Instructions to use admin-lima/qwen05b-saude-amazonia-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use admin-lima/qwen05b-saude-amazonia-gguf with Transformers:

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

pipe = pipeline("text-generation", model="admin-lima/qwen05b-saude-amazonia-gguf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("admin-lima/qwen05b-saude-amazonia-gguf", dtype="auto")

llama-cpp-python

How to use admin-lima/qwen05b-saude-amazonia-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="admin-lima/qwen05b-saude-amazonia-gguf",
	filename="qwen05b-saude-amazonia.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 admin-lima/qwen05b-saude-amazonia-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 admin-lima/qwen05b-saude-amazonia-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf admin-lima/qwen05b-saude-amazonia-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 admin-lima/qwen05b-saude-amazonia-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf admin-lima/qwen05b-saude-amazonia-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 admin-lima/qwen05b-saude-amazonia-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf admin-lima/qwen05b-saude-amazonia-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 admin-lima/qwen05b-saude-amazonia-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf admin-lima/qwen05b-saude-amazonia-gguf:Q4_K_M

Use Docker

docker model run hf.co/admin-lima/qwen05b-saude-amazonia-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use admin-lima/qwen05b-saude-amazonia-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "admin-lima/qwen05b-saude-amazonia-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": "admin-lima/qwen05b-saude-amazonia-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/admin-lima/qwen05b-saude-amazonia-gguf:Q4_K_M

SGLang

How to use admin-lima/qwen05b-saude-amazonia-gguf 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 "admin-lima/qwen05b-saude-amazonia-gguf" \
    --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": "admin-lima/qwen05b-saude-amazonia-gguf",
		"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 "admin-lima/qwen05b-saude-amazonia-gguf" \
        --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": "admin-lima/qwen05b-saude-amazonia-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use admin-lima/qwen05b-saude-amazonia-gguf with Ollama:
```
ollama run hf.co/admin-lima/qwen05b-saude-amazonia-gguf:Q4_K_M
```

Unsloth Studio

How to use admin-lima/qwen05b-saude-amazonia-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 admin-lima/qwen05b-saude-amazonia-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 admin-lima/qwen05b-saude-amazonia-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for admin-lima/qwen05b-saude-amazonia-gguf to start chatting

How to use admin-lima/qwen05b-saude-amazonia-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf admin-lima/qwen05b-saude-amazonia-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": "admin-lima/qwen05b-saude-amazonia-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use admin-lima/qwen05b-saude-amazonia-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 admin-lima/qwen05b-saude-amazonia-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 admin-lima/qwen05b-saude-amazonia-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use admin-lima/qwen05b-saude-amazonia-gguf with Docker Model Runner:
```
docker model run hf.co/admin-lima/qwen05b-saude-amazonia-gguf:Q4_K_M
```

Lemonade

How to use admin-lima/qwen05b-saude-amazonia-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull admin-lima/qwen05b-saude-amazonia-gguf:Q4_K_M

Run and chat with the model

lemonade run user.qwen05b-saude-amazonia-gguf-Q4_K_M

List all available models

lemonade list

Qwen2.5-0.5B — GGUF Q4_K_M · Saúde Coletiva Amazônia (sLLM offline)

Potencialidades dos Pequenos Modelos de Linguagem (sLLMs) como Assistentes Offline na Saúde Coletiva: Curadoria Informacional contra Assimetrias na Amazônia Isolada. (ENANCIB 2026 / GT 8 — Ciência da Informação)

📋 Resumo

sLLM (small LLM) em português para apoiar profissionais de saúde em comunidades isoladas da Amazônia, operando 100% offline com grounding (RAG) em um corpus oficial do SUS. A tese: a curadoria da informação — mais que o porte do modelo — determina a confiabilidade. Treinado em 1.000 diálogos clínicos sintéticos curados (pilares P3 Saúde Indígena e P5 Atenção Primária).

🧩 Este artefato — GGUF Q4_K_M (deploy smartphone)

GGUF quantizado Q4_K_M (~4 bits/peso, ~0.4 GB) derivado do fundido fp16 (admin-lima/qwen05b-saude-amazonia-merged) via llama.cpp. Voltado para inferência offline.

Como rodar (100% offline):

Desktop/servidor: llama.cpp (llama-cli -m <arquivo>.gguf) ou llama-cpp-python.
Smartphone: apps Chatterbox, LM Studio, Maid ou PocketPal — abra o .gguf.

./llama-cli -m qwen05b-saude-amazonia-gguf.Q4_K_M.gguf \
  --chat-template chatml  # Phi-3.5 / Qwen2.5: template system/user/assistant

Chat template: system / user / assistant (mesmo do Qwen2.5-0.5B).

📊 Resultados (conjunto hold-out, n=33)

Modelo	Porte	TRR	FRR	F1	Halluc.
Phi-3.5-mini (QLoRA)	3.8B	0.929	0.266	0.813	0.03
Qwen2.5-0.5B (LoRA)	500M	0.857	0.053	0.889	0.03

TRR — relevância da resposta · FRR — taxa de recusa · F1 — F1 de recusa (recusar o que está fora do escopo) · Halluc. — taxa de alucinação.

🔗 Artefatos relacionados

Artefato	Repositório
Dataset (SFT)	`admin-lima/sllm-amazonia-saude-sft`
Phi-3.5-mini — adapter	`admin-lima/phi35-saude-amazonia-lora`
Phi-3.5-mini — fundido fp16	`admin-lima/phi35-saude-amazonia-merged`
Phi-3.5-mini — GGUF Q4_K_M	`admin-lima/phi35-saude-amazonia-gguf`
Qwen2.5-0.5B — adapter	`admin-lima/qwen05b-saude-amazonia-lora`
Qwen2.5-0.5B — fundido fp16	`admin-lima/qwen05b-saude-amazonia-merged`
✅ Qwen2.5-0.5B — GGUF Q4_K_M	`admin-lima/qwen05b-saude-amazonia-gguf`

🛡️ Limitações e uso responsável

Não é dispositivo médico nem substitui avaliação profissional. Use como apoio à decisão.
Deve operar acoplado ao corpus RAG (pilares oficiais do SUS) para grounding.
Treinado em dados sintéticos em PT-BR com foco regional (Amazônia); pode ter lacunas.
Alucinação ≈ 3 % (não nula) — sempre verifique informações críticas.
Mantenha o modelo offline em ambientes sem conectividade; respeite a privacidade dos dados locais.

📜 Licença

Derivado de Qwen/Qwen2.5-0.5B-Instruct. Distribuído sob a licença do modelo base (apache-2.0). Dataset sintético próprio.

📚 Citação (preliminar)

@misc{sllm_amazonia_saude_2026,
  title  = {sLLMs Offline de Saúde Coletiva na Amazônia},
  author = {admin-lima},
  year   = {2026},
  note   = {ENANCIB 2026 / GT 8 — pré-print}
}

Downloads last month: 41

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for admin-lima/qwen05b-saude-amazonia-gguf

Base model

Qwen/Qwen2.5-0.5B

Finetuned

Qwen/Qwen2.5-0.5B-Instruct

Quantized

(230)

this model