Instructions to use infinitylogesh/vlm-workshop-qwen3.5-4b-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use infinitylogesh/vlm-workshop-qwen3.5-4b-sft with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B")
model = PeftModel.from_pretrained(base_model, "infinitylogesh/vlm-workshop-qwen3.5-4b-sft")

Transformers

How to use infinitylogesh/vlm-workshop-qwen3.5-4b-sft with Transformers:

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

pipe = pipeline("text-generation", model="infinitylogesh/vlm-workshop-qwen3.5-4b-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("infinitylogesh/vlm-workshop-qwen3.5-4b-sft", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use infinitylogesh/vlm-workshop-qwen3.5-4b-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "infinitylogesh/vlm-workshop-qwen3.5-4b-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": "infinitylogesh/vlm-workshop-qwen3.5-4b-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/infinitylogesh/vlm-workshop-qwen3.5-4b-sft

SGLang

How to use infinitylogesh/vlm-workshop-qwen3.5-4b-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 "infinitylogesh/vlm-workshop-qwen3.5-4b-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": "infinitylogesh/vlm-workshop-qwen3.5-4b-sft",
		"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 "infinitylogesh/vlm-workshop-qwen3.5-4b-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": "infinitylogesh/vlm-workshop-qwen3.5-4b-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use infinitylogesh/vlm-workshop-qwen3.5-4b-sft with Docker Model Runner:
```
docker model run hf.co/infinitylogesh/vlm-workshop-qwen3.5-4b-sft
```

VLM Workshop Qwen3.5 4B SFT adapter

This model is a fine-tuned version of Qwen/Qwen3.5-4B. It has been trained using TRL.

Quick start

This repository contains a LoRA adapter, not merged model weights. Load the Qwen3.5 base model first, then attach the adapter:

import torch
from peft import PeftModel
from transformers import AutoModelForImageTextToText, AutoProcessor

adapter_id = "infinitylogesh/vlm-workshop-qwen3.5-4b-sft"
base_id = "Qwen/Qwen3.5-4B"

processor = AutoProcessor.from_pretrained(adapter_id)
model = AutoModelForImageTextToText.from_pretrained(
    base_id,
    dtype=torch.bfloat16,
    device_map="auto",
)
model = PeftModel.from_pretrained(model, adapter_id).eval()

Training procedure

This model was trained with SFT.

Framework versions

PEFT 0.19.1
TRL: 1.2.0
Transformers: 5.6.2
Pytorch: 2.11.0+cu128
Datasets: 4.8.4
Tokenizers: 0.22.2

Citations

Cite TRL as:

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}

Downloads last month: 43

Model tree for infinitylogesh/vlm-workshop-qwen3.5-4b-sft

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Adapter

(477)

this model

Collection including infinitylogesh/vlm-workshop-qwen3.5-4b-sft

VLM Workshop

Collection

Models trained for LLM to VLM workshop : https://logeshumapathi.com/VLM_workshop/ • 7 items • Updated 3 days ago