Instructions to use TanitAI/Tanit-MedReason-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TanitAI/Tanit-MedReason-8B with Transformers:

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

pipe = pipeline("text-generation", model="TanitAI/Tanit-MedReason-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TanitAI/Tanit-MedReason-8B")
model = AutoModelForCausalLM.from_pretrained("TanitAI/Tanit-MedReason-8B")
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 TanitAI/Tanit-MedReason-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TanitAI/Tanit-MedReason-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TanitAI/Tanit-MedReason-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TanitAI/Tanit-MedReason-8B

SGLang

How to use TanitAI/Tanit-MedReason-8B 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 "TanitAI/Tanit-MedReason-8B" \
    --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": "TanitAI/Tanit-MedReason-8B",
		"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 "TanitAI/Tanit-MedReason-8B" \
        --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": "TanitAI/Tanit-MedReason-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TanitAI/Tanit-MedReason-8B with Docker Model Runner:
```
docker model run hf.co/TanitAI/Tanit-MedReason-8B
```

Tanit-MedReason-8B

File size: 931 Bytes

0a51fc3

{
  "total_samples": 35526,
  "config": {
    "model_path": "./outputs/phase1_phase3a_dpo_alignment",
    "output_dir": "./outputs/phase4_medreason_cot",
    "max_seq_length": 8192,
    "min_reasoning_length": 500,
    "max_reasoning_length": 4500,
    "learning_rate": 5e-07,
    "num_train_epochs": 2,
    "per_device_train_batch_size": 2,
    "gradient_accumulation_steps": 8,
    "warmup_ratio": 0.05,
    "lr_scheduler_type": "cosine",
    "weight_decay": 0.01,
    "max_grad_norm": 0.5,
    "optim": "adamw_torch",
    "adam_beta1": 0.9,
    "adam_beta2": 0.999,
    "adam_epsilon": 1e-08,
    "use_curriculum": true,
    "use_neftune": true,
    "neftune_noise_alpha": 5.0,
    "save_steps": 200,
    "save_total_limit": 3,
    "logging_steps": 10,
    "eval_steps": 500,
    "seed": 42,
    "bf16": true,
    "gradient_checkpointing": true,
    "dataloader_num_workers": 4
  },
  "timestamp": "2026-01-26T18:01:49.960457"
}