Instructions to use yasserrmd/PharmaQA-270M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yasserrmd/PharmaQA-270M with Transformers:

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

pipe = pipeline("text-generation", model="yasserrmd/PharmaQA-270M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("yasserrmd/PharmaQA-270M")
model = AutoModelForMultimodalLM.from_pretrained("yasserrmd/PharmaQA-270M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yasserrmd/PharmaQA-270M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yasserrmd/PharmaQA-270M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yasserrmd/PharmaQA-270M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yasserrmd/PharmaQA-270M

SGLang

How to use yasserrmd/PharmaQA-270M 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 "yasserrmd/PharmaQA-270M" \
    --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": "yasserrmd/PharmaQA-270M",
		"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 "yasserrmd/PharmaQA-270M" \
        --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": "yasserrmd/PharmaQA-270M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use yasserrmd/PharmaQA-270M with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for yasserrmd/PharmaQA-270M to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for yasserrmd/PharmaQA-270M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for yasserrmd/PharmaQA-270M to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="yasserrmd/PharmaQA-270M",
    max_seq_length=2048,
)

Docker Model Runner
How to use yasserrmd/PharmaQA-270M with Docker Model Runner:
```
docker model run hf.co/yasserrmd/PharmaQA-270M
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

PharmaQA‑270M

PharmaQA‑270M is a compact, instruction-tuned language model for pharmacology and pharmacy domains. Based on Gemma3 (270M parameters), it was fine-tuned using LoRA and merged into a single model checkpoint for easy deployment. This model is optimized for educational and research use cases, especially where compute constraints are present.

Model Details

Property	Value
Base Model	Google Gemma3 (270M parameters)
Fine-tuning Method	LoRA using Unsloth
Dataset Used	25,000 Q&A pairs from MIRIAD-4.4M
Epochs	3
Final Format	Merged (base + LoRA weights)
Model Size	270M
License	ODC-BY v1.0 dataset license (non-commercial)
Author	Mohamed Yasser

⚠️ Caution & Intended Use

Do not use this model for real-world medical diagnosis, treatment, or care decisions.
The model was trained on MIRIAD Q&A pairs generated via LLMs from biomedical literature.
MIRIAD and this model must be used for educational, research, and academic exploration only.
This model inherits all OpenAI and ODC-BY v1.0 usage limitations associated with the dataset.

Performance Summary

From evaluation on 50 unseen pharma questions:

Metric	Value
Average Answer Length	40.3 words
Longest Answer	95 words
Shortest Answer	12 words
Empty / Short Responses	0
Clinical Accuracy	✅ Consistent terminology
Depth in Short Responses	⚠️ Limited
Best Use Case	Lightweight educational deployment (MCQs, tutoring)

Sample Inference Code

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "yasserrmd/PharmaQA-270M"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
model.eval()

question = "What is the mechanism of action of metformin?"
messages = [{"role": "user", "content": f"Q: {question} A:"}]

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
    return_dict=True
).to(model.device)

if "token_type_ids" in inputs:
    del inputs["token_type_ids"]

with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=128,
        temperature=0.7,
        top_p=0.95,
        repetition_penalty=1.05
    )

response = tokenizer.decode(outputs[0], skip_special_tokens=True).strip()
answer = response.split("A:")[-1].strip()

print("💊 Question:", question)
print("🧠 Answer:", answer)