Skip to page content
SAVRN
Search Plan a project

Open-weight model · Text generation

qwen2.5-0.5b-bragasaude

by Yuri Fernandes fernandes-yuri/qwen2.5-0.5b-bragasaude

qwen2.5-0.5b-bragasaude is an open-weight model for text generation from Yuri Fernandes, released under Apache License 2.0. Its published files total 397.8 MB.

Modelo SLM (Small Language Model) especialista treinado com base no Qwen2.5-0.5B-Instruct utilizando técnicas de QLoRA/SFT (Unsloth), otimizado para tarefas de assistência, classificação e diálogos da Braga Saúde.

Parameters—
Context—
Weights397.8 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—

Model Card

By Yuri Fernandes, published under apache-2.0, revision 77a0d9d85171.

Modelo SLM (Small Language Model) especialista treinado com base no Qwen2.5-0.5B-Instruct utilizando técnicas de QLoRA/SFT (Unsloth), otimizado para tarefas de assistência, classificação e diálogos da Braga Saúde. - Quantização: Q4KM (4-bit Medium) Você pode rodar diretamente com o Modelfile presente neste repositório: - Método: SFT com QLoRA 4-bit (r=16, loraalpha=32)

Read Yuri Fernandes's full model card

Qwen2.5-0.5B Braga Saúde (GGUF - Q4_K_M)

Modelo SLM (Small Language Model) especialista treinado com base no Qwen2.5-0.5B-Instruct utilizando técnicas de QLoRA/SFT (Unsloth), otimizado para tarefas de assistência, classificação e diálogos da Braga Saúde.

  • Tamanho: ~397 MB
  • Quantização: Q4_K_M (4-bit Medium)
  • Formato: GGUF (compatível com llama.cpp, Ollama, LM Studio, vLLM e Hugging Face Spaces)
  • Contexto: 2048 tokens

Como Usar

1. Via Ollama

Você pode rodar diretamente com o Modelfile presente neste repositório:

# Clone ou baixe o arquivo GGUF e o Modelfile, depois execute:
ollama create braga-qwen05 -f Modelfile
ollama run braga-qwen05

2. Via Python (llama-cpp-python)

from llama_cpp import Llama

# Carrega o modelo baixando automaticamente do Hugging Face
llm = Llama.from_pretrained(
    repo_id="yuriojogador/qwen2.5-0.5b-bragasaude",
    filename="Qwen2.5-0.5B-Instruct.Q4_K_M.gguf",
    n_ctx=2048,
    verbose=False
)

# Exemplo de inferência
messages = [
    {"role": "system", "content": "Você é o assistente virtual da Braga Saúde, prestativo e empático."},
    {"role": "user", "content": "Olá, como funciona o acompanhamento de saúde?"}
]

response = llm.create_chat_completion(
    messages=messages,
    max_tokens=256,
    temperature=0.7
)

print(response["choices"][0]["message"]["content"])

3. Via llama.cpp (CLI)

llama-cli -m Qwen2.5-0.5B-Instruct.Q4_K_M.gguf -p "Você é o assistente da Braga Saúde." -cnv

Detalhes do Treinamento

  • Base Model: unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit
  • Método: SFT com QLoRA 4-bit (r=16, lora_alpha=32)
  • Frameworks: Unsloth, TRL, PyTorch, Transformers

Identity and Version

Repository
fernandes-yuri/qwen2.5-0.5b-bragasaude
Publisher
Yuri Fernandes
Task
Text generation
Modality
Text
Library
gguf
Parameters
Not stated by the source
Languages
pt
Revision
77a0d9d8517121589613eca5554d6fb41cc95930
First published
2026-09-30
Last updated
2026-10-01

Files and Weights

4 files, 397.8 MB in total. The weights are 1 file totalling 397.8 MB in gguf.

Weights1 file · 397.8 MB
Documentation1 file · 2.0 KB
Other1 file · 1.7 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
Qwen2.5-0.5B-Instruct.Q4_K_M.ggufWeights397.8 MB 407a240740de
README.mdDocumentation2.0 KB —
ModelfileOther1.7 KB —
.gitattributesRepository1.6 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
397.8 MB
Download from Yuri Fernandes

Released by Yuri Fernandes through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published397.8 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About qwen2.5-0.5b-bragasaude

Can I use qwen2.5-0.5b-bragasaude commercially?

Yes. qwen2.5-0.5b-bragasaude is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.

Similar Models

Model · Text generation

opt-125m

AI at Meta

OPT was first introduced in Open Pre-trained Transformer Language Models and first released in metaseq's repository on May 3rd 2022 by Meta AI. Disclaimer: The team releasing OPT wrote an official model card, which is available in Appendix D of the paper. Content from this model card has been written by the Hugging Face team. To quote the first two paragraphs of the official paper OPT was predominantly pretrained with English text, but a small amount of non-English data is still present within the training corpus via CommonCrawl. The model was pretrained using a causal language modeling (CLM) objective. OPT belongs to the same family of decoder-only models like GPT-3. As such, it was…

Open weights other 2,048 tokens transformers

Model · Text generation

Ornith-1.5-9B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

Model · Text generation

Ternary-Bonsai-2-27B-gguf

Prism ML

Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) - \~5.9 GB language model (down from \~54 GB FP16) — full 27B-class reasoning on a standard laptop or a single GPU - 98.2% of FP16 intelligence retained: 84.78 average across 14 thinking-mode benchmarks — far above the conventional IQ2XXS build (72.59) at about 82% of its footprint, and within 0.4 points of UD-Q4KXL at three times the footprint - Retains thinking, reasoning, and agentic behavior deep in the sub-4-bit regime, where conventional low-bit representations collapse: math within half a point of full precision (96.57), coding level with the baseline (89.42), agentic tool calling at 74.92…

Open weights apache-2.0 llama.cpp

Model · Text generation

Ornith-1.5-35B-A3B-GGUF

Ornith

Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For…

Open weights mit transformers

Uncensored Qwen3.8-27B, published as GGUF quantizations with the multi token prediction (MTP) head retained and verified. Refusal behaviour has been substantially reduced, not eliminated. See Measured behaviour for the numbers. Capabilities, training data, and architecture are otherwise unchanged. - Refusal directions removed with Heretic, which co minimizes refusal count against KL divergence from the base model. No handwritten refusal removal code, no finetuning, no additional training data. - Abliteration runs at bf16 (no 4 bit quantization). the resulting LoRA is merged into the bf16 base, so the published weights are not a quantized round trip. - mtp. tensors are copied verbatim from…

Open weights apache-2.0 llama.cpp

Model · Text generation

Ornith-1.0-9B-GGUF

Ornith

Aloha! Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding. This model card documents Ornith-1.0-9B, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment. Ornith-1.0-9B is a dense ~9B model (≈19 GB in bf16), so it serves comfortably on a single 80GB GPU. The recipes below stand up an OpenAI-compatible server; add --tensor-parallel-size / --tp if you want to shard across more GPUs. For a quick local test (or to script offline generation), load the model directly with Transformers. Make sure you have a recent release installed — see the Transformers installation guide; Ornith-1.0-9B requires…

Open weights mit transformers