Instructions to use Davis426/COMP8420-Healthcare-LLM-Assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use Davis426/COMP8420-Healthcare-LLM-Assistant with PEFT:
```
Task type is invalid.
```

How to use Davis426/COMP8420-Healthcare-LLM-Assistant with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Davis426/COMP8420-Healthcare-LLM-Assistant",
	filename="llama32/llama32-medqa-gguf/model.Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Davis426/COMP8420-Healthcare-LLM-Assistant with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M

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 Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M

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 Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M

Use Docker

docker model run hf.co/Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M

LM Studio
Jan

vLLM

How to use Davis426/COMP8420-Healthcare-LLM-Assistant with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Davis426/COMP8420-Healthcare-LLM-Assistant"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Davis426/COMP8420-Healthcare-LLM-Assistant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M

Ollama
How to use Davis426/COMP8420-Healthcare-LLM-Assistant with Ollama:
```
ollama run hf.co/Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M
```

Unsloth Studio new

How to use Davis426/COMP8420-Healthcare-LLM-Assistant 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 Davis426/COMP8420-Healthcare-LLM-Assistant 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 Davis426/COMP8420-Healthcare-LLM-Assistant to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Davis426/COMP8420-Healthcare-LLM-Assistant to start chatting

Pi new

How to use Davis426/COMP8420-Healthcare-LLM-Assistant with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M

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": "Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Davis426/COMP8420-Healthcare-LLM-Assistant with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M

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 Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Davis426/COMP8420-Healthcare-LLM-Assistant with Docker Model Runner:
```
docker model run hf.co/Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M
```

Lemonade

How to use Davis426/COMP8420-Healthcare-LLM-Assistant with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Davis426/COMP8420-Healthcare-LLM-Assistant:Q4_K_M

Run and chat with the model

lemonade run user.COMP8420-Healthcare-LLM-Assistant-Q4_K_M

List all available models

lemonade list

Davis426 commited on about 14 hours ago

Commit

7b86930

verified ·

1 Parent(s): 2ec559e

Update combined model card

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -22,7 +22,7 @@ tags:
   - gguf
 ---
-# Healthcare LLM Assistant — QLoRA fine-tunes
 Two parallel QLoRA fine-tunes of small instruct models on the same 9,000-pair mix of public biomedical Q&A, served side-by-side in the parent project's Streamlit UI for a 3-way bake-off against GPT-5.5.
@@ -127,7 +127,7 @@ Detailed numbers and charts live in the parent repo:
 Replace `<variant>` with `qwen` or `llama32` in the examples below.
-### Option 1 — Ollama (recommended for local serving)
 ```bash
 # Fetch one variant's GGUF + Modelfile
@@ -147,7 +147,7 @@ For the Llama variant, swap every `qwen` for `llama32` (paths) and the Ollama ta
 You can register both side-by-side; one `ollama serve` daemon handles both tags concurrently (`OLLAMA_MAX_LOADED_MODELS` defaults to 3).
-### Option 2 — transformers + peft (Python)
 ```python
 from peft import PeftModel
@@ -171,7 +171,7 @@ out = model.generate(inputs, max_new_tokens=256)
 print(tokenizer.decode(out[0][inputs.shape[1]:], skip_special_tokens=True))
 ```
-### Option 3 — llama.cpp directly
 ```bash
 huggingface-cli download Davis426/COMP8420-Healthcare-LLM-Assistant \

   - gguf
 ---
+# Healthcare LLM Assistant - QLoRA fine-tunes
 Two parallel QLoRA fine-tunes of small instruct models on the same 9,000-pair mix of public biomedical Q&A, served side-by-side in the parent project's Streamlit UI for a 3-way bake-off against GPT-5.5.
 Replace `<variant>` with `qwen` or `llama32` in the examples below.
+### Option 1: Ollama (recommended for local serving)
 ```bash
 # Fetch one variant's GGUF + Modelfile
 You can register both side-by-side; one `ollama serve` daemon handles both tags concurrently (`OLLAMA_MAX_LOADED_MODELS` defaults to 3).
+### Option 2: transformers + peft (Python)
 ```python
 from peft import PeftModel
 print(tokenizer.decode(out[0][inputs.shape[1]:], skip_special_tokens=True))
 ```
+### Option 3: llama.cpp directly
 ```bash
 huggingface-cli download Davis426/COMP8420-Healthcare-LLM-Assistant \