Welcome to distil labs | Distil Labs

distil labs provides a platform for training task-specific small language models (SLMs) with just a prompt and a few dozen examples. Our platform handles the complex machine learning processes behind the scenes. This allows you to focus on your use-case instead of managing large datasets and infrastructure.

Why distil labs?

Train Specialized Models with Minimal Data: Train specialized SLMs with just a prompt and a few dozen examples.
Full Ownership of Your Models: Download and deploy your models anywhere - your servers, applications, or at the edge. No vendor lock-in for inference.
Fully Automated ML Pipeline: No ML expertise required, we handle the technical complexity.
High Performance with Smaller Footprint: Get LLM-level accuracy with models up to 400x smaller. Run locally on affordable hardware.

Minimal example

Here’s how simple it is to train a specialized model with distil labs (get YOUR_API_KEY):

1 import json
2 import requests
3 
4 # Register a new model
5 auth_header = {"Authorization": f"Bearer {distil_bearer_token()}"}
6 response = requests.post(
7     "https://api.distillabs.ai/models",
8     data=json.dumps({"name": "testmodel-123"}),
9     headers={"Content-Type": "application/json", **auth_header},
10 )
11 model_id = response.json()["id"]
12 
13 # Upload your task description and examples
14 data = {
15     "job_description": {"type": "json", "content": open("data/job_description.json").read()},
16     "train_data": {"type": "csv", "content": open("data/train.csv").read()},
17     "test_data": {"type": "csv", "content": open("data/test.csv").read()},
18     "unstructured_data": {"type": "csv", "content": open("data/unstructured.csv").read()},
19     "config": {"type": "yaml", "content": open("data/config.yaml").read()},
20 }
21 response = requests.post(
22     f"https://api.distillabs.ai/models/{model_id}/uploads",
23     data=json.dumps(data),
24     headers={"Content-Type": "application/json", **auth_header},
25 )
26 upload_id = response.json()["id"]
27 
28 # Start SLM training
29 response = requests.post(
30     f"https://api.distillabs.ai/models/{model_id}/training",
31     data=json.dumps({"upload_id": upload_id}),
32     headers={"Content-Type": "application/json", **auth_header},
33 )
34 slm_training_job_id = response.json()["id"]
35 
36 # When training completes, get your model download link
37 response = requests.get(
38     f"https://api.distillabs.ai/trainings/{slm_training_job_id}/model",
39     headers=auth_header,
40 )
41 print(response.json())

Next steps

Ready to build your own specialized models? Continue to our How to train your SLM guide, see more detailed examples, or jump straight into the API reference.

How to train your SLM?

Tutorials

API Reference