mistralai
/
mixtral-8x7b-instruct-v0.1
The Mixtral-8x7B-instruct-v0.1 Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts tuned to be a helpful assistant.
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 4x Nvidia A100 (80GB) GPU hardware, which costs $0.0056 per second.
Create a training
Install the Python library:
pip install replicate
Then, run this to create a training with replicate-internal/mixtral-instruct-v0.1-fp16-triton-sm80:63888b8a as the base model:
import replicate
training = replicate.trainings.create(
version="replicate-internal/mixtral-instruct-v0.1-fp16-triton-sm80:63888b8acf98421eb6ec992180ef3fbd2510f2ab18fcf368e76b13ccaf16d308",
input={
...
},
destination=f"{username}/<destination-model-name>"
)
print(training)
curl -s -X POST \
-d '{"destination": "{username}/<destination-model-name>", "input": {...}}' \
-H "Authorization: Bearer $REPLICATE_API_TOKEN" \
https://api.replicate.com/v1/models/mistralai/mixtral-8x7b-instruct-v0.1/versions/63888b8acf98421eb6ec992180ef3fbd2510f2ab18fcf368e76b13ccaf16d308/trainings
The API response will look like this:
{
"id": "zz4ibbonubfz7carwiefibzgga",
"version": "63888b8acf98421eb6ec992180ef3fbd2510f2ab18fcf368e76b13ccaf16d308",
"status": "starting",
"input": {
"data": "..."
},
"output": null,
"error": null,
"logs": null,
"started_at": null,
"created_at": "2023-03-28T21:47:58.566434Z",
"completed_at": null
}
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.