Instructions to use OpenPathAI/Orbit-3-8B-Llama-thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenPathAI/Orbit-3-8B-Llama-thinking with Transformers:

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

pipe = pipeline("text-generation", model="OpenPathAI/Orbit-3-8B-Llama-thinking")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenPathAI/Orbit-3-8B-Llama-thinking")
model = AutoModelForCausalLM.from_pretrained("OpenPathAI/Orbit-3-8B-Llama-thinking", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use OpenPathAI/Orbit-3-8B-Llama-thinking with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenPathAI/Orbit-3-8B-Llama-thinking with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenPathAI/Orbit-3-8B-Llama-thinking"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenPathAI/Orbit-3-8B-Llama-thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenPathAI/Orbit-3-8B-Llama-thinking

SGLang

How to use OpenPathAI/Orbit-3-8B-Llama-thinking 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 "OpenPathAI/Orbit-3-8B-Llama-thinking" \
    --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": "OpenPathAI/Orbit-3-8B-Llama-thinking",
		"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 "OpenPathAI/Orbit-3-8B-Llama-thinking" \
        --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": "OpenPathAI/Orbit-3-8B-Llama-thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenPathAI/Orbit-3-8B-Llama-thinking with Docker Model Runner:
```
docker model run hf.co/OpenPathAI/Orbit-3-8B-Llama-thinking
```

titanthree commited on Sep 26

Commit

5c48534

verified ·

1 Parent(s): f64aa28

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -46,7 +46,7 @@ This model is specifically designed for:
 | Total Parameters | 8.07 Billion |
 | Trained Parameters | 41.9 Million (0.52%) |
 | Architecture | Transformer-based |
-| Context Length | 512 tokens (during training) |
 | Language | English |
 ---

 | Total Parameters | 8.07 Billion |
 | Trained Parameters | 41.9 Million (0.52%) |
 | Architecture | Transformer-based |
+| Context Length | 8.192 tokens (during training) |
 | Language | English |
 ---