Community

Blog

Fireworks AI Docs

API Reference

Tools & SDK

Get Started

Status

Support

List Fine-tuning Jobs

If not specified, default to the base model conversation_config.template, if exists.

the boolean flag to cleanup the deployment after the data generation job is done.

the model deployment where we generate responses from.

The JSON dataset field that contains the classification label.

The JSON dataset field that is to be classified.

The template used to format the dataset input.

The template used to format the dataset output.

- OK: Not an error; returned on success.

HTTP Mapping: 200 OK
 - CANCELLED: The operation was cancelled, typically by the caller.

HTTP Mapping: 499 Client Closed Request
 - UNKNOWN: Unknown error.  For example, this error may be returned when
a `Status` value received from another address space belongs to
an error space that is not known in this address space.  Also
errors raised by APIs that do not return enough error information
may be converted to this error.

HTTP Mapping: 500 Internal Server Error
 - INVALID_ARGUMENT: The client specified an invalid argument.  Note that this differs
from `FAILED_PRECONDITION`.  `INVALID_ARGUMENT` indicates arguments
that are problematic regardless of the state of the system
(e.g., a malformed file name).

HTTP Mapping: 400 Bad Request
 - DEADLINE_EXCEEDED: The deadline expired before the operation could complete. For operations
that change the state of the system, this error may be returned
even if the operation has completed successfully.  For example, a
successful response from a server could have been delayed long
enough for the deadline to expire.

HTTP Mapping: 504 Gateway Timeout
 - NOT_FOUND: Some requested entity (e.g., file or directory) was not found.

Note to server developers: if a request is denied for an entire class
of users, such as gradual feature rollout or undocumented allowlist,
`NOT_FOUND` may be used. If a request is denied for some users within
a class of users, such as user-based access control, `PERMISSION_DENIED`
must be used.

HTTP Mapping: 404 Not Found
 - ALREADY_EXISTS: The entity that a client attempted to create (e.g., file or directory)
already exists.

HTTP Mapping: 409 Conflict
 - PERMISSION_DENIED: The caller does not have permission to execute the specified
operation. `PERMISSION_DENIED` must not be used for rejections
caused by exhausting some resource (use `RESOURCE_EXHAUSTED`
instead for those errors). `PERMISSION_DENIED` must not be
used if the caller can not be identified (use `UNAUTHENTICATED`
instead for those errors). This error code does not imply the
request is valid or the requested entity exists or satisfies
other pre-conditions.

HTTP Mapping: 403 Forbidden
 - UNAUTHENTICATED: The request does not have valid authentication credentials for the
operation.

HTTP Mapping: 401 Unauthorized
 - RESOURCE_EXHAUSTED: Some resource has been exhausted, perhaps a per-user quota, or
perhaps the entire file system is out of space.

HTTP Mapping: 429 Too Many Requests
 - FAILED_PRECONDITION: The operation was rejected because the system is not in a state
required for the operation's execution.  For example, the directory
to be deleted is non-empty, an rmdir operation is applied to
a non-directory, etc.

Service implementors can use the following guidelines to decide
between `FAILED_PRECONDITION`, `ABORTED`, and `UNAVAILABLE`:
 (a) Use `UNAVAILABLE` if the client can retry just the failing call.
 (b) Use `ABORTED` if the client should retry at a higher level. For
     example, when a client-specified test-and-set fails, indicating the
     client should restart a read-modify-write sequence.
 (c) Use `FAILED_PRECONDITION` if the client should not retry until
     the system state has been explicitly fixed. For example, if an "rmdir"
     fails because the directory is non-empty, `FAILED_PRECONDITION`
     should be returned since the client should not retry unless
     the files are deleted from the directory.

HTTP Mapping: 400 Bad Request
 - ABORTED: The operation was aborted, typically due to a concurrency issue such as
a sequencer check failure or transaction abort.

See the guidelines above for deciding between `FAILED_PRECONDITION`,
`ABORTED`, and `UNAVAILABLE`.

HTTP Mapping: 409 Conflict
 - OUT_OF_RANGE: The operation was attempted past the valid range.  E.g., seeking or
reading past end-of-file.

Unlike `INVALID_ARGUMENT`, this error indicates a problem that may
be fixed if the system state changes. For example, a 32-bit file
system will generate `INVALID_ARGUMENT` if asked to read at an
offset that is not in the range [0,2^32-1], but it will generate
`OUT_OF_RANGE` if asked to read from an offset past the current
file size.

There is a fair bit of overlap between `FAILED_PRECONDITION` and
`OUT_OF_RANGE`.  We recommend using `OUT_OF_RANGE` (the more specific
error) when it applies so that callers who are iterating through
a space can easily look for an `OUT_OF_RANGE` error to detect when
they are done.

HTTP Mapping: 400 Bad Request
 - UNIMPLEMENTED: The operation is not implemented or is not supported/enabled in this
service.

HTTP Mapping: 501 Not Implemented
 - INTERNAL: Internal errors.  This means that some invariants expected by the
underlying system have been broken.  This error code is reserved
for serious errors.

HTTP Mapping: 500 Internal Server Error
 - UNAVAILABLE: The service is currently unavailable.  This is most likely a
transient condition, which can be corrected by retrying with
a backoff. Note that it is not always safe to retry
non-idempotent operations.

See the guidelines above for deciding between `FAILED_PRECONDITION`,
`ABORTED`, and `UNAVAILABLE`.

HTTP Mapping: 503 Service Unavailable
 - DATA_LOSS: Unrecoverable data loss or corruption.

HTTP Mapping: 500 Internal Server Error

Mimics [https://github.com/googleapis/googleapis/blob/master/google/rpc/code.proto]

The batch size of dataset used for training.

The email address of the user who created this fine tuning job.

The max length to cut off prompts, used by draft model data generation.

The name of the dataset used for training. A dataset ID may also be supplied, in
which case the ID will be normalized into the fully qualified dataset name using
the parent of the job.

the split flag to take from training dataset for evaluation.

The lora target modules used for training.

The learning rate scheduler used for training.

The token to mask out prompts, used by draft model data generation.

The batch size of dataset used for training per accelerator.

the model id to generate for training jobs.

The token for padding, used by draft model data generation.

The Weights & Biases API key associated with the entity.
Required if and only if wandb_entity is specified.

The Weights & Biases entity where training progress should be reported.
If unspecified, then progress will not be reported to W&B.

The Weights & Biases project where training progress should be reported.
Required if and only if wandb_entity is specified.

The Weights & Biases url to see training progress.

peft addon model in fireworks format to warm start a fine-tuning job from.

Next ID: 46

The list of datasets to be used for training.  The dataset IDs may also be
supplied, in which case the ID will be normalized into the fully qualified
dataset name using the parent of the job.
TODO(shaunak): Once this is rolled out deprecate field 5 in favour of this.

- CREATING: The fine-tuning job is being created.
 - PENDING: The fine-tuning job scheduled and is waiting for resource allocation.
 - RUNNING: The fine-tuning job is running.
 - COMPLETED: The fine-tuning job has finished successfully.
 - FAILED: The fine-tuning job has failed.
 - DELETING: The fine-tuning job is being deleted

Next ID: 8

A developer-facing error message in English.

Mimics [https://github.com/googleapis/googleapis/blob/master/google/rpc/status.proto]

BearerAuth

Fireworks AI is a generative AI inference platform to run and customize models with industry-leading speed and production-readiness.

Introduction

Quickstart

This document outlines basic Fireworks AI concepts.

Concepts

Querying text models

Querying vision-language models

Querying embedding models

Using function-calling

Using grammar mode

Using JSON mode

Prompt caching

Overview

Uploading a custom model

Fine-tuning models

Fine-tuning models via API

Deploying models

Quantization

On-demand deployments

Reserved capacity

Add and delete additional users in your Fireworks account

Managing users

Quotas

Set up custom Single Sign-On (SSO) authentication for Fireworks AI

Custom SSO

Creates a model response for the given chat conversation.

Create Chat Completion

Creates a completion for the provided prompt and parameters.

Create Completion

Create embeddings

Generate an image

Transcribe audio

Translate audio

Align transcription

Transcribe audio (realtime)

Learn to create, deploy, and manage resources using Firectl

Getting Started

Authentication for access to your account

Authentication

List various resources in an Fireworks AI account

List Resources

Create a Deployment on Fireworks AI platform

Create a deployment

Create a fine-tuning job with a base model

Create a fine-tuning job

Create a Dataset on Fireworks AI platform

Create a Dataset

Create Model

Deletes resource(s) in a Fireworks AI account

Delete Resources

Deploy Model

Download a model from third-party locations

Download a model

Retrieves model information from Fireworks AI platform

Get Resources

Imports specified model from Fireworks AI Platform

Import Model

Undeploy a model on Fireworks AI platform

Undeploy Model

Updates Resources on Fireworks AI platform

API Documentation

LLM API

Embeddings API

Image API

Audio API

Accounts

Deployments

Models

Users

Datasets

Fine-tuning Jobs

List Fine-tuning Jobs

Authorizations

Path Parameters

Query Parameters

Response