Instructions to use mkurman/llama-3.2-MEDIT-3B-o1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mkurman/llama-3.2-MEDIT-3B-o1 with Transformers:

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

pipe = pipeline("text-generation", model="mkurman/llama-3.2-MEDIT-3B-o1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mkurman/llama-3.2-MEDIT-3B-o1")
model = AutoModelForCausalLM.from_pretrained("mkurman/llama-3.2-MEDIT-3B-o1")
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]:]))

llama-cpp-python

How to use mkurman/llama-3.2-MEDIT-3B-o1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mkurman/llama-3.2-MEDIT-3B-o1",
	filename="llama-3.2-MedIT-3B-o1-GGUF.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use mkurman/llama-3.2-MEDIT-3B-o1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mkurman/llama-3.2-MEDIT-3B-o1
# Run inference directly in the terminal:
llama-cli -hf mkurman/llama-3.2-MEDIT-3B-o1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mkurman/llama-3.2-MEDIT-3B-o1
# Run inference directly in the terminal:
llama-cli -hf mkurman/llama-3.2-MEDIT-3B-o1

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf mkurman/llama-3.2-MEDIT-3B-o1
# Run inference directly in the terminal:
./llama-cli -hf mkurman/llama-3.2-MEDIT-3B-o1

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf mkurman/llama-3.2-MEDIT-3B-o1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mkurman/llama-3.2-MEDIT-3B-o1

Use Docker

docker model run hf.co/mkurman/llama-3.2-MEDIT-3B-o1

LM Studio
Jan

vLLM

How to use mkurman/llama-3.2-MEDIT-3B-o1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mkurman/llama-3.2-MEDIT-3B-o1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mkurman/llama-3.2-MEDIT-3B-o1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mkurman/llama-3.2-MEDIT-3B-o1

SGLang

How to use mkurman/llama-3.2-MEDIT-3B-o1 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 "mkurman/llama-3.2-MEDIT-3B-o1" \
    --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": "mkurman/llama-3.2-MEDIT-3B-o1",
		"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 "mkurman/llama-3.2-MEDIT-3B-o1" \
        --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": "mkurman/llama-3.2-MEDIT-3B-o1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use mkurman/llama-3.2-MEDIT-3B-o1 with Ollama:
```
ollama run hf.co/mkurman/llama-3.2-MEDIT-3B-o1
```

Unsloth Studio

How to use mkurman/llama-3.2-MEDIT-3B-o1 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 mkurman/llama-3.2-MEDIT-3B-o1 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 mkurman/llama-3.2-MEDIT-3B-o1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mkurman/llama-3.2-MEDIT-3B-o1 to start chatting

How to use mkurman/llama-3.2-MEDIT-3B-o1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mkurman/llama-3.2-MEDIT-3B-o1

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mkurman/llama-3.2-MEDIT-3B-o1"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mkurman/llama-3.2-MEDIT-3B-o1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mkurman/llama-3.2-MEDIT-3B-o1

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default mkurman/llama-3.2-MEDIT-3B-o1

Run Hermes

hermes

Docker Model Runner
How to use mkurman/llama-3.2-MEDIT-3B-o1 with Docker Model Runner:
```
docker model run hf.co/mkurman/llama-3.2-MEDIT-3B-o1
```

Lemonade

How to use mkurman/llama-3.2-MEDIT-3B-o1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mkurman/llama-3.2-MEDIT-3B-o1

Run and chat with the model

lemonade run user.llama-3.2-MEDIT-3B-o1-{{QUANT_TAG}}

List all available models

lemonade list

Model Card: mkurman/llama-3.2-MEDIT-3B-o1

This model is a variant of o1-like reasoning that has been fine-tuned on MedIT Solutions Llama 3.2 3B Instruct (a variant of Meta LLama 3.2 3B Instruct). The model introduces specific tags (<Thought> and <Output>) for chain-of-thought style text generation, with a focus on instruct-style reasoning tasks. This model was fine-tuned for exact matching rather than generating a diverse distribution. Therefore, I recommend testing it with do_sample=False or setting temperature=0.0 for deterministic outputs.

Model Details

Model name: mkurman/llama-3.2-MEDIT-3B-o1
Type: Small Language Model (SLM)
Base model: MedIT Solutions Llama 3.2 3B Instruct (derived from Meta Llama 3.2 3B Instruct)
Architecture: 3 billion parameters
License: llama3.2

Intended Use Cases:

General question answering
Instruction-based generation
Reasoning and chain-of-thought exploration

Not Recommended For:

Sensitive, real-world medical diagnosis without expert verification
Highly domain-specific or regulated fields outside the model’s training scope

Usage

Important Notes on Usage

Stop strings:
Because the model uses <Thought> and <Output> tags to separate internal reasoning from the final answer, you must supply </Output> as a stop sequence (or multiple stop sequences, if your framework allows) to avoid the model generating infinitely.
Preventing <|python_tag|> bug:
Sometimes the model starts with <|python_tag|> instead of the intended <Thought>. As a workaround, add "<Thought>\n\n" to the end of your generation prompt (in your chat template) to ensure it starts correctly.
Libraries/Tools:
- Ollama and LM Studio: Via GGUF file.
- Jupyter Notebook (or similar): Using the Transformers library.

In Ollama or LM Studio

If you are loading the GGUF file, follow the instructions provided by Ollama or LM Studio. Typically, it involves placing the model file in the appropriate directory and selecting it within the interface.

Example (in Ollama CLI):
ollama run hf.co/mkurman/llama-3.2-MEDIT-3B-o1

You can then issue prompts. Make sure to set stop sequences to </Output> (and possibly </Thought> if your environment supports multiple stops).

In a Jupyter Notebook or Python Script (Transformers)

from transformers import AutoTokenizer, AutoModelForCausalLM

# 1. Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("mkurman/llama-3.2-MEDIT-3B-o1")
model = AutoModelForCausalLM.from_pretrained("mkurman/llama-3.2-MEDIT-3B-o1")

# 2. Define and encode your prompt
#   Add '<Thought>\n\n' at the end if you want to ensure 
#   the model uses the correct reasoning tag.
prompt = [{'role': 'user', 'content': 'Write a short instagram post about hypertension in children. Finish with 3 hashtags'}]
input_ids = tokenizer(tokenizer.apply_chat_template(prompt, tokenize=False, add_generation_prompt=True) + '<Thought>\n\n', return_tensors='pt')

# 3. Generate response with stop sequences (if your generation method supports them)
#    If your method doesn't support stop sequences directly, 
#    you can manually slice the model's output at '</Output>'.
output = model.generate(
    input_ids=input_ids,
    max_new_tokens=256,
    do_sample=False, #or True with temperature 0.0
    temperature=0.0,
    # Some generation methods or libraries allow specifying stop sequences. 
    # This is an example if your environment supports it.
    # stop=["</Output>"]
)

# 4. Decode the output
decoded_output = tokenizer.decode(output[0], skip_special_tokens=True)
print(decoded_output)

Note: If your generation library does not allow direct stop sequences, you can manually parse and remove any tokens that appear after </Output>.

Example Prompt/Response

Prompt:

<Talk about the impact of regular exercise on cardiovascular health>
<Thought>

(Remember to add <Thought>\n\n at the end if you see the <|python_tag|> bug.)

Model’s Reasoning (<Thought> block):

Exercise improves heart function by ...

Model’s Final Answer (<Output> block):

Regular exercise has been shown to ...
</Output>

You would display the <Output> portion as the final user-facing answer.

Limitations and Bias

Hallucination: The model may generate plausible-sounding but incorrect or nonsensical answers.
Medical Information: Never rely on this model as a source of truth! this model is not a certified medical professional. Always verify with qualified experts before acting on medical advice.
Biases: The model’s outputs may reflect biases present in the training data. Users should evaluate content for fairness and accuracy.

License and Citation

Please refer to the base model’s Llama 3.2 Community License Agreement and any additional licenses from MedIT Solutions. If you use this model in your work, please cite:

@misc{mkurman2025llama3medit3bo1,
  title={{mkurman/llama-3.2-MEDIT-3B-o1}: A fine-tuned Llama 3.2 3B Instruct model for reasoning tasks},
  author={Kurman, Mariusz},
  year={2025},
  howpublished={\url{https://huggingface.co/mkurman/llama-3.2-MEDIT-3B-o1}}
}

Contact

For questions, comments, or issues related to mkurman/llama-3.2-MEDIT-3B-o1, please open an issue on the model repository or contact mkurman.

Downloads last month: 107

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for mkurman/llama-3.2-MEDIT-3B-o1

Base model

meta-llama/Llama-3.2-3B-Instruct

Quantized

(459)

this model

Quantizations

2 models

mkurman
/

llama-3.2-MEDIT-3B-o1