Instructions to use leobo09263013/all_train with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leobo09263013/all_train with Transformers:

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

pipe = pipeline("image-text-to-text", model="leobo09263013/all_train", trust_remote_code=True)
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("leobo09263013/all_train", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("leobo09263013/all_train", trust_remote_code=True, 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 leobo09263013/all_train with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "leobo09263013/all_train"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "leobo09263013/all_train",
		"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/leobo09263013/all_train

SGLang

How to use leobo09263013/all_train 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 "leobo09263013/all_train" \
    --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": "leobo09263013/all_train",
		"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 "leobo09263013/all_train" \
        --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": "leobo09263013/all_train",
		"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 leobo09263013/all_train with Docker Model Runner:
```
docker model run hf.co/leobo09263013/all_train
```

all_train

Final Qwen3-VL-8B CE ablation checkpoint from job 713, step 2712 (one epoch, 173,553 training examples).

All assistant replies are supervised; silent-token weights use the reciprocal of the single-device micro-batch silent-token count.

Prompts and padding remain masked. Samples without silent tokens retain all original assistant labels. The reply terminator and newline retain weight 1. See training_metadata.json for training settings.

This repository contains model weights, tokenizer, processor settings and custom model/processor code. Load with Transformers 4.57.1 and trust_remote_code=True, for example:

from transformers import AutoProcessor, AutoModelForCausalLM

repo_id = "leobo09263013/all_train"
processor = AutoProcessor.from_pretrained(repo_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo_id, trust_remote_code=True, dtype="auto", device_map="auto"
)

The saved weights are ready for inference. The Python training loss hook is not serialized with the weights; further training must explicitly configure the corresponding AURA CE objective. Optimizer/RNG states are retained in the original training checkpoint and are not part of this model export.

Full-training mean loss: 0.8174977. This is a training metric, not an evaluation score. The two ablation losses use different supervision/weighting and are not directly comparable. No downstream evaluation is reported.

The base model is Qwen/Qwen3-VL-8B-Instruct. Preserve its applicable license and notices when using or redistributing the model.

Downloads last month: 24

Safetensors

Model size

770k params

Tensor type

BF16

Model tree for leobo09263013/all_train

Base model

Qwen/Qwen3-VL-8B-Instruct

Finetuned

(735)

this model