Instructions to use Raras-AI/araras-gemma4-e4b-v4-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use Raras-AI/araras-gemma4-e4b-v4-gguf with PEFT:
```
Task type is invalid.
```

How to use Raras-AI/araras-gemma4-e4b-v4-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Raras-AI/araras-gemma4-e4b-v4-gguf",
	filename="araras-gemma4-e4b-v4-Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Raras-AI/araras-gemma4-e4b-v4-gguf 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 Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Raras-AI/araras-gemma4-e4b-v4-gguf: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 Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Raras-AI/araras-gemma4-e4b-v4-gguf: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 Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M

Use Docker

docker model run hf.co/Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use Raras-AI/araras-gemma4-e4b-v4-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Raras-AI/araras-gemma4-e4b-v4-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Raras-AI/araras-gemma4-e4b-v4-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M

Ollama
How to use Raras-AI/araras-gemma4-e4b-v4-gguf with Ollama:
```
ollama run hf.co/Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M
```

Unsloth Studio

How to use Raras-AI/araras-gemma4-e4b-v4-gguf 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 Raras-AI/araras-gemma4-e4b-v4-gguf 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 Raras-AI/araras-gemma4-e4b-v4-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Raras-AI/araras-gemma4-e4b-v4-gguf to start chatting

How to use Raras-AI/araras-gemma4-e4b-v4-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Raras-AI/araras-gemma4-e4b-v4-gguf: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": "Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Raras-AI/araras-gemma4-e4b-v4-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Raras-AI/araras-gemma4-e4b-v4-gguf: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 Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Raras-AI/araras-gemma4-e4b-v4-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M

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 "Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M" \
  --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"

Docker Model Runner
How to use Raras-AI/araras-gemma4-e4b-v4-gguf with Docker Model Runner:
```
docker model run hf.co/Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M
```

Lemonade

How to use Raras-AI/araras-gemma4-e4b-v4-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Raras-AI/araras-gemma4-e4b-v4-gguf:Q4_K_M

Run and chat with the model

lemonade run user.araras-gemma4-e4b-v4-gguf-Q4_K_M

List all available models

lemonade list

timmers commited on May 18

Commit

457e16a

verified ·

1 Parent(s): 74ddcd8

card: hybrid resolver (substring + BioLORD 0.78) + production-grade pipeline details

Browse files

Files changed (1) hide show

README.md +12 -6

README.md CHANGED Viewed

@@ -125,18 +125,24 @@ Positioned as **Software as a Medical Device (SaMD) — Clinical Decision Suppor
 ```
 PT-BR free text (laudo, prontuário, transcrição da consulta)
     ↓
-[1] araras-hpo-brasil — normaliza idioma clínico regional ("amarelão", "bebê molinho") → HPO codes
     ↓
-[2] araras-gemma4-e4b — recebe prompt + HPO codes → diferencial diagnóstico ranqueado
     ↓
-[3] Canonical ORPHA lookup — nome de doença → código ORPHA (corrige hallucination de tokens esparsos)
     ↓
-[4] PCDT overlay — 24 PCDTs do MS → fármaco CEAF + centro de referência
     ↓
-Output ao médico: Dx + evidência + conduta SUS + custo + centro mais próximo
 ```
-Total stack footprint: **5.5 GB**. Runs **offline** on iPhone, Android, laptop. Zero cloud.
 ---

 ```
 PT-BR free text (laudo, prontuário, transcrição da consulta)
     ↓
+[1] 🧬 araras-hpo-brasil (BioLORD-2023 fine-tune for PT-BR)
+       Normaliza idioma clínico regional → HPO codes
+       "amarelão" → HP:0000952 · "bebê molinho" → HP:0001252
     ↓
+[2] 🧠 araras-gemma4-e4b Q4_K_M (this model, 5.3 GB, llama.cpp)
+       Gera TOP-5 diferenciais ranqueados em PT-BR
     ↓
+[3] ✅ Hybrid canonical ORPHA resolver (production technique, e.g. MedCAT/scispaCy)
+       Tier 1: strict substring match on 10,468-keyword PT-BR dict (~30ms)
+       Tier 2: BioLORD semantic fallback @ cosine ≥ 0.78 (~50ms, only if Tier 1 fails)
+       Returns None (honest abstention) if neither tier matches confidently
     ↓
+[4] 📋 PCDT overlay — 24 PCDTs do MS estruturados → CEAF + centro de referência
     ↓
+Output: structured clinical decision support — differentials + PCDT + SUS conduta + centro
 ```
+Total stack footprint: **5.5 GB**. Runs **offline** on iPhone, Android, laptop. Zero cloud. Zero LGPD risk.
 ---