Instructions to use dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2 with Transformers:

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

pipe = pipeline("text-generation", model="dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2")
model = AutoModelForCausalLM.from_pretrained("dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2")
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 dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2

SGLang

How to use dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2 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 "dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2" \
    --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": "dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2",
		"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 "dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2" \
        --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": "dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2 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 dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2 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 dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2",
    max_seq_length=2048,
)

Docker Model Runner
How to use dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2 with Docker Model Runner:
```
docker model run hf.co/dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen2.5 7B trained to think and reason like Deepseek R1, specifically on Diagnostic Medicine.

Use this to aid your differential diagnosis or ask questions or even just test it's reasoning.

Use the system prompt below for better results

Respond in the following format:
<reasoning>
...
</reasoning>
<answer>
...
</answer>

Uploaded model

Developed by: dumbequation
License: apache-2.0
Finetuned from model : Qwen/Qwen2.5-7B-Instruct-1M

Downloads last month: 9

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct-1M

Finetuned

(50)

this model

Quantizations

1 model

Collection including dumbequation/Qwen2.5-7B-GRPO-1M-Context-Medical-Reasoning-f16-v2

Medical LLMs

Collection

My experiments to push AI in Medicine, not to replace doctors but to empower them • 4 items • Updated May 1, 2025