Instructions to use paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24 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, "paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24")

Transformers

How to use paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24 with Transformers:

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

pipe = pipeline("text-generation", model="paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24

SGLang

How to use paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24 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 "paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24" \
    --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": "paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24",
		"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 "paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24" \
        --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": "paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24 with Docker Model Runner:
```
docker model run hf.co/paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24
```

20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24

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: 0.1285
Graft/constrained Ratio: 1.0
Graft/constrained Tokens: 53933.0
Graft/fallback Samples: 0.0
Graft/standard Fallback Samples: 0.0

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	Ratio	Tokens
0.0914	0.3303	27	0.1261	1.0	69377.0
0.0497	0.6606	54	0.1225	1.0	50808.0
0.0401	0.9908	81	0.1234	1.0	38265.0
0.0355	1.3180	108	0.1239	1.0	28908.0
0.0384	1.6483	135	0.1257	1.0	58447.0
0.0307	1.9786	162	0.1229	1.0	51038.0
0.0253	2.3058	189	0.1291	1.0	40722.0
0.0269	2.6361	216	0.1301	1.0	28908.0
0.022	2.9664	243	0.1285	1.0	53933.0

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: 1

Model tree for paulo037/20260503T001054Z-legal_extraction_v2-graft-soft-invalid-b10-2b-3k-a76acd24

Base model

Qwen/Qwen3-VL-2B-Instruct

Adapter

(92)

this model