Instructions to use RetrO21/agrofinetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RetrO21/agrofinetune with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")
model = PeftModel.from_pretrained(base_model, "RetrO21/agrofinetune")

Transformers

How to use RetrO21/agrofinetune with Transformers:

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

pipe = pipeline("text-generation", model="RetrO21/agrofinetune")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("RetrO21/agrofinetune")
model = AutoModelForImageTextToText.from_pretrained("RetrO21/agrofinetune")
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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RetrO21/agrofinetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RetrO21/agrofinetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RetrO21/agrofinetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RetrO21/agrofinetune

SGLang

How to use RetrO21/agrofinetune 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 "RetrO21/agrofinetune" \
    --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": "RetrO21/agrofinetune",
		"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 "RetrO21/agrofinetune" \
        --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": "RetrO21/agrofinetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RetrO21/agrofinetune with Docker Model Runner:
```
docker model run hf.co/RetrO21/agrofinetune
```

Model Card for output

This model is a fine-tuned version of Qwen/Qwen2-VL-2B-Instruct.
It has been trained using TRL and PEFT LoRA.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"

generator = pipeline(
    "text-generation", 
    model="RetrO21/agrofinetune",  # replace with your repo
    device="cuda"
)

output = generator(
    [{"role": "user", "content": question}],
    max_new_tokens=128,
    return_full_text=False
)[0]

print(output["generated_text"])

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

F32

Model tree for RetrO21/agrofinetune

Base model

Qwen/Qwen2-VL-2B

Finetuned

Qwen/Qwen2-VL-2B-Instruct

Adapter

(160)

this model