From zero to IPO. Designed for every stage of your journey.

ModelsDatasets

PricingDocumentation

Login

Build with
open-source AI.

A better way to run & fine-tune open-source models on your data. Your data, your models, your AI.

Forefront enables developers to build on open-source AI with the familiar experience of leading closed-source platforms.

Forget deprecated models, inconsistent performance, arbitrary usage policies, and lack of control & transparency.

Don’t settle for AI you don’t own. The future is open.

Models designed to be your own.

Start fine-tuning models on your data in minutes. Fine-tune models for any use case.

No data? No problem. Start with the best model for your use case. Use our API to store the responses. Then seamlessly fine-tune a model when you’re ready.

from openai import OpenAI
from forefront import ff

openai = OpenAI(api_key="OPENAI_API_KEY")
pipe = ff.pipelines.get_by_id("PIPELINE_ID")

messages = [{
    "role": "user",
    "content": "What is the meaning of 42?"
}]

completion = openai.complete(
    engine="gpt-4",
    messages=messages
)

messages.append({
    "role": "assistant",
    "content": completion["choices"][0]["text"]
})

pipe.add(messages)

Validate model performance. Assess how your fine-tuned model performs on a validation set.

Validation results

Sample

of 10

User

How can I reduce stress at work?

Validation

Take short, regular breaks throughout the day to step away from your work. This helps in clearing your mind and reducing stress.

Your model

Organize your workspace and keep it clutter-free. A tidy space can lead to a more peaceful and less stressful work environment.

Watch your model learn. Analyze built-in loss charts as your model trains.

Training loss

0.132

const ff = new Forefront(process.env.FOREFRONT_API_KEY); try { const response = await ff.chat.completions.create({ model: "team-name/fine-tuned-llm", messages: [ { role: "system", content: "You are Deep Thought." } { role: "user", content: "What is the meaning of life?", }, ], max_tokens: 64, temperature: 0.5, stop: ["\n"], stream: false }); const completion = response.choices[0].content } catch (e) { console.log(e); }

Integration made simple. Three lines of code and you’re good to go.

+3

-3

Take your model and run. Prefer self-hosting or hosting with another provider? Export your models and host them where you want.

Import from HuggingFace. Forget loading models into Colab. Just copy and paste the model string into Forefront and inference in minutes.

= OpenAI(api_key="OPENAI_API_KEY") pipe = ff.pipelines.get_by_id("PIPELINE_ID") messages = [{ "role": "user", "content": "What is the meaning of 42?" }] completion = openai.complete( engine="gpt-4", messages=messages ) messages.append({ "role": "assistant", "content": completion["choices"][0]["text"] }) pipe.add(messages)

Become one with your data. Navigate your data in the Inspector—built to help you thoroughly and quickly inspect your samples.

Sample

of 12

User

Divide 129 by 42

Assistant

To divide 129 by 42, you can use long division or a calculator. Here's the long division method: ```markdown __3_ 42|129 -126 _____ 3 ``` So, 129 divided by 42 is equal to 3 with a remainder of 3. If you want to express it as a mixed number, it would be 3 and 3/42. To simplify the fraction, you can divide both the numerator and the denominator by their greatest common divisor, which is 3. So, the simplified fraction would be 1/14. Thus, the final answer is 3 and 1/14, or 3.07142857 when expressed as a decimal (rounded to eight decimal places).

Instant insights. Get a sense of your data’s distribution and patterns. Discover imbalances and biases without painstaking effort.

Tokens per sample

2900