Instructions to use paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c 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, "paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c")

Transformers

How to use paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c with Transformers:

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

pipe = pipeline("text-generation", model="paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c

SGLang

How to use paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c 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 "paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c" \
    --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": "paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c",
		"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 "paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c" \
        --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": "paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c with Docker Model Runner:
```
docker model run hf.co/paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c
```

20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c

This model is a fine-tuned version of Qwen/Qwen3-VL-2B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1521

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 14
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.2087	0.3146	7	0.1920
0.0952	0.6292	14	0.1692
0.0892	0.9438	21	0.1599
0.0597	1.2247	28	0.1590
0.0563	1.5393	35	0.1550
0.0773	1.8539	42	0.1542
0.043	2.1348	49	0.1515
0.044	2.4494	56	0.1522
0.0346	2.7640	63	0.1521

Framework versions

PEFT 0.17.1
Transformers 4.57.0
Pytorch 2.11.0a0+eb65b36914.nv26.02
Datasets 4.1.1
Tokenizers 0.22.2

Downloads last month: 2

Model tree for paulo037/20260502T215713Z-legal_extraction_v2-baseline-2b-b346a08c

Base model

Qwen/Qwen3-VL-2B-Instruct

Adapter

(92)

this model