Instructions to use SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-VL-2B-Instruct")
model = PeftModel.from_pretrained(base_model, "SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl")

Transformers

How to use SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl with Transformers:

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

pipe = pipeline("text-generation", model="SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl

SGLang

How to use SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl 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 "SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl" \
    --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": "SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl" \
        --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": "SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl with Docker Model Runner:
```
docker model run hf.co/SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl
```

Model Card for Model ID

This model is a fine-tuned version of Qwen/Qwen3-VL-2B-Instruct. It has been trained using TRL.

Refer main github repository for more details: https://github.com/SarveshBTelang/SFT-Qwen3-Vision-Language-Assistant-for-Autonomous-Driving

For inference:

Model Details

Model Description

A parameter-efficient fine-tuned vision-language model for ADAS and autonomous driving applications. This model processes driving videos as sequential multi-image inputs to generate structured scene descriptions, driving parameters, and safety risk assessments. Key Features:

Fine-tuned using QLoRA (4-bit quantization) on BDD100K driving videos ~~2B parameters with 1.64% LoRA adapter overhead (~~35M trainable params) Generates outputs in natural language and structured JSON format Performs temporal reasoning across video frames for context-aware understanding Optimized for T4 GPU deployment (<16GB VRAM)

Capabilities:

Scene understanding and object detection across temporal sequences Contextual awareness of traffic rules and driving norms Safety-critical hazard identification (pedestrians, lane changes, etc.) Structured output generation adhering to JSON schemas

Developed by: Sarvesh Telang
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: [More Information Needed]
Language(s) (NLP): [More Information Needed]
License: Apache-2.0
Finetuned from model [optional]: Qwen3-VL-2B-Instruct

Model Sources [optional]

Repository: Github
Paper [optional]: [More Information Needed]
Demo [optional]: Colab

Uses

Autonomous driving perception, ADAS systems, driving scene analysis, safety assessment, driver assistance applications.

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Refer to the colab notebook for model inference.

Training Details

Training Data

BDD100K-derived instruction-following dataset

Training Procedure

Refer to the "generate_instruction_dataset.ipynb" from the main github repository.

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

Training regime: fp16 mixed precision

Speeds, Sizes, Times [optional]

Training Time: ~2-4 hours (T4 GPU) Memory Footprint: <16GB VRAM Inference Latency: ~60 seconds per video

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

[More Information Needed]

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: Nvidia T4 GPU
Hours used: 2-4 hours
Cloud Provider: [More Information Needed]
Compute Region: [More Information Needed]
Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

Hardware: Google Colab T4 GPU (2-4 hour training time) Framework: TRL (Transformer Reinforcement Learning) with PEFT

Software

[More Information Needed]

Citation [optional]

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

@InProceedings{bdd100k,
    author = {Yu, Fisher and Chen, Haofeng and Wang, Xin and Xian, Wenqi and Chen, Yingying and Liu, Fangchen and Madhavan, Vashisht and Darrell, Trevor},
    title = {BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning},
    booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    month = {June},
    year = {2020}
}

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Framework versions

PEFT 0.18.0
TRL: 0.26.0
Transformers: 4.57.3
Pytorch: 2.9.0+cu126
Datasets: 4.4.1
Tokenizers: 0.22.1

Downloads last month: 2

Model tree for SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl

Base model

Qwen/Qwen3-VL-2B-Instruct

Adapter

(68)

this model

Paper for SarveshBTelang/SFT_VLA_Qwen3-VL-2B-Instruct-multimage-trl

Quantifying the Carbon Emissions of Machine Learning

Paper • 1910.09700 • Published Oct 21, 2019 • 52