nateraw / axolotl-trainer-llama-2-7b

  • Public
  • 34 runs
  • L40S
Run with an API
Playground API Examples Train README Versions

If you haven’t yet trained a model on Replicate, we recommend you read one of the following guides.

Pricing

Trainings for this model run on 8x Nvidia L40S GPU hardware, which costs $0.0078 per second.

Create a training

Install the Python library:

pip install replicate

Then, run this to create a training with nateraw/axolotl-trainer-llama-2-7b:895d22a6 as the base model:

import replicate

training = replicate.trainings.create(
  version="nateraw/axolotl-trainer-llama-2-7b:895d22a6364e09e25fc2ba5ce8c23a0f8e957f7ac69620ab8dd21a07cde2cfb5",
  input={
    ...
  },
  destination=f"{username}/<destination-model-name>"
)

print(training)

Note that before you can create a training, you’ll need to create a model and use its name as the value for the destination field.