Instructions to use ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("ferrazzipietro/unsup-Qwen3-8B-datav3-only_mask_w_item_mesh")
model = PeftModel.from_pretrained(base_model, "ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh")

Transformers

How to use ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh with Transformers:

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

pipe = pipeline("text-generation", model="ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh

SGLang

How to use ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh 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 "ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh" \
    --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": "ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh",
		"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 "ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh" \
        --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": "ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh with Docker Model Runner:
```
docker model run hf.co/ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh
```

meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh

This model is a fine-tuned version of ferrazzipietro/unsup-Qwen3-8B-datav3-only_mask_w_item_mesh on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.5778
F1 Micro: 0.8977
F1 Macro: 0.8905
F1 Weighted: 0.8977
Class/f1 Results Per Class: {}
Items/f1 Scores Per Item: {'Disease Models, Animal': 0.8571184000622544, 'Animals': 0.9414907872696818, 'Pregnancy': 0.9134651504285763, 'Aged': 0.874931822949444, 'Time Factors': 0.621755779322082, 'Surveys and Questionnaires': 0.8991391167031735, 'Cell Line, Tumor': 0.8556286549707601, 'Signal Transduction': 0.8322662440570523, 'Adolescent': 0.8287955699123212, 'Prognosis': 0.8414678860638821, 'Male': 0.7407382861687322, 'Risk Factors': 0.8782002726859567, 'Mice': 0.9083138977163718, 'Treatment Outcome': 0.8537806547787833}

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: 0.0003
train_batch_size: 32
eval_batch_size: 32
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-07 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Micro	F1 Macro	F1 Weighted	Class/f1 Results Per Class	Items/f1 Scores Per Item
4.1828	0.0517	20	2.1711	0.0	0.0	0.0	{}	{'Pregnancy': 0.0, 'Animals': 0.0, 'Aged': 0.0, 'Disease Models, Animal': 0.0, 'Time Factors': 0.0, 'Surveys and Questionnaires': 0.0, 'Cell Line, Tumor': 0.0, 'Signal Transduction': 0.0, 'Adolescent': 0.0, 'Prognosis': 0.0, 'Male': 0.0, 'Risk Factors': 0.0, 'Mice': 0.0, 'Treatment Outcome': 0.0}
3.2031	0.1034	40	1.6619	0.7409	0.6817	0.7123	{}	{'Pregnancy': 0.9137502822307519, 'Animals': 0.8154411764705882, 'Aged': 0.34839842035980695, 'Disease Models, Animal': 0.8119457485654669, 'Time Factors': 0.577951388888889, 'Surveys and Questionnaires': 0.911839351707556, 'Cell Line, Tumor': 0.7375497567448033, 'Signal Transduction': 0.7842612700510916, 'Adolescent': 0.5668395668395668, 'Prognosis': 0.8145669517304712, 'Male': 0.2877874694066782, 'Risk Factors': 0.8322033492249827, 'Mice': 0.7040664442268001, 'Treatment Outcome': 0.6655943881786486}
3.0344	0.1550	60	1.6264	0.8385	0.2059	0.8353	{}	{'Pregnancy': 0.6353566591878398, 'Animals': 0.8834189608177866, 'Aged': 0.6418811934399662, 'Disease Models, Animal': 0.8171617817519456, 'Time Factors': 0.46356855995410207, 'Surveys and Questionnaires': 0.9200821290373529, 'Cell Line, Tumor': 0.6153378337286384, 'Signal Transduction': 0.7662248235496643, 'Adolescent': 0.6860733521415747, 'Prognosis': 0.26052005034505066, 'Male': 0.5031009812390635, 'Risk Factors': 0.8302347046413503, 'Mice': 0.7567812520230466, 'Treatment Outcome': 0.704342330956035}
3.0719	0.2067	80	1.6134	0.8612	0.5699	0.8617	{}	{'Pregnancy': 0.935798319327731, 'Animals': 0.9204848606109111, 'Aged': 0.5928352620830497, 'Disease Models, Animal': 0.8220279427219332, 'Time Factors': 0.5357781897316031, 'Surveys and Questionnaires': 0.9180774402648002, 'Cell Line, Tumor': 0.8269592476489028, 'Signal Transduction': 0.8583496769482862, 'Adolescent': 0.507077856420627, 'Prognosis': 0.8353105095541402, 'Male': 0.6488762559492333, 'Risk Factors': 0.8466263378315495, 'Mice': 0.8460322659471038, 'Treatment Outcome': 0.8440387777084868}
3.0094	0.2584	100	1.6056	0.8625	0.8586	0.8639	{}	{'Pregnancy': 0.935798319327731, 'Animals': 0.9129560271882369, 'Aged': 0.606174869448235, 'Disease Models, Animal': 0.8165394402035624, 'Time Factors': 0.6113454367626383, 'Surveys and Questionnaires': 0.9130405405405405, 'Cell Line, Tumor': 0.868859649122807, 'Signal Transduction': 0.843268509435051, 'Adolescent': 0.7964833520389076, 'Prognosis': 0.8244682911711153, 'Male': 0.6058505630905477, 'Risk Factors': 0.8467261904761905, 'Mice': 0.8845154845154846, 'Treatment Outcome': 0.8444458241817943}
3.0125	0.3101	120	1.5999	0.8627	0.5730	0.8643	{}	{'Pregnancy': 0.9474740807964139, 'Animals': 0.9125069715560513, 'Aged': 0.5767102615694165, 'Disease Models, Animal': 0.8112977099236641, 'Time Factors': 0.42706633031607066, 'Surveys and Questionnaires': 0.9191919191919191, 'Cell Line, Tumor': 0.868859649122807, 'Signal Transduction': 0.8505037587204773, 'Adolescent': 0.8275158533223049, 'Prognosis': 0.8305972482801751, 'Male': 0.6648556073938463, 'Risk Factors': 0.8260135135135135, 'Mice': 0.8729885057471265, 'Treatment Outcome': 0.8514155223519448}
3.0234	0.3618	140	1.5959	0.8823	0.5829	0.8814	{}	{'Pregnancy': 0.9276515151515152, 'Animals': 0.9300643799472296, 'Aged': 0.825487012987013, 'Disease Models, Animal': 0.8367159633716443, 'Time Factors': 0.3774724065280966, 'Surveys and Questionnaires': 0.9111685375111039, 'Cell Line, Tumor': 0.8269592476489028, 'Signal Transduction': 0.832628763695971, 'Adolescent': 0.763444739351148, 'Prognosis': 0.8012042113760973, 'Male': 0.7561162038645535, 'Risk Factors': 0.8419342462750257, 'Mice': 0.8750276316939385, 'Treatment Outcome': 0.857577734290063}
3.0203	0.4134	160	1.5910	0.8850	0.8783	0.8847	{}	{'Pregnancy': 0.9409673929840828, 'Animals': 0.9231318905675786, 'Aged': 0.8040116086844715, 'Disease Models, Animal': 0.8427006932583141, 'Time Factors': 0.5864715447154472, 'Surveys and Questionnaires': 0.9200821290373529, 'Cell Line, Tumor': 0.8568804077278653, 'Signal Transduction': 0.8706002181300307, 'Adolescent': 0.7920135938827527, 'Prognosis': 0.8318610506550591, 'Male': 0.7630274032187908, 'Risk Factors': 0.8485100890719854, 'Mice': 0.9004015077023926, 'Treatment Outcome': 0.855926055926056}
2.9797	0.4651	180	1.5876	0.8886	0.8838	0.8891	{}	{'Pregnancy': 0.9409673929840828, 'Animals': 0.9201746582259984, 'Aged': 0.8395160739881237, 'Disease Models, Animal': 0.8396327713948244, 'Time Factors': 0.5930467091295117, 'Surveys and Questionnaires': 0.9200821290373529, 'Cell Line, Tumor': 0.8610551751913009, 'Signal Transduction': 0.8706002181300307, 'Adolescent': 0.8173591114767585, 'Prognosis': 0.8175925925925926, 'Male': 0.7521625934324347, 'Risk Factors': 0.8388713021790302, 'Mice': 0.9027144341559046, 'Treatment Outcome': 0.8497952497952498}
2.9703	0.5168	200	1.5854	0.8865	0.8797	0.8861	{}	{'Pregnancy': 0.9276515151515152, 'Animals': 0.9269061445432276, 'Aged': 0.8180563269840233, 'Disease Models, Animal': 0.8438264585271719, 'Time Factors': 0.5962016260162601, 'Surveys and Questionnaires': 0.9200821290373529, 'Cell Line, Tumor': 0.8486956521739131, 'Signal Transduction': 0.8353187515916358, 'Adolescent': 0.8196286472148542, 'Prognosis': 0.8175925925925926, 'Male': 0.7602640264026403, 'Risk Factors': 0.8467261904761905, 'Mice': 0.9025708061002178, 'Treatment Outcome': 0.851726089417091}
2.9609	0.5685	220	1.5826	0.8878	0.8834	0.8884	{}	{'Pregnancy': 0.9276515151515152, 'Animals': 0.9164388842164284, 'Aged': 0.8321133412042503, 'Disease Models, Animal': 0.850780742816141, 'Time Factors': 0.5917817014446228, 'Surveys and Questionnaires': 0.9163026630970833, 'Cell Line, Tumor': 0.8610551751913009, 'Signal Transduction': 0.8784624334362554, 'Adolescent': 0.8175048355899419, 'Prognosis': 0.8300552104899931, 'Male': 0.7568753010511999, 'Risk Factors': 0.8320130475302889, 'Mice': 0.8981269494937079, 'Treatment Outcome': 0.8481004024282108}
2.9797	0.6202	240	1.5811	0.8916	0.8870	0.8921	{}	{'Pregnancy': 0.9409673929840828, 'Animals': 0.9162113252631023, 'Aged': 0.8606331076736886, 'Disease Models, Animal': 0.8500224014336917, 'Time Factors': 0.5865385995893814, 'Surveys and Questionnaires': 0.9163026630970833, 'Cell Line, Tumor': 0.8730665646293543, 'Signal Transduction': 0.8745464343452487, 'Adolescent': 0.8153679065978822, 'Prognosis': 0.8369257219268362, 'Male': 0.7538794265619533, 'Risk Factors': 0.8311228224271703, 'Mice': 0.9004015077023926, 'Treatment Outcome': 0.8468341527761123}
2.9594	0.6718	260	1.5797	0.8901	0.8863	0.8909	{}	{'Pregnancy': 0.9659930561737737, 'Animals': 0.9159795630725863, 'Aged': 0.8556186353625492, 'Disease Models, Animal': 0.854293588143838, 'Time Factors': 0.6112509549035078, 'Surveys and Questionnaires': 0.9206558005418544, 'Cell Line, Tumor': 0.8974159292035397, 'Signal Transduction': 0.8749727841982877, 'Adolescent': 0.8274987316083207, 'Prognosis': 0.8353564694491158, 'Male': 0.7484183791272223, 'Risk Factors': 0.8154121863799283, 'Mice': 0.9049287118977385, 'Treatment Outcome': 0.8429489077023267}
3.0016	0.7235	280	1.5781	0.8881	0.8810	0.8875	{}	{'Pregnancy': 0.9383930587362513, 'Animals': 0.9193819310314895, 'Aged': 0.8699763593380614, 'Disease Models, Animal': 0.8096759291882962, 'Time Factors': 0.5272428794221456, 'Surveys and Questionnaires': 0.8811702925731433, 'Cell Line, Tumor': 0.8486956521739131, 'Signal Transduction': 0.8067113024071417, 'Adolescent': 0.7924629016760969, 'Prognosis': 0.8133796463370624, 'Male': 0.7781196828729682, 'Risk Factors': 0.8494152046783625, 'Mice': 0.9094948502160247, 'Treatment Outcome': 0.8501525165226234}
2.9047	0.7752	300	1.5768	0.8886	0.8844	0.8893	{}	{'Pregnancy': 0.9537362238101005, 'Animals': 0.9162113252631023, 'Aged': 0.8386404968603095, 'Disease Models, Animal': 0.8488471096405308, 'Time Factors': 0.5969163274880495, 'Surveys and Questionnaires': 0.9200821290373529, 'Cell Line, Tumor': 0.8862218780917968, 'Signal Transduction': 0.8754280821917808, 'Adolescent': 0.8210526315789474, 'Prognosis': 0.8337296073284957, 'Male': 0.7484183791272223, 'Risk Factors': 0.8269930179426774, 'Mice': 0.9003790595225899, 'Treatment Outcome': 0.8455383428872294}
3.0	0.8269	320	1.5761	0.8938	0.8888	0.8940	{}	{'Pregnancy': 0.9517676767676768, 'Animals': 0.9145822698655777, 'Aged': 0.8628094870158229, 'Disease Models, Animal': 0.8497156957408003, 'Time Factors': 0.5910303701867701, 'Surveys and Questionnaires': 0.9200821290373529, 'Cell Line, Tumor': 0.868859649122807, 'Signal Transduction': 0.8686971235194585, 'Adolescent': 0.8293936785143279, 'Prognosis': 0.8452885054177677, 'Male': 0.7597883597883598, 'Risk Factors': 0.8345780133301213, 'Mice': 0.9004341415465269, 'Treatment Outcome': 0.8461607949412827}
2.9703	0.8786	340	1.5758	0.8898	0.8854	0.8904	{}	{'Pregnancy': 0.9537362238101005, 'Animals': 0.918527583680953, 'Aged': 0.8538615965989608, 'Disease Models, Animal': 0.8444952271152011, 'Time Factors': 0.5939826302729528, 'Surveys and Questionnaires': 0.9169085504458822, 'Cell Line, Tumor': 0.8918556936053801, 'Signal Transduction': 0.8784624334362554, 'Adolescent': 0.8208387206947867, 'Prognosis': 0.8320563069853515, 'Male': 0.7484183791272223, 'Risk Factors': 0.821128374483107, 'Mice': 0.9049072840897449, 'Treatment Outcome': 0.8455383428872294}
2.9781	0.9302	360	1.5758	0.8928	0.8882	0.8933	{}	{'Pregnancy': 0.9537362238101005, 'Animals': 0.9187471292023011, 'Aged': 0.8626156433978133, 'Disease Models, Animal': 0.8481744922578447, 'Time Factors': 0.58528276175335, 'Surveys and Questionnaires': 0.9200821290373529, 'Cell Line, Tumor': 0.8805125836989147, 'Signal Transduction': 0.8784624334362554, 'Adolescent': 0.8229934924078091, 'Prognosis': 0.8419341216216216, 'Male': 0.7568753010511999, 'Risk Factors': 0.8311948763288983, 'Mice': 0.9094559160930842, 'Treatment Outcome': 0.8474925373134329}
2.9531	0.9819	380	1.5759	0.8929	0.8883	0.8934	{}	{'Pregnancy': 0.9409673929840828, 'Animals': 0.9187471292023011, 'Aged': 0.8606331076736886, 'Disease Models, Animal': 0.855790770609319, 'Time Factors': 0.5918812745525971, 'Surveys and Questionnaires': 0.9200821290373529, 'Cell Line, Tumor': 0.8805125836989147, 'Signal Transduction': 0.8784624334362554, 'Adolescent': 0.8203830068236848, 'Prognosis': 0.8452885054177677, 'Male': 0.7545061283345349, 'Risk Factors': 0.8277989161766401, 'Mice': 0.9049287118977385, 'Treatment Outcome': 0.8501043279262301}

Framework versions

PEFT 0.18.1
Transformers 4.51.0
Pytorch 2.8.0+cu128
Datasets 3.6.0
Tokenizers 0.21.0

Downloads last month: 11

Model tree for ferrazzipietro/meshTask-unsup-Qwen3-8B-datav3-only_mask_w_item_mesh

Base model

ferrazzipietro/unsup-Qwen3-8B-datav3-only_mask_w_item_mesh

Adapter

(1)

this model