Models and Model Versions

from truefoundry.ml import get_client
  
client = get_client()
model_version = client.log_model(
    ml_repo="name-of-the-ml-repo",
    name="name-for-the-model",
    model_file_or_folder="path/to/model/file/or/folder/on/disk",
    framework=<None or Framework object (see below)>
)

from truefoundry.ml import get_client, SklearnFramework, infer_signature

import joblib
import numpy as np
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC

X = np.array([[-1, -1], [-2, -1], [1, 1], [2, 1]])
y = np.array([1, 1, 2, 2])
clf = make_pipeline(StandardScaler(), SVC(gamma='auto'))
clf.fit(X, y)
joblib.dump(clf, "sklearn-pipeline.joblib")

client = get_client()
client.create_ml_repo(  # This is only required once
     name="my-classification-project",
     # This controls which bucket is used.
     # You can get this from Integrations > Blob Storage.
     storage_integration_fqn='<storage_integration_fqn>'
)
model_version = client.log_model(
     ml_repo="my-classification-project",
     name="my-sklearn-model",
     description="A simple sklearn pipeline",
     model_file_or_folder="sklearn-pipeline.joblib",
     framework=SklearnFramework(),
     metadata={"accuracy": 0.99, "f1": 0.80},
)
print(model_version.fqn)

import os
import shutil

from truefoundry.ml import get_client, TransformersFramework
from huggingface_hub import snapshot_download

MODEL_ID = "HuggingFaceTB/SmolLM2-135M"   # Model Id from huggingface hub
PIPELINE_TAG = "text-generation"          # Task the model is trained for
LOCAL_PATH = "./transformers-model"       # Path for local download

snapshot_download(
    MODEL_ID,
    revision=None,
    cache_dir=None,
    local_dir=LOCAL_PATH,
    ignore_patterns=["*.h5", "*.ot", "pytorch_model*.bin"],
    local_dir_use_symlinks=False,
)

if os.path.exists(os.path.join(LOCAL_PATH, '.cache')):
    shutil.rmtree(os.path.join(LOCAL_PATH, '.cache'))


ML_REPO = "my-llm-project"         # ML Repo to upload to
MODEL_NAME = "smollm2-135m"        # Model Name to upload as

client = get_client()
model_version = client.log_model(
    ml_repo=ML_REPO,
    name=MODEL_NAME,
    model_file_or_folder=LOCAL_PATH,
    framework=TransformersFramework(
        pipeline_tag=PIPELINE_TAG
    ),
)
print(model_version.fqn)

import os
import tempfile
import joblib
from truefoundry.ml import get_client

client = get_client()
model_version = client.get_model_version_by_fqn(
     fqn="model:truefoundry/my-classification-project/my-sklearn-model:1"
)

# Download the model to disk
temp = tempfile.TemporaryDirectory()
download_info = model_version.download(path=temp.name)
print(download_info.model_dir)

# Deserialize and Load
model = joblib.load(
     os.path.join(download_info.model_dir, "sklearn-pipeline.joblib")
)

import torch
from transformers import pipeline
from truefoundry.ml import get_client

client = get_client()
model_version = client.get_model_version_by_fqn(
     fqn="model:truefoundry/my-llm-project/my-transformers-model:1"
)
# Download the model to disk
temp = tempfile.TemporaryDirectory()
download_info = model_version.download(path=temp.name)
print(download_info.model_dir)

# Deserialize and Load
pln = pipeline("text-generation", model=download_info.model_dir, torch_dtype=torch.float16)s

from truefoundry.ml import get_client, SklearnFramework


client = get_client()
model_version = client.get_model_version_by_fqn(
    "model:truefoundry/my-classification-project/my-sklearn-model:1"
)
model_version.description = "This is my updated description"
model_version.metadata = {"accuracy": 0.98, "f1": 0.85}
model_version.framework = SklearnFramework(
    model_filepath="sklearn-pipeline.joblib",
    serialization_format="joblib"
)
# Updates the model fields for existing model version.
model_version.update()