Instructions to use Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k with Transformers:

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

pipe = pipeline("text-generation", model="Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k")
model = AutoModelForCausalLM.from_pretrained("Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k", device_map="auto")
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 Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k

SGLang

How to use Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k 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 "Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k" \
    --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": "Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k",
		"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 "Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k" \
        --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": "Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k with Docker Model Runner:
```
docker model run hf.co/Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k
```

Qwen2.5-0.5B-Med-Pre-Trained-92k

A continued pre-trained (CPT) version of Qwen/Qwen2.5-0.5B on 92,000 English PubMed biomedical abstracts.

Info:

Training Details

Property	Value
Base model	Qwen/Qwen2.5-0.5B
Training type	Full-parameter Continued Pre-Training (CPT)
Dataset	VietAI/vi_pubmed (92k English abstracts)
Tokens trained on	~23.6 million
Block size	256 tokens
Training objective	Causal Language Modeling (CLM)
Optimizer	AdamW 8-bit (bitsandbytes)
Learning rate	2e-5 (cosine schedule)
Hardware	Kaggle Tesla T4 (15.6GB VRAM)
Training time	~3h 45m
Starting loss	2.581
Final loss	~2.48
Precision	fp32 master weights + AMP fp16

What is this model?

This is a base model — not an instruction-tuned or chat model. It is intended as a domain-adapted foundation for further fine-tuning on medical instruction datasets.

All 494M parameters were updated during training (no LoRA, no frozen layers). The model has been adapted toward biomedical vocabulary, PubMed abstract structure, and medical terminology through full-parameter CLM training.

Intended Use

Base model for downstream medical SFT
Research into biomedical domain adaptation
Starting point for medical reasoning models

Not Intended For

Direct conversational use (no instruction tuning)
Clinical decision making
Patient-facing applications

Downloads last month: 249

Safetensors

Model size

0.5B params

Tensor type

F16

Model tree for Rumiii/Qwen2.5-0.5B-Med-Pre-Trained-92k

Base model

Qwen/Qwen2.5-0.5B

Finetuned

(708)

this model