Instructions to use redflash6/sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use redflash6/sft with Transformers:

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

pipe = pipeline("image-text-to-text", model="redflash6/sft")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("redflash6/sft")
model = AutoModelForMultimodalLM.from_pretrained("redflash6/sft", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use redflash6/sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "redflash6/sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redflash6/sft",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/redflash6/sft

SGLang

How to use redflash6/sft 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 "redflash6/sft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redflash6/sft",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "redflash6/sft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redflash6/sft",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use redflash6/sft with Docker Model Runner:
```
docker model run hf.co/redflash6/sft
```

redflash6 commited on 24 days ago

Commit

0106c0a

verified ·

1 Parent(s): fae8090

Remove checkpoint step details from model card

Browse files

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -20,7 +20,6 @@ REEL is a tool-using visual-memory planner for long-horizon, multi-shot video ge
 ## Checkpoint
 - **Stage:** Supervised fine-tuning.
-- **Selected checkpoint:** stage-local step 1034.
 - **Parent checkpoint:** [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B).
 - **Stored precision:** float32, in Hugging Face Safetensors format.
@@ -45,7 +44,7 @@ This loads the planner, not an end-to-end video generator. Use the [REEL tool ru
 ## Released stages
-[SFT](https://huggingface.co/redflash6/sft) · [Single-shot GRPO](https://huggingface.co/redflash6/singleshotgrpo) · [Multi-shot GRPO, step 50](https://huggingface.co/redflash6/multishotgrpo)
 ## Citation

 ## Checkpoint
 - **Stage:** Supervised fine-tuning.
 - **Parent checkpoint:** [Qwen/Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B).
 - **Stored precision:** float32, in Hugging Face Safetensors format.
 ## Released stages
+[SFT](https://huggingface.co/redflash6/sft) · [Single-shot GRPO](https://huggingface.co/redflash6/singleshotgrpo) · [Multi-shot GRPO](https://huggingface.co/redflash6/multishotgrpo)
 ## Citation