Instructions to use SynastriaNetworks/U1-0817 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SynastriaNetworks/U1-0817 with Transformers:

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

pipe = pipeline("text-generation", model="SynastriaNetworks/U1-0817")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("SynastriaNetworks/U1-0817")
model = AutoModelForMultimodalLM.from_pretrained("SynastriaNetworks/U1-0817", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SynastriaNetworks/U1-0817 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SynastriaNetworks/U1-0817"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SynastriaNetworks/U1-0817",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SynastriaNetworks/U1-0817

SGLang

How to use SynastriaNetworks/U1-0817 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 "SynastriaNetworks/U1-0817" \
    --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": "SynastriaNetworks/U1-0817",
		"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 "SynastriaNetworks/U1-0817" \
        --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": "SynastriaNetworks/U1-0817",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SynastriaNetworks/U1-0817 with Docker Model Runner:
```
docker model run hf.co/SynastriaNetworks/U1-0817
```

gustajunq commited on Aug 17

Commit

fdbf3ba

verified ·

1 Parent(s): 5e24b1e

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -10

README.md CHANGED Viewed

@@ -8,8 +8,6 @@ base_model:
 pipeline_tag: text-generation
 library_name: transformers
 ---
-Uirapuru U1.1
 <p align="center">
   <img src="https://ol0qculvfdcjt1p5.public.blob.vercel-storage.com/112%20Sem%20T%C3%ADtulo_20260718173634.png" width="180" alt="Uirapuru Logo">
 </p><p align="center">
@@ -38,7 +36,7 @@ Compared to Uirapuru U1, U1.1 focuses on:
 - Higher LoRA rank — increased adapter capacity for capturing behavioral and capability changes.
 - No adaptive thinking — the model was retrained without the adaptive-thinking mechanism used in previous experiments.
-Thinking Behavior
 Uirapuru U1.1 does not use adaptive thinking.
@@ -46,7 +44,7 @@ The model was retrained to incorporate its reasoning behavior directly into its
 This does not mean that the model cannot reason. Instead, the goal is to provide a more consistent reasoning behavior across different types of prompts.
-Training
 Uirapuru U1.1 was produced through a new training cycle based on Uirapuru U1.
@@ -62,7 +60,7 @@ The training focused particularly on:
 4. Informal Brazilian Portuguese.
 5. Agentic and multi-step task behavior.
-Intended Use
 Uirapuru U1.1 is intended for applications such as:
@@ -74,7 +72,7 @@ Uirapuru U1.1 is intended for applications such as:
 - LLM experimentation
 - Research and prototyping
-Expected Behavior
 Uirapuru U1.1 is designed to provide:
@@ -86,7 +84,7 @@ Uirapuru U1.1 is designed to provide:
 - Improved behavior for agentic workflows.
 - More consistent reasoning without adaptive thinking.
-Limitations
 Uirapuru U1.1 is still an experimental model and may:
@@ -100,7 +98,7 @@ Uirapuru U1.1 is still an experimental model and may:
 A higher LoRA rank does not guarantee that every trained behavior or capability will generalize perfectly to unseen situations.
-Safety
 Uirapuru U1.1 should not be assumed to be perfectly safe or reliable.
@@ -108,13 +106,13 @@ Applications using the model should implement appropriate safeguards, validation
 The model should not be relied upon as the sole source of truth for high-impact decisions.
-Version Summary
 Uirapuru U1.1 = Uirapuru U1 + retraining + higher-rank LoRA + stronger identity + improved reasoning behavior + new capabilities + better informal Brazilian Portuguese + improved agentic behavior.
 U1.1 is intended as a hotfix and evolutionary update, rather than a completely new model generation.
-Credits
 Developed by SynastrIA Networks.

 pipeline_tag: text-generation
 library_name: transformers
 ---
 <p align="center">
   <img src="https://ol0qculvfdcjt1p5.public.blob.vercel-storage.com/112%20Sem%20T%C3%ADtulo_20260718173634.png" width="180" alt="Uirapuru Logo">
 </p><p align="center">
 - Higher LoRA rank — increased adapter capacity for capturing behavioral and capability changes.
 - No adaptive thinking — the model was retrained without the adaptive-thinking mechanism used in previous experiments.
+## Thinking Behavior
 Uirapuru U1.1 does not use adaptive thinking.
 This does not mean that the model cannot reason. Instead, the goal is to provide a more consistent reasoning behavior across different types of prompts.
+## Training
 Uirapuru U1.1 was produced through a new training cycle based on Uirapuru U1.
 4. Informal Brazilian Portuguese.
 5. Agentic and multi-step task behavior.
+## Intended Use
 Uirapuru U1.1 is intended for applications such as:
 - LLM experimentation
 - Research and prototyping
+## Expected Behavior
 Uirapuru U1.1 is designed to provide:
 - Improved behavior for agentic workflows.
 - More consistent reasoning without adaptive thinking.
+## Limitations
 Uirapuru U1.1 is still an experimental model and may:
 A higher LoRA rank does not guarantee that every trained behavior or capability will generalize perfectly to unseen situations.
+## Safety
 Uirapuru U1.1 should not be assumed to be perfectly safe or reliable.
 The model should not be relied upon as the sole source of truth for high-impact decisions.
+## Version Summary
 Uirapuru U1.1 = Uirapuru U1 + retraining + higher-rank LoRA + stronger identity + improved reasoning behavior + new capabilities + better informal Brazilian Portuguese + improved agentic behavior.
 U1.1 is intended as a hotfix and evolutionary update, rather than a completely new model generation.
+## Credits
 Developed by SynastrIA Networks.