Instructions to use prefeitura-rio/Rio-3.5-Open-397B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prefeitura-rio/Rio-3.5-Open-397B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="prefeitura-rio/Rio-3.5-Open-397B") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("prefeitura-rio/Rio-3.5-Open-397B") model = AutoModelForMultimodalLM.from_pretrained("prefeitura-rio/Rio-3.5-Open-397B", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use prefeitura-rio/Rio-3.5-Open-397B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "prefeitura-rio/Rio-3.5-Open-397B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "prefeitura-rio/Rio-3.5-Open-397B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/prefeitura-rio/Rio-3.5-Open-397B
- SGLang
How to use prefeitura-rio/Rio-3.5-Open-397B 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 "prefeitura-rio/Rio-3.5-Open-397B" \ --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": "prefeitura-rio/Rio-3.5-Open-397B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "prefeitura-rio/Rio-3.5-Open-397B" \ --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": "prefeitura-rio/Rio-3.5-Open-397B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use prefeitura-rio/Rio-3.5-Open-397B with Docker Model Runner:
docker model run hf.co/prefeitura-rio/Rio-3.5-Open-397B
Distilled Model
🚀 1
#28 opened 2 months ago
by
brandonmusic
TUTORIAL
17
#27 opened 3 months ago
by
godnett
gastaram 500 mil pra financiar essa mentira hahahahahhaa
4
#26 opened 3 months ago
by
jsob7
Despite the way the project was released, this is a good model.
👍 5
9
#25 opened 3 months ago
by
tarruda
"É MUITO MALANDRO PRA POUCO OTÁRIO"... ENTÃO TENTARAM FAZER O PLANETA INTEIRO DE OTÁRIO!
😎👍 4
24
#24 opened 3 months ago
by
Nerdsking
Estou à espera do "final distilled model"
11
#23 opened 3 months ago
by
danielgweb
plágio + dinheiro publico = this is brazil
👍😎 8
4
#22 opened 3 months ago
by
lucasdeboa
Que venha muita atualização e crescimento constante deste modelo e iniciativa, parabéns!
4
#21 opened 3 months ago
by
Branux
BRAZILIAN MIKUUUU 🇧🇷🇧🇷🗣️🗣️🗣️🗣️🔥🔥🔥
🤗 8
3
#20 opened 3 months ago
by
evewashere
If you do not upload the post-training model you mentioned within 2 to 3 days, then it is effectively a lie.
🤗👍 18
7
#19 opened 3 months ago
by
cocorang
Rio-3.5-Open-397B ≈ 0.6 x Nex-N2_pro + 0.4 x Qwen
🤗👍 16
15
#18 opened 3 months ago
by
spanspek
MTP Support?
2
#17 opened 3 months ago
by
alexanderacuna
Merging method
👍 2
#16 opened 3 months ago
by
erichartford
Why merge first?
👍 3
#15 opened 3 months ago
by
erichartford
Cópia descarada do Modelo Nex-N2_pro
👀🔥 7
3
#14 opened 3 months ago
by
jkepler81
Que Coisa Maravilhosa/Conta comigo no próxima!!
2
#13 opened 3 months ago
by
Guilherme34
mxfp4 QAT variant
#12 opened 3 months ago
by
lostmsu
Tarefas em Português
❤️ 1
1
#11 opened 3 months ago
by
burguela
what kinds of data did you use in post-training?
👍 1
3
#9 opened 3 months ago
by
michael234
Smaller variants
👍 1
6
#8 opened 3 months ago
by
nonetrix
Parabéns pelo que vocês construíram, definitivamente estão na vanguarda da tecnologia dos modelos transformes.
❤️ 3
6
#7 opened 3 months ago
by
rodrigoramosrs
Parabéns galera, como brasileiro fico feliz de ver esse modelo, acredito que é um avanço para todos nós
❤️ 4
10
#6 opened 3 months ago
by
mayk0
FP8 or even GPTQ?
#4 opened 3 months ago
by
ebfio
About the SwiReasoning (requirement?)
❤️ 5
8
#2 opened 3 months ago
by
abc-nix
Gguf
👍 5
5
#1 opened 3 months ago
by
cdani