Text Generation
Transformers
Safetensors
English
qwen2
routing
preference
llm
conversational
text-generation-inference
Instructions to use katanemo/Arch-Router-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use katanemo/Arch-Router-1.5B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="katanemo/Arch-Router-1.5B") 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("katanemo/Arch-Router-1.5B") model = AutoModelForCausalLM.from_pretrained("katanemo/Arch-Router-1.5B", 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]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use katanemo/Arch-Router-1.5B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "katanemo/Arch-Router-1.5B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "katanemo/Arch-Router-1.5B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/katanemo/Arch-Router-1.5B
- SGLang
How to use katanemo/Arch-Router-1.5B 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 "katanemo/Arch-Router-1.5B" \ --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": "katanemo/Arch-Router-1.5B", "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 "katanemo/Arch-Router-1.5B" \ --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": "katanemo/Arch-Router-1.5B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use katanemo/Arch-Router-1.5B with Docker Model Runner:
docker model run hf.co/katanemo/Arch-Router-1.5B
Update LICENSE
Browse files
LICENSE
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
# Katanemo Labs, Inc. COMMUNITY LICENSE AGREEMENT
|
| 2 |
-
**Version Release Date:**
|
| 3 |
|
| 4 |
This Katanemo Labs, Inc. COMMUNITY LICENSE AGREEMENT is based on the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. The terms and conditions have been adapted to reflect the proprietary nature of Katanemo Labs' materials.
|
| 5 |
|
|
@@ -54,6 +54,14 @@ You may NOT package, distribute, or make available the Katanemo Materials as par
|
|
| 54 |
|
| 55 |
unless you obtain a separate commercial license from Katanemo Labs.
|
| 56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
---
|
| 58 |
|
| 59 |
This license does not grant trademark rights or rights outside the scope described above.
|
|
|
|
| 1 |
# Katanemo Labs, Inc. COMMUNITY LICENSE AGREEMENT
|
| 2 |
+
**Version Release Date:** November 15th, 2025
|
| 3 |
|
| 4 |
This Katanemo Labs, Inc. COMMUNITY LICENSE AGREEMENT is based on the Llama 3.2 Community License, Copyright © Meta Platforms, Inc. The terms and conditions have been adapted to reflect the proprietary nature of Katanemo Labs' materials.
|
| 5 |
|
|
|
|
| 54 |
|
| 55 |
unless you obtain a separate commercial license from Katanemo Labs.
|
| 56 |
|
| 57 |
+
**Exception for Katanemo-integrated products.**
|
| 58 |
+
You do not need a separate commercial license when you use the Arch-Router model (or other Katanemo models) **only through a Katanemo product that provides an integrated experience and is itself licensed under Apache 2.0** (for example, the Arch Gateway project at https://github.com/katanemo/archgw), as long as:
|
| 59 |
+
|
| 60 |
+
1. The model is called only through that integrated product experience and is **not** exposed or offered as a separate framework, proxy, middleware, gateway infrastructure product, or similar service; and
|
| 61 |
+
2. For Arch Gateway (archgw), any LLM traffic using the Arch-Router model is proxied through Arch Gateway’s data plane.
|
| 62 |
+
|
| 63 |
+
This exception applies only to use of the Katanemo Materials through such Katanemo-provided integrated products. It does **not** permit you to repackage or redistribute the Katanemo Materials as your own framework, proxy server, middleware, gateway infrastructure product, or any substantially similar product.
|
| 64 |
+
|
| 65 |
---
|
| 66 |
|
| 67 |
This license does not grant trademark rights or rights outside the scope described above.
|