Instructions to use zenlm/zen-sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zenlm/zen-sql with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="zenlm/zen-sql")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-sql") model = AutoModelForCausalLM.from_pretrained("zenlm/zen-sql", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use zenlm/zen-sql with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "zenlm/zen-sql" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zenlm/zen-sql", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/zenlm/zen-sql
- SGLang
How to use zenlm/zen-sql 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 "zenlm/zen-sql" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zenlm/zen-sql", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "zenlm/zen-sql" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zenlm/zen-sql", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use zenlm/zen-sql with Docker Model Runner:
docker model run hf.co/zenlm/zen-sql
Restore upstream attribution in NOTICE (Qwen3-8B)
Browse filesThe shipped NOTICE reads "Copyright 2025-2026 Zen Authors" and names no upstream, but these weights are a derivative of Qwen/Qwen3-8B (Apache-2.0).
Apache-2.0 section 4(c) requires retaining upstream attribution notices in distributed derivative works; section 4(d) requires carrying upstream's NOTICE text where upstream ships one. Replacing upstream's copyright with Zen's drops both.
Evidence of derivation: via zenlm/zen-pro; config.json: Qwen3ForCausalLM, hidden 4096, 36 layers
This PR names the upstream and its true license, and keeps Zen's copyright scoped to Zen's own modifications. One LICENSE + one NOTICE; no license change.
|
@@ -1,5 +1,8 @@
|
|
| 1 |
-
|
| 2 |
Copyright 2025-2026 Zen Authors
|
| 3 |
|
| 4 |
-
This model
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
zen-sql
|
| 2 |
Copyright 2025-2026 Zen Authors
|
| 3 |
|
| 4 |
+
This model is a derivative work distributed under the Apache-2.0 license.
|
| 5 |
+
A copy of the license is in the accompanying LICENSE file.
|
| 6 |
+
|
| 7 |
+
Built on:
|
| 8 |
+
- Qwen3-8B (https://huggingface.co/Qwen/Qwen3-8B), Apache-2.0.
|