Python SDK

Installation

pip install fleethq

Requires Python 3.10 or later. Install huggingface_hub separately if you want to use client.models.from_huggingface():

pip install fleethq huggingface_hub

Client

from fleet import Fleet

client = Fleet()                          # reads ~/.fleet/credentials
client = Fleet(api_key="fleet_sk_...")    # explicit key
client = Fleet(base_url="http://localhost:8787")  # custom endpoint

---

Models

client.models.from_huggingface(repo_id, ...)

Download a model from HuggingFace and upload it to Fleet. Returns immediately if the model is already uploaded.

model = client.models.from_huggingface("meta-llama/Llama-3.2-1B")
model = client.models.from_huggingface("mistralai/Mistral-7B-v0.1", revision="main")

client.models.upload(directory, ...)

Upload a local model directory to Fleet.

model = client.models.upload("./my-model/")
model = client.models.upload("./my-model/", name="my-model-v2")

Fleet hashes the model files before uploading. Identical models are deduplicated automatically.

client.models.get(model_id)

model = client.models.get("model_abc123")
print(model.name, model.status)

client.models.list(source=None)

models = client.models.list()              # all models
models = client.models.list(source="upload")      # uploaded base models
models = client.models.list(source="job_output")  # fine-tuned models
models = client.models.list(source="checkpoint")  # training checkpoints

Model object

model.estimate(dataset, method, hyperparameters)

Estimate cost and runtime for a training job without launching it. Returns a dict with per-tier ranges.

estimate = model.estimate(dataset, method="lora")

print(estimate["recommended_tier"])   # e.g. "fleet:standard"
print(estimate["vram_estimated_gb"])  # estimated VRAM required

for tier in estimate["tiers"]:
    if tier["fits"]:
        print(
            tier["tier"],
            f"{tier['estimated_minutes_min']:.0f}–{tier['estimated_minutes_max']:.0f} min",
            f"${tier['estimated_cost_min']:.2f}–${tier['estimated_cost_max']:.2f}",
        )

Each entry in tiers:

model.train(dataset, hardware, hyperparameters)

See the Training page for full details.

job = model.train(dataset, hardware="fleet:standard")

model.evaluate(dataset, hardware)

Run a forward-pass evaluation on a held-out dataset. No weights are updated. Returns loss and perplexity.

job = model.evaluate("./held-out.jsonl")
job.monitor()
results = job.eval_results()
print(results["loss"])        # e.g. 1.23
print(results["perplexity"])  # e.g. 3.42

The dataset must be a .jsonl file in the same format as your training data. Fleet runs a forward pass over every row and computes cross-entropy loss — no gradient updates occur.

model.deploy(hardware, workers_min, workers_max)

endpoint = model.deploy(hardware="fleet:economy")

model.download()

Returns presigned download URLs for all files in the model. URLs expire after 1 hour.

files = model.download()
for f in files:
    print(f["filename"], f["url"])

model.infer(prompt, max_tokens, temperature)

Proxy inference through the model's active deployment.

response = model.infer("Summarise this text:")

---

Datasets

client.datasets.upload(path, name=None)

Upload a .jsonl file to Fleet. Returns immediately if the same file was already uploaded (content-hash deduplication).

dataset = client.datasets.upload("./train.jsonl")
dataset = client.datasets.upload("./train.jsonl", name="my-dataset")

client.datasets.get(dataset_id)

dataset = client.datasets.get("dataset_abc123")

client.datasets.list(page, limit)

result = client.datasets.list()
for d in result["datasets"]:
    print(d["id"], d["name"])

Dataset object

client.datasets.delete(dataset_id)

client.datasets.delete("dataset_abc123")

dataset.download()

Returns a presigned download URL for this dataset. URL expires after 1 hour.

result = dataset.download()
print(result["url"])
print(result["size"])  # bytes

---

Jobs

client.jobs.get(job_id)

Retrieve a job by ID. Use this to reattach to a running job.

job = client.jobs.get("job_abc123")
job.monitor()

client.jobs.list()

jobs = client.jobs.list()
for job in jobs:
    print(job.id, job.status, job.hardware)

Job object

job.monitor(poll_interval, verbose)

Block until the job finishes. Streams a live progress bar with loss and learning rate.

job.monitor()                   # default: poll every 10s
job.monitor(verbose=True)       # also print all log lines
job.monitor(poll_interval=30)   # poll every 30s

Raises RuntimeError if the job fails.

job.logs()

for line in job.logs():
    print(line)

job.model()

Register and return the fine-tuned model produced by this job.

fine_tuned = job.model()

job.cancel()

job.cancel()

job.delete()

job.delete()

job.metrics()

Return the full training metrics series for this job.

data = job.metrics()
print(data["current_step"])
print(data["latest"])   # {'step': 100, 'loss': 2.34, 'lr': 1.38e-05, 'val_loss': None}

for point in data["metrics"]:
    print(point["step"], point["loss"])

The metrics array is ordered by step and safe to feed directly into a chart. val_loss is non-null when validation has run at that step.

job.eval_results()

Return evaluation results for a completed eval job. Raises if called on a training job.

results = job.eval_results()

job.refresh()

Re-fetch the job's status from the API.

job.refresh()
print(job.status)

---

Deployments

client.deployments.get(deployment_id)

endpoint = client.deployments.get("dep_abc123")

client.deployments.list()

deployments = client.deployments.list()
for d in deployments:
    print(d.id, d.status, d.hardware)

Deployment object

deployment.infer(prompt, max_tokens, temperature)

result = endpoint.infer("What is LoRA?")
result = endpoint.infer("Summarise:", max_tokens=512, temperature=0.5)

Blocks until the response is complete. Cold starts may take up to a minute.

deployment.delete()

endpoint.delete()

---

Account

client.billing()

Returns current balance and up to 3 recent transactions.

info = client.billing()
print(info["balance"])

client.transactions(page, limit)

result = client.transactions(page=1, limit=50)
for tx in result["transactions"]:
    print(tx["type"], tx["amount"])

client.overview()

Returns a dashboard summary: balance, active jobs, recent activity.

summary = client.overview()

client.settings()

Return current account settings.

settings = client.settings()
print(settings["max_checkpoints"])               # 1
print(settings["prune_checkpoints_on_completion"])  # True
print(settings["auto_recharge_enabled"])         # False
print(settings["auto_recharge_status"])          # "no_card"

client.update_settings(...)

Update account settings. All parameters are optional; only those provided are changed. Returns the updated settings object.

client.update_settings(max_checkpoints=5)
client.update_settings(prune_checkpoints_on_completion=False)
client.update_settings(
    auto_recharge_enabled=True,
    auto_recharge_threshold=5.0,
    auto_recharge_amount=25.0,
)

See the Billing page for details on auto-recharge and payment methods.

client.hardware()

Returns available hardware tiers and their pricing.

tiers = client.hardware()