Instructions to use pedrobsb/alzbot-qwen3-4b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pedrobsb/alzbot-qwen3-4b-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base_model, "pedrobsb/alzbot-qwen3-4b-lora")

Transformers

How to use pedrobsb/alzbot-qwen3-4b-lora with Transformers:

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

pipe = pipeline("text-generation", model="pedrobsb/alzbot-qwen3-4b-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("pedrobsb/alzbot-qwen3-4b-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pedrobsb/alzbot-qwen3-4b-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pedrobsb/alzbot-qwen3-4b-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pedrobsb/alzbot-qwen3-4b-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pedrobsb/alzbot-qwen3-4b-lora

SGLang

How to use pedrobsb/alzbot-qwen3-4b-lora 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 "pedrobsb/alzbot-qwen3-4b-lora" \
    --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": "pedrobsb/alzbot-qwen3-4b-lora",
		"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 "pedrobsb/alzbot-qwen3-4b-lora" \
        --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": "pedrobsb/alzbot-qwen3-4b-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pedrobsb/alzbot-qwen3-4b-lora with Docker Model Runner:
```
docker model run hf.co/pedrobsb/alzbot-qwen3-4b-lora
```

AlzBot: Alzheimer's Disease Research Assistant (LoRA Adapter)

A domain-specific LoRA adapter fine-tuned on 95,374 biomedical records (~110M tokens) from 13 public data sources, specializing in Alzheimer's disease research.

Model Details

Parameter	Value
Base Model	Qwen/Qwen3-4B-Instruct-2507
Adapter Type	LoRA (r=64, α=128)
Trainable Parameters	161.5M (2.1% of 7.66B total)
Training Data	95,374 examples from 13 biomedical APIs
Training Tokens	~110M
Best Eval Loss	0.830
Token Accuracy	80.4%
Training Time	72.6 hours on NVIDIA A10G
Training Cost	~$88

Data Sources

The AlzCorpus was constructed from 13 public biomedical APIs:

Europe PMC (75,954 articles) — research abstracts and open-access full text
openFDA (25,100) — drug labels, indications, warnings
PubMed (9,994) — articles with metadata
ClinicalTrials.gov (4,194) — clinical trial records
SIDER (1,226) — drug side effects
Open Targets (868) — drug-target associations
Plus: ChEMBL, PharmGKB, OMIM, and 6,104 conversational Q&A pairs

All records are evidence-graded (A-E) based on study type, sample size, and recency.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen3-4B-Instruct-2507",
    dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base, "pedrobsb/alzbot-qwen3-4b-lora")
model.eval()

messages = [
    {"role": "system", "content": "You are AlzBot, a specialized Alzheimer's disease research assistant."},
    {"role": "user", "content": "What are the FDA-approved treatments for Alzheimer's disease?"},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

with torch.no_grad():
    output = model.generate(**inputs, max_new_tokens=512, temperature=0.3, top_p=0.9, do_sample=True)
print(tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Training Configuration

LoRA targets: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Optimizer: Paged AdamW 8-bit
Learning rate: 1e-4 (cosine schedule, 500 warmup steps)
Batch size: 16 (effective)
Sequence length: 512 tokens (with packing)
Precision: float16
Epochs: 2
GPU: NVIDIA A10G (24 GB VRAM), AWS g5.2xlarge

Eval Results

Epoch	Eval Loss	Token Accuracy
0.5	0.855	79.8%
1.0	0.836	80.2%
1.5	0.832	80.3%
2.0	0.830	80.4%

Topics Covered

FDA-approved treatments (donepezil, rivastigmine, galantamine, memantine, lecanemab, donanemab)
Genetic risk factors (APOE e4, PSEN1, APP)
Biomarkers (amyloid-beta, tau, CSF markers, PET imaging)
Clinical trials and emerging therapies
Drug interactions and contraindications
Caregiver support and patient care
Evidence grading and source citations

Citation

@article{albuquerque2026alzbot,
  title={AlzBot: Toward Community-Driven Lightweight Domain Language Models as Living Alternatives to Systematic Literature Reviews},
  author={Albuquerque, Pedro H. M.},
  year={2026}
}

Disclaimer

This model is designed as a research tool for clinicians and researchers, not as a direct-to-patient advisory system. It should not be used for individual treatment decisions without verification by a qualified clinician.

Framework Versions

PEFT 0.19.1
Transformers 5.12.1
PyTorch 2.12.1+cu130
TRL 1.7.0

Downloads last month: 21

Model tree for pedrobsb/alzbot-qwen3-4b-lora

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5632)

this model