Instructions to use Rumiii/LlamaMed-3.1-8B-Reasoner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rumiii/LlamaMed-3.1-8B-Reasoner with Transformers:

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

pipe = pipeline("text-generation", model="Rumiii/LlamaMed-3.1-8B-Reasoner")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Rumiii/LlamaMed-3.1-8B-Reasoner")
model = AutoModelForCausalLM.from_pretrained("Rumiii/LlamaMed-3.1-8B-Reasoner", 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

llama.cpp

How to use Rumiii/LlamaMed-3.1-8B-Reasoner with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0
# Run inference directly in the terminal:
llama cli -hf Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0
# Run inference directly in the terminal:
llama cli -hf Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0

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 Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0

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 Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0

Use Docker

docker model run hf.co/Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0

LM Studio
Jan

vLLM

How to use Rumiii/LlamaMed-3.1-8B-Reasoner with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rumiii/LlamaMed-3.1-8B-Reasoner"
# 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/LlamaMed-3.1-8B-Reasoner",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0

SGLang

How to use Rumiii/LlamaMed-3.1-8B-Reasoner 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/LlamaMed-3.1-8B-Reasoner" \
    --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/LlamaMed-3.1-8B-Reasoner",
		"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/LlamaMed-3.1-8B-Reasoner" \
        --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/LlamaMed-3.1-8B-Reasoner",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Rumiii/LlamaMed-3.1-8B-Reasoner with Ollama:
```
ollama run hf.co/Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0
```
Unsloth Desktop

How to use Rumiii/LlamaMed-3.1-8B-Reasoner with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Rumiii/LlamaMed-3.1-8B-Reasoner with Docker Model Runner:
```
docker model run hf.co/Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0
```

Lemonade

How to use Rumiii/LlamaMed-3.1-8B-Reasoner with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0

Run and chat with the model

lemonade run user.LlamaMed-3.1-8B-Reasoner-Q8_0

List all available models

lemonade list

Hermes Agent

How to use Rumiii/LlamaMed-3.1-8B-Reasoner with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0

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 Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Rumiii/LlamaMed-3.1-8B-Reasoner with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "Rumiii/LlamaMed-3.1-8B-Reasoner:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

LlamaMed-3.1-8B-Reasoner

LlamaMed-3.1-8B-Reasoner is a fine-tune of Llama-3.1-8B-Instruct trained on ReasonMed, a dataset of chain-of-thought medical reasoning over multiple-choice clinical questions. The model works through a question step by step — considering each answer option in turn — before giving a final answer, in the same structured reasoning style as its training data.

Model Details

Base model: unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
Dataset: lingshu-medical-mllm/ReasonMed — 10,000 samples used for training
Method: QLoRA (4-bit), rank 16, via Unsloth
License: Apache 2.0

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
import torch

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
)

tokenizer = AutoTokenizer.from_pretrained("Rumiii/LlamaMed-3.1-8B-Reasoner")
model = AutoModelForCausalLM.from_pretrained(
    "Rumiii/LlamaMed-3.1-8B-Reasoner",
    device_map={"": 0},
    quantization_config=bnb_config,
)

messages = [
    {"role": "user", "content": "A 45-year-old man presents with polyuria, polydipsia, and weight loss. Fasting blood glucose is 210 mg/dL. What is the most likely diagnosis?\nA. Type 1 Diabetes Mellitus\nB. Type 2 Diabetes Mellitus\nC. Diabetes Insipidus\nD. Cushing's Syndrome"},
]

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=1500, temperature=0.6, top_p=0.95)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

Training

Trained on a single Tesla T4 GPU using Unsloth for memory-efficient QLoRA fine-tuning, with periodic adapter checkpoints saved during training.

Intended Use

This model is a research checkpoint intended for exploring medical reasoning fine-tunes. It is not validated for clinical use and should not be used to inform real medical decisions.

Downloads last month: 443

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Rumiii/LlamaMed-3.1-8B-Reasoner

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Quantized

unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit

Quantized

(365)

this model

Quantizations

2 models

Rumiii
/

LlamaMed-3.1-8B-Reasoner

LlamaMed-3.1-8B-Reasoner

Model Details

Usage

Training

Intended Use

Model tree for Rumiii/LlamaMed-3.1-8B-Reasoner

Dataset used to train Rumiii/LlamaMed-3.1-8B-Reasoner