Instructions to use deepreinforce-ai/Ornith-1.0-397B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepreinforce-ai/Ornith-1.0-397B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="deepreinforce-ai/Ornith-1.0-397B") 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("deepreinforce-ai/Ornith-1.0-397B") model = AutoModelForMultimodalLM.from_pretrained("deepreinforce-ai/Ornith-1.0-397B") 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?"} ] }, ] 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 deepreinforce-ai/Ornith-1.0-397B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "deepreinforce-ai/Ornith-1.0-397B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepreinforce-ai/Ornith-1.0-397B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/deepreinforce-ai/Ornith-1.0-397B
- SGLang
How to use deepreinforce-ai/Ornith-1.0-397B 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 "deepreinforce-ai/Ornith-1.0-397B" \ --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": "deepreinforce-ai/Ornith-1.0-397B", "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 "deepreinforce-ai/Ornith-1.0-397B" \ --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": "deepreinforce-ai/Ornith-1.0-397B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use deepreinforce-ai/Ornith-1.0-397B with Docker Model Runner:
docker model run hf.co/deepreinforce-ai/Ornith-1.0-397B
Update README.md
Browse files
README.md
CHANGED
|
@@ -344,47 +344,110 @@ Ornith-1.0-397B excels in tool-calling and agentic coding capabilities.
|
|
| 344 |
Because Ornith-1.0-397B exposes an OpenAI-compatible endpoint with tool calling, it works out of the box with standard agent frameworks. Below is a minimal example that connects Ornith-1.0-397B to tools through an MCP server.
|
| 345 |
|
| 346 |
```python
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 347 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 348 |
```
|
| 349 |
|
| 350 |
**Examples of using Ornith with agent harness:**
|
| 351 |
|
| 352 |
#### Hermes Agent
|
| 353 |
```bash
|
| 354 |
-
|
|
|
|
|
|
|
|
|
|
| 355 |
```
|
| 356 |
|
| 357 |
-
####
|
| 358 |
-
```bash
|
| 359 |
-
|
| 360 |
-
```
|
| 361 |
|
| 362 |
-
#### llama.cpp / Ollama
|
| 363 |
```bash
|
| 364 |
-
|
|
|
|
|
|
|
|
|
|
| 365 |
```
|
| 366 |
|
| 367 |
#### Unsloth Studio
|
| 368 |
|
| 369 |
```bash
|
| 370 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 371 |
```
|
| 372 |
|
| 373 |
-
####
|
| 374 |
-
|
| 375 |
```bash
|
|
|
|
| 376 |
|
| 377 |
-
|
|
|
|
|
|
|
|
|
|
| 378 |
|
|
|
|
|
|
|
|
|
|
| 379 |
|
| 380 |
### Coding CLIs
|
| 381 |
|
| 382 |
Ornith-1.0-397B is optimized for terminal-based coding agents. Point any OpenAI-compatible coding CLI at your Ornith-1.0-397B endpoint (set `OPENAI_BASE_URL` and `OPENAI_API_KEY`) to understand large codebases, automate tedious work, and ship faster.
|
| 383 |
|
| 384 |
-
|
| 385 |
#### OpenCode
|
| 386 |
```bash
|
| 387 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 388 |
```
|
| 389 |
|
| 390 |
|
|
|
|
| 344 |
Because Ornith-1.0-397B exposes an OpenAI-compatible endpoint with tool calling, it works out of the box with standard agent frameworks. Below is a minimal example that connects Ornith-1.0-397B to tools through an MCP server.
|
| 345 |
|
| 346 |
```python
|
| 347 |
+
import os
|
| 348 |
+
from openai import OpenAI
|
| 349 |
+
|
| 350 |
+
client = OpenAI(
|
| 351 |
+
base_url=os.getenv("OPENAI_BASE_URL", "http://localhost:8000/v1"),
|
| 352 |
+
api_key=os.getenv("OPENAI_API_KEY", "EMPTY"),
|
| 353 |
+
)
|
| 354 |
+
|
| 355 |
+
tools = [
|
| 356 |
+
{
|
| 357 |
+
"type": "function",
|
| 358 |
+
"function": {
|
| 359 |
+
"name": "run_shell",
|
| 360 |
+
"description": "Run a shell command and return its output.",
|
| 361 |
+
"parameters": {
|
| 362 |
+
"type": "object",
|
| 363 |
+
"properties": {
|
| 364 |
+
"command": {"type": "string", "description": "The command to run"}
|
| 365 |
+
},
|
| 366 |
+
"required": ["command"],
|
| 367 |
+
},
|
| 368 |
+
},
|
| 369 |
+
}
|
| 370 |
+
]
|
| 371 |
+
|
| 372 |
+
messages = [{"role": "user", "content": "List the Python files in the current directory."}]
|
| 373 |
|
| 374 |
+
response = client.chat.completions.create(
|
| 375 |
+
model="deepreinforce-ai/Ornith-1.0-397B",
|
| 376 |
+
messages=messages,
|
| 377 |
+
tools=tools,
|
| 378 |
+
temperature=0.6,
|
| 379 |
+
top_p=0.95,
|
| 380 |
+
)
|
| 381 |
+
print(response.choices[0].message)
|
| 382 |
```
|
| 383 |
|
| 384 |
**Examples of using Ornith with agent harness:**
|
| 385 |
|
| 386 |
#### Hermes Agent
|
| 387 |
```bash
|
| 388 |
+
# Hermes talks to any OpenAI-compatible endpoint — point it at your Ornith server.
|
| 389 |
+
export OPENAI_BASE_URL="http://localhost:8000/v1"
|
| 390 |
+
export OPENAI_API_KEY="EMPTY"
|
| 391 |
+
export MODEL="deepreinforce-ai/Ornith-1.0-397B"
|
| 392 |
```
|
| 393 |
|
| 394 |
+
#### OpenClaw
|
|
|
|
|
|
|
|
|
|
| 395 |
|
|
|
|
| 396 |
```bash
|
| 397 |
+
# OpenClaw talks to any OpenAI-compatible endpoint — point it at your Ornith server.
|
| 398 |
+
export OPENAI_BASE_URL="http://localhost:8000/v1"
|
| 399 |
+
export OPENAI_API_KEY="EMPTY"
|
| 400 |
+
export OPENAI_MODEL="deepreinforce-ai/Ornith-1.0-397B"
|
| 401 |
```
|
| 402 |
|
| 403 |
#### Unsloth Studio
|
| 404 |
|
| 405 |
```bash
|
| 406 |
+
pip install unsloth
|
| 407 |
+
|
| 408 |
+
# Load Ornith for fast local inference or fine-tuning (Python):
|
| 409 |
+
# from unsloth import FastLanguageModel
|
| 410 |
+
# model, tokenizer = FastLanguageModel.from_pretrained(
|
| 411 |
+
# "deepreinforce-ai/Ornith-1.0-397B",
|
| 412 |
+
# max_seq_length=262144,
|
| 413 |
+
# load_in_4bit=True,
|
| 414 |
+
# )
|
| 415 |
```
|
| 416 |
|
| 417 |
+
#### OpenHands
|
|
|
|
| 418 |
```bash
|
| 419 |
+
pip install openhands-ai
|
| 420 |
|
| 421 |
+
# OpenHands routes through LiteLLM; the "openai/" prefix selects the OpenAI-compatible path.
|
| 422 |
+
export LLM_MODEL="openai/deepreinforce-ai/Ornith-1.0-397B"
|
| 423 |
+
export LLM_BASE_URL="http://localhost:8000/v1"
|
| 424 |
+
export LLM_API_KEY="EMPTY"
|
| 425 |
|
| 426 |
+
# Launch the CLI (or run the official OpenHands Docker image with the same env vars).
|
| 427 |
+
openhands
|
| 428 |
+
```
|
| 429 |
|
| 430 |
### Coding CLIs
|
| 431 |
|
| 432 |
Ornith-1.0-397B is optimized for terminal-based coding agents. Point any OpenAI-compatible coding CLI at your Ornith-1.0-397B endpoint (set `OPENAI_BASE_URL` and `OPENAI_API_KEY`) to understand large codebases, automate tedious work, and ship faster.
|
| 433 |
|
|
|
|
| 434 |
#### OpenCode
|
| 435 |
```bash
|
| 436 |
+
# Register your local Ornith endpoint as a provider in ~/.config/opencode/opencode.json:
|
| 437 |
+
#
|
| 438 |
+
# {
|
| 439 |
+
# "$schema": "https://opencode.ai/config.json",
|
| 440 |
+
# "provider": {
|
| 441 |
+
# "ornith": {
|
| 442 |
+
# "npm": "@ai-sdk/openai-compatible",
|
| 443 |
+
# "name": "Ornith (local)",
|
| 444 |
+
# "options": { "baseURL": "http://localhost:8000/v1", "apiKey": "EMPTY" },
|
| 445 |
+
# "models": { "deepreinforce-ai/Ornith-1.0-397B": { "name": "Ornith-1.0-397B" } }
|
| 446 |
+
# }
|
| 447 |
+
# }
|
| 448 |
+
# }
|
| 449 |
+
|
| 450 |
+
opencode
|
| 451 |
```
|
| 452 |
|
| 453 |
|