Instructions to use Makrrr/qwen2.5-7B-reasonmed-finetune-extreme with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Makrrr/qwen2.5-7B-reasonmed-finetune-extreme with Transformers:

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

pipe = pipeline("text-generation", model="Makrrr/qwen2.5-7B-reasonmed-finetune-extreme")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Makrrr/qwen2.5-7B-reasonmed-finetune-extreme")
model = AutoModelForCausalLM.from_pretrained("Makrrr/qwen2.5-7B-reasonmed-finetune-extreme")
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

vLLM

How to use Makrrr/qwen2.5-7B-reasonmed-finetune-extreme with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Makrrr/qwen2.5-7B-reasonmed-finetune-extreme"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Makrrr/qwen2.5-7B-reasonmed-finetune-extreme",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Makrrr/qwen2.5-7B-reasonmed-finetune-extreme

SGLang

How to use Makrrr/qwen2.5-7B-reasonmed-finetune-extreme 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 "Makrrr/qwen2.5-7B-reasonmed-finetune-extreme" \
    --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": "Makrrr/qwen2.5-7B-reasonmed-finetune-extreme",
		"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 "Makrrr/qwen2.5-7B-reasonmed-finetune-extreme" \
        --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": "Makrrr/qwen2.5-7B-reasonmed-finetune-extreme",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Makrrr/qwen2.5-7B-reasonmed-finetune-extreme with Docker Model Runner:
```
docker model run hf.co/Makrrr/qwen2.5-7B-reasonmed-finetune-extreme
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

reason_med_final

This model is a fine-tuned version of ../models/Qwen2.5-7B-Instruct on the reason_med_full dataset. It achieves the following results on the evaluation set:

Loss: 0.4633

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: 2e-05
train_batch_size: 8
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 128
total_eval_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.514	0.3844	1000	0.4880
0.4958	0.5766	1500	0.4770
0.4856	0.7688	2000	0.4683
0.4809	0.9610	2500	0.4610
0.4048	1.1534	3000	0.4647
0.4073	1.3456	3500	0.4587
0.3971	1.5378	4000	0.4527
0.3985	1.7300	4500	0.4479
0.402	1.9222	5000	0.4420
0.3008	2.1142	5500	0.4667
0.2989	2.3064	6000	0.4659
0.2955	2.4986	6500	0.4652
0.2926	2.6908	7000	0.4641
0.2982	2.8830	7500	0.4634

Framework versions

Transformers 4.52.4
Pytorch 2.7.1+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Downloads last month: 4

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Makrrr/qwen2.5-7B-reasonmed-finetune-extreme

Unable to build the model tree, the base model loops to the model itself. Learn more.