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ssingh22/LLAMIAFlux-7b-unprojector-inverted

SGLang

How to use ssingh22/LLAMIAFlux-7b-unprojector-inverted 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 "ssingh22/LLAMIAFlux-7b-unprojector-inverted" \
    --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": "ssingh22/LLAMIAFlux-7b-unprojector-inverted",
		"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 "ssingh22/LLAMIAFlux-7b-unprojector-inverted" \
        --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": "ssingh22/LLAMIAFlux-7b-unprojector-inverted",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ssingh22/LLAMIAFlux-7b-unprojector-inverted with Docker Model Runner:
```
docker model run hf.co/ssingh22/LLAMIAFlux-7b-unprojector-inverted
```

ssingh22 commited on Apr 15, 2025

Commit

fce78ae

verified ·

1 Parent(s): a3c56d1

Update config.json

Browse files

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -3,7 +3,7 @@
   "architectures": [
     "LLAMIAFluxForConditionalGeneration"
   ],
-  "base_mllm": "llava-hf/llava-1.5-7b-hf"
   "feature_extraction_model_name": "openai/clip-vit-large-patch14-336",
   "ignore_index": -100,
   "im_end_token_ids": [

   "architectures": [
     "LLAMIAFluxForConditionalGeneration"
   ],
+  "base_mllm": "llava-hf/llava-1.5-7b-hf",
   "feature_extraction_model_name": "openai/clip-vit-large-patch14-336",
   "ignore_index": -100,
   "im_end_token_ids": [