Build and Upload Models | Clarifai Docs

Skip to main content

GPU Shortage?Make the most out of your GPUs with Compute Orchestration. Learn More

On this page

Build and import models, including from sources like Hugging Face

Upload Custom Models to Clarifai Platform using Python SDK - YouTube

Tap to unmute

Upload Custom Models to Clarifai Platform using Python SDK Clarifai

Clarifai1.93K subscribers

The Clarifai Python SDK allows you to upload custom models easily. Whether you're working with a pre-trained model from an external source like Hugging Face, or one you've built from scratch, Clarifai allows seamless integration of your models, enabling you to take advantage of the platform’s powerful capabilities.

Once imported to our platform, your model can be utilized alongside Clarifai's vast suite of AI tools. It will be automatically deployed and ready to be evaluated, combined with other models and agent operators in a workflow, or used to serve inference requests as it is.

Let’s walk through how to build and upload a custom model to the Clarifai platform. This example model appends the phrase Hello World to any input text and also supports streaming responses.

note

Explore this repository for examples on uploading different model types.

Step 1: Perform Prerequisites ​

Sign Up and Log In ​

Log in to your existing Clarifai account, or sign up for a new one. If you’re creating a new account, a default application will be provided for you.

Then authenticate using the CLI:

clarifai login

The CLI will prompt for your Personal Access Token (PAT) — find it in Settings > Secrets in the left sidebar. It will auto-detect your user ID and save everything locally. You can verify with clarifai whoami.

Note: Alternatively, you can set export CLARIFAI_PAT=YOUR_PAT_HERE as an environment variable, but clarifai login is the recommended approach since it also configures your user ID and app context.

Install Clarifai Package ​

Install the latest version of the clarifai Python package. This will also install the Clarifai Command Line Interface (CLI), which we'll use for testing and uploading the model.

 pip install --upgrade clarifai

Set Up Compute (For Manual Deploy Only) ​

One-Command Deploy

If you plan to use clarifai model deploy (recommended), you can skip this step entirely — the CLI automatically creates the compute cluster, nodepool, and deployment for you. See the Getting Started guide for the simplified flow.

If you prefer to manage compute infrastructure manually, your model requires a dedicated compute environment consisting of a cluster and a nodepool.

Note: A cluster is the foundation of your compute environment, while a nodepool is a single compute node or a group of nodes within a cluster that provides the resources your model requires.

Set Up Docker or a Virtual Environment ​

To test, run, and upload your model, you need to set up either a Docker container or a Python virtual environment. This ensures proper dependency management and prevents conflicts in your project.

Both options allow you to work with different Python versions. For example, you can use Python 3.11 for uploading one model and Python 3.12 for another — configured via the config.yaml file.

If Docker is installed on your system, it is highly recommended to use it for running the model. Docker provides better isolation and a fully portable environment, including for Python and system libraries.

You should ensure your local environment has sufficient memory and compute resources to handle model loading and execution, especially during testing.

Create Project Directory ​

tip

You can automatically generate the required files by running the clarifai model init command in the terminal from your current directory. After the files are created, you can modify them as needed.

Create a project directory and organize your files as indicated below to fit the requirements of uploading models to the Clarifai platform.

your_model_directory/
├── 1/
│   └── model.py
├── requirements.txt
└── config.yaml

Step 2: Build a Model ​

Let's talk about the general steps you'd follow to upload any type of model to the Clarifai platform.

Scaffold the Project With clarifai model init (Recommended) ​

The fastest way to start is to scaffold a complete model project — model.py, config.yaml, and requirements.txt — with one command. Pick a built-in toolkit for a common inference engine, or scaffold a blank Python template you can fill in:

# GPU LLM serving:
clarifai model init --toolkit vllm --model-name Qwen/Qwen3-0.6B
clarifai model init --toolkit sglang --model-name Qwen/Qwen3-0.6B
clarifai model init --toolkit huggingface --model-name bert-base-uncased

# Local LLM servers:
clarifai model init --toolkit ollama --model-name llama3.1
clarifai model init --toolkit lmstudio --model-name llama-3.2-3b-instruct

# Other use cases:
clarifai model init --toolkit mcp my-mcp-server         # MCP tool server
clarifai model init --toolkit openai my-openai-wrapper  # OpenAI-compatible wrapper

# Blank Python template:
clarifai model init my-model

Each toolkit pre-fills model.py with a working ModelClass implementation, config.yaml with reasonable compute defaults, and requirements.txt with the right dependencies. After scaffolding, you can run the model locally (Step 3), upload it (Step 4), and deploy it (Step 5) — often with no further code changes.

You can also clone an existing example from a GitHub URL with clarifai model init --github-url <url> — useful for starting from a known-good reference (see the runners-examples repo).

The rest of this step walks through model.py, config.yaml, and requirements.txt in detail — either as reference for what gets generated, or as a guide if you'd rather build everything from scratch.

Prepare model.py ​

The model.py file contains the core logic for your model, including how the model is loaded and how predictions are made. This file must define a custom class that inherits from ModelClass and implements the required methods.

This is the model.py file for the custom model we want to upload:

from clarifai.runners.models.model_class import ModelClass
from typing import Iterator

class MyModel(ModelClass):
  """A custom runner that adds "Hello World" to the end of the text."""

def load_model(self):
    """Load the model here."""

@ModelClass.method
  def predict(self, text1: str = "") -> str:
    """This is the method that will be called when the runner is run. It takes in an input and
    returns an output.
    """

output_text = text1 + " Hello World!"

return output_text

@ModelClass.method
  def generate(self, text1: str = "") -> Iterator[str]:
    """Example yielding a whole batch of streamed stuff back."""

for i in range(10):  # fake something iterating generating 10 times.
      output_text = text1 + f"Generate Hello World {i}"
      yield output_text

@ModelClass.method
  def stream(self, input_iterator: Iterator[str]) -> Iterator[str]:
    """Example yielding a whole batch of streamed stuff back."""

for i, input in enumerate(input_iterator):
      output_text = input + f"Stream Hello World {i}"
      yield output_text

Let’s break down what each part of the file does.

a. load_model Method ​

The load_model method is optional but recommended, as it prepares the model for inference by handling resource-heavy initializations. It is particularly useful for:

Here is an example:

def load_model(self):
  self.tokenizer = AutoTokenizer.from_pretrained("model/")
  self.pipeline = transformers.pipeline(...)

b. Prediction Methods ​

The model.py file must include at least one method decorated with @ModelClass.method to define the prediction endpoints.

In the example model we want to upload, we defined a method that appends the phrase Hello World to any input text and added support for different types of streaming responses.

Note: The structure of prediction methods on the client side directly mirrors the method signatures defined in your model.py file. This one-to-one mapping provides flexibility in defining prediction methods with varying names and arguments.

Here are some examples of method mapping:

model.py Model Implementation Client-Side Usage Pattern
@ModelClass.method def predict(...) model.predict(...)
@ModelClass.method def generate(...) model.generate(...)
@ModelClass.method def stream(...) model.stream(...)

You can learn more about the structure of prediction methods here.

Supported Input and Output Data Types

Each parameter in the class methods must be annotated with a type, and the return type must also be specified. Clarifai's model framework supports rich data typing for both inputs and outputs. Supported types include Text, Image, Audio, Video, and more.

Prepare config.yaml ​

The config.yaml file is essential for specifying the model’s metadata, compute resource requirements, and model checkpoints.

Simplified Config Format

When using clarifai model init --toolkit, the CLI generates a minimal config that works out of the box. Fields like user_id, app_id, and model_type_id are auto-filled from your CLI context at deploy time:

build_info:
  image: vllm/vllm-openai:latest
checkpoints:
  repo_id: Qwen/Qwen3-0.6B
  type: huggingface
  when: runtime
compute:
  instance: g4dn.xlarge
model:
  id: qwen3-06b

Use clarifai list-instances to browse available instance types, or clarifai model deploy --instance-info.

For a simpler end-to-end flow, use clarifai model deploy which handles both upload and deployment in one step.

This is the config.yaml file for the custom model we want to upload:

model:
  id: "my-uploaded-model"
  user_id: "YOUR_USER_ID_HERE"
  app_id: "YOUR_APP_ID_HERE"
  model_type_id: "text-to-text"

build_info:
  python_version: "3.11"
  # platform: "linux/amd64,linux/arm64"  # Optional: Specify target platform(s) for Docker image build

inference_compute_info:
  cpu_limit: "1"
  cpu_requests: "1"
  cpu_memory: "13Gi"
  cpu_memory_requests: "2Gi"
  num_accelerators: 1
  accelerator_type: ["NVIDIA-*"]
  accelerator_memory: "15Gi"

Let’s break down what each part of the file does.

Model Info ​

This section defines your unique model ID (any arbitrary name you choose), along with the Clarifai user ID and app ID you retrieved earlier. These values will determine where the model is uploaded on the Clarifai platform.

Note: If you reference an app that doesn’t exist, the CLI will prompt you to create it during the model upload process.

Build Info ​

This section specifies details about the environment used to build or run the model. You can include the python_version, which is useful for ensuring compatibility between the model and its runtime environment, as different Python versions may have varying dependencies, library support, and performance characteristics.

Note: We currently support Python 3.11 and Python 3.12 (default).

multi-architecture support

By default, Docker model images are built for the linux/amd64 architecture. If needed, you can provide a comma-separated list of additional target platforms to build a multi-architecture image.

Enabling multi-architecture builds allows the system to route requests to model-serving nodepools running on different hardware architectures (such as x86 or Arm).

During deployment configuration and request routing, the system automatically validates which node instance types are compatible with the model’s supported platforms.

This unified build process enhances cost efficiency and hardware flexibility. For example, you can build a single model version that works across multiple architectures, eliminating the need to maintain and manage separate model versions for each hardware type.

Note: You can also use the --platform flag when uploading a model to specify the target platform(s). This overrides any platform settings defined in your config.yaml.

# Specify multiple platforms
clarifai model upload --platform "linux/amd64,linux/arm64"

# Combine with other options
clarifai model upload --platform "linux/arm64" --stage upload

Compute Resources ​

To deploy your model on Clarifai’s dedicated compute, you must define the minimum compute resources required for running it, including CPU, memory, and optional GPU specifications.

Note: For local execution, the inference_compute_info section is optional — the model runs entirely on your machine using local CPU/GPU resources.

These are some parameters you can define:

Hugging Face Model Checkpoints ​

If you're using a model from Hugging Face, you can automatically download its checkpoints by specifying the appropriate configuration in this section.

For private or restricted Hugging Face repositories, make sure to include an access token. Learn how to generate one here.

See the additional examples below for how to define Hugging Face checkpoints.

checkpoints:
  type: "huggingface"
  repo_id: "meta-llama/Meta-Llama-3-8B-Instruct"
  when: "runtime"
  hf_token: "your_hf_token" # Required for private models

note

The when parameter in the checkpoints section determines when model checkpoints should be downloaded and stored. It must be set to one of the following options:

For larger models, we highly recommend downloading checkpoints at runtime. Doing so prevents unnecessary increases in Docker image size, which has some advantages:

Downloading checkpoints at build or upload time can significantly increase image size, resulting in longer upload times and increased cold start latency.

Model Concepts or Labels ​

This section is required if your model outputs concepts or labels and is not being directly loaded from Hugging Face. So, you must define a concepts section in the config.yaml file.

The following model types output concepts or labels:

Note: For visual-classifier and visual-detector models, you can now specify explicit concept IDs in config.yaml in addition to concept names. When concept IDs are defined, the platform uses them directly instead of auto-generating IDs from names. This ensures the concept IDs in your model's output_info match those returned in prediction outputs, preventing ID mismatches.

concepts:
  - id: '0'
    name: bus
  - id: '1'
    name: person
  - id: '2'
    name: bicycle
  - id: '3'
    name: car

note

If you're using a model from Hugging Face and the checkpoints section is defined, the Clarifai platform will automatically infer concepts. In this case, you don’t need to manually specify them.

Prepare requirements.txt ​

The requirements.txt file lists all the Python dependencies your model needs.

This is the requirements.txt file for the custom model we want to upload:

clarifai>=11.8.2

If your model requires Torch, we provide optimized pre-built Torch images as the base for machine learning and inference tasks.

These images include all necessary dependencies, ensuring efficient execution. The available pre-built Torch images are:

To use a specific Torch version, define it in your requirements.txt file like this:

torch==2.5.1

This ensures the correct pre-built image is pulled from Clarifai's container registry, ensuring the correct environment is used. This minimizes cold start times and speeds up model uploads and runtime execution — avoiding the overhead of building images from scratch or pulling and configuring them from external sources.

We recommend using either torch==2.5.1 or torch==2.4.1. If your model requires a different Torch version, you can specify it in requirements.txt, but this may slightly increase the model upload time.

Step 3: Test the Model Locally ​

Before uploading your model to the Clarifai platform, it's important to test it locally to catch any typos or misconfigurations in the code.

Learn how to run and test your models locally here.

Step 4: Upload the Model to Clarifai ​

Once your model is ready, you can upload it to the platform using Clarifai CLI.

To upload your model, run the following command in your terminal:

 clarifai model upload ./your/model/path/here

Alternatively, navigate to the directory containing your custom model and run the command without specifying the directory path:

 clarifai model upload

This command builds the model’s Docker image using the defined compute resources and uploads it to Clarifai, where it can be served in production. The build logs will be displayed in your terminal, which helps you troubleshoot any upload issues.

Note: If you make any changes to your model and upload it again to the Clarifai platform, a new version of the model will be created automatically.

note

Skip Dockerfile ​

By default, when you upload a model, the CLI automatically generates a Dockerfile in the root of your model directory. This ensures your model can be built and deployed with the correct environment.

In some cases, though, you may prefer to provide your own custom Dockerfile, such as when a specific base image is required for model inference.

To do this, use the --skip_dockerfile flag. This tells the CLI to skip automatic Dockerfile generation and instead rely on the one you’ve created.

clarifai model upload --skip_dockerfile

Automatically Generated Dockerfile Example

# syntax=docker/dockerfile:1.13-labs
FROM --platform=$TARGETPLATFORM public.ecr.aws/clarifai-models/python-base:3.11-42938da8e33b0f37ee7db16b83631da94c2348b9 as final

COPY --link requirements.txt /home/nonroot/requirements.txt

ENV VIRTUAL_ENV=/venv
ENV PATH="/home/nonroot/.local/bin:$VIRTUAL_ENV/bin:$PATH"

# Update clarifai package so we always have latest protocol to the API. Everything should land in /venv
RUN ["uv", "pip", "install", "--no-cache-dir", "-r", "/home/nonroot/requirements.txt"]
RUN ["uv", "pip", "show", "--no-cache-dir", "clarifai"]

# Set the NUMBA cache dir to /tmp
# Set the TORCHINDUCTOR cache dir to /tmp
# The CLARIFAI* will be set by the templaing system.
ENV NUMBA_CACHE_DIR=/tmp/numba_cache \
    TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_cache \
    HOME=/tmp \
    DEBIAN_FRONTEND=noninteractive

#####
# Copy the files needed to download
#####
# This creates the directory that HF downloader will populate and with nonroot:nonroot permissions up.
COPY --chown=nonroot:nonroot downloader/unused.yaml /home/nonroot/main/1/checkpoints/.cache/unused.yaml

#####
# Download checkpoints if config.yaml has checkpoints.when = "build"
COPY --link=true config.yaml /home/nonroot/main/
RUN ["python", "-m", "clarifai.cli", "model", "download-checkpoints", "/home/nonroot/main", "--out_path", "/home/nonroot/main/1/checkpoints", "--stage", "build"]
#####

# Copy in the actual files like config.yaml, requirements.txt, and most importantly 1/model.py
# for the actual model.
# If checkpoints aren't downloaded since a checkpoints: block is not provided, then they will
# be in the build context and copied here as well.
COPY --link=true 1 /home/nonroot/main/1
# At this point we only need these for validation in the SDK.
COPY --link=true requirements.txt config.yaml /home/nonroot/main/

# Add the model directory to the python path.
ENV PYTHONPATH=${PYTHONPATH}:/home/nonroot/main \
    CLARIFAI_PAT=${CLARIFAI_PAT} \
    CLARIFAI_USER_ID=${CLARIFAI_USER_ID} \
    CLARIFAI_RUNNER_ID=${CLARIFAI_RUNNER_ID} \
    CLARIFAI_NODEPOOL_ID=${CLARIFAI_NODEPOOL_ID} \
    CLARIFAI_COMPUTE_CLUSTER_ID=${CLARIFAI_COMPUTE_CLUSTER_ID} \
    CLARIFAI_API_BASE=${CLARIFAI_API_BASE:-https://api.clarifai.com}

# Finally run the clarifai entrypoint to start the runner loop and local runner server.
# Note(zeiler): we may want to make this a clarifai CLI call.
ENTRYPOINT ["python", "-m", "clarifai.runners.server"]
CMD ["--model_path", "/home/nonroot/main"]
#############################

Step 5: Deploy the Model ​

After your model is uploaded, you need to deploy it to make it available for inference.

One-Command Deploy

You can skip the separate upload and deploy steps entirely by using clarifai model deploy, which handles everything in one command — including auto-creating the compute infrastructure:

clarifai model deploy ./your-model --instance g5.xlarge

See the CLI deploy reference for all options.

Alternatively, after uploading with clarifai model upload, follow the on-screen prompts to:

Build Logs Example

clarifai model init
[INFO] 13:58:37.002093 Initializing model with default templates... |  thread=8349786304
Press Enter to continue...
[INFO] 13:58:39.866019 Created /Users/macbookpro/Desktop/code3/two/1/model.py |  thread=8349786304
[INFO] 13:58:39.866409 Created /Users/macbookpro/Desktop/code3/two/requirements.txt |  thread=8349786304
[INFO] 13:58:39.866669 Created /Users/macbookpro/Desktop/code3/two/config.yaml |  thread=8349786304
[INFO] 13:58:39.866717 Model initialization complete in /Users/macbookpro/Desktop/code3/two |  thread=8349786304
[INFO] 13:58:39.866755 Next steps: |  thread=8349786304
[INFO] 13:58:39.866789 1. Search for '# TODO: please fill in' comments in the generated files |  thread=8349786304
[INFO] 13:58:39.866822 2. Update the model configuration in config.yaml |  thread=8349786304
[INFO] 13:58:39.866853 3. Add your model dependencies to requirements.txt |  thread=8349786304
[INFO] 13:58:39.866883 4. Implement your model logic in 1/model.py |  thread=8349786304
clarifai model upload
[INFO] 14:05:28.366437 No checkpoints specified in the config file |  thread=8349786304
[INFO] 14:05:28.367158 Setup: Using Python version 3.11 from the config file to build the Dockerfile |  thread=8349786304
[INFO] 14:05:28.367434 Setup: Validating requirements.txt file at /Users/macbookpro/Desktop/code3/two/requirements.txt using uv pip compile |  thread=8349786304
[INFO] 14:08:20.832060 Setup: Requirements.txt file validated successfully |  thread=8349786304
[INFO] 14:08:20.832914 Setup: Linting Python files: ['/Users/macbookpro/Desktop/code3/two/1/model.py'] |  thread=8349786304
[INFO] 14:08:20.893378 Setup: Python code linted successfully, no errors found. |  thread=8349786304
[INFO] 14:08:20.893821 Setup: Using NVIDIA base image to build the Docker image and upload the model |  thread=8349786304
[INFO] 14:08:21.153133 New model will be created at https://clarifai.com/alfrick/my-models/models/friday20th-two with it's first version. |  thread=8349786304
Press Enter to continue...
[INFO] 14:08:30.795209 Uploading file... |  thread=6171717632
[INFO] 14:08:30.796342 Upload complete! |  thread=6171717632
Status: Upload done, Progress: 0% - Completed upload of files, initiating model version image build..  request_id: sdk-python-11.10.2-6a2Status: Model image is currently being built., Progress: 0% - Model version image is being built.  request_id: sdk-python-11.10.2-6a242da[INFO] 14:08:31.584822 Created Model Version ID: ffb9c659ead240b69a5f829b503e725d |  thread=8349786304
[INFO] 14:08:31.585337 Full url to that version is: https://clarifai.com/alfrick/my-models/models/friday20th-two |  thread=8349786304
[INFO] 14:08:38.535619 2025-11-20 11:08:33.133911 INFO: Downloading uploaded buildable from storage...
2025-11-20 11:08:33.966481 INFO: Done downloading buildable from storage
2025-11-20 11:08:33.969976 INFO: Extracting upload...
2025-11-20 11:08:33.975026 INFO: Done extracting upload
2025-11-20 11:08:33.977716 INFO: Parsing requirements file for buildable version ID ****829b503e725d
2025-11-20 11:08:34.004653 INFO: Dockerfile found at /shared/context/Dockerfile
cat: /shared/context/downloader/hf_token: No such file or directory
2025-11-20 11:08:34.748208 INFO: Setting up credentials
amazon-ecr-credential-helper
Version:    0.8.0
Git commit: ********
2025-11-20 11:08:34.753465 INFO: Building image...
#1 \[internal] load build definition from Dockerfile
#1 DONE 0.0s

#1 \[internal] load build definition from Dockerfile
#1 transferring dockerfile: 3.40kB done
#1 WARN: FromAsCasing: 'as' and 'FROM' keywords' casing do not match (line 7)
#1 DONE 0.0s

#2 resolve image config for docker-image://docker.io/docker/dockerfile:1.13-labs
#2 DONE 0.1s

#3 docker-image://docker.io/docker/dockerfile:1.13-labs@sha256:************18b8
#3 resolve docker.io/docker/dockerfile:1.13-labs@sha256:************18b8 done
#3 CACHED

#4 \[linux/arm64 internal] load metadata for public.ecr.aws/clarifai-models/python-base:3.11-********
#4 DONE 0.2s

#5 \[linux/amd64 internal] load metadata for public.ecr.aws/clarifai-models/python-base:3.11-********
#5 DONE 0.2s

#6 \[internal] load .dockerignore
#6 transferring context: 2B done
#6 DONE 0.0s

#7 \[internal] load build context
#7 transferring context: 2.73kB done
#7 DONE 0.0s

#8 \[linux/amd64 model-assets 1/8] FROM public.ecr.aws/clarifai-models/python-base:3.11-********@sha256:************48e5
#8 resolve public.ecr.aws/clarifai-models/python-base:3.11-********@sha256:************48e5 done
#8 CACHED

#9 \[linux/arm64 final 1/5] FROM public.ecr.aws/clarifai-models/python-base:3.11-********@sha256:************48e5
#9 resolve public.ecr.aws/clarifai-models/python-base:3.11-********@sha256:************48e5 done
#9 CACHED

#10 \[linux/arm64 final 2/5] COPY --link --chown=65532:65532 requirements.txt /home/nonroot/requirements.txt
#10 merging done
#10 DONE 0.0s

#11 \[linux/amd64 final 2/5] COPY --link --chown=65532:65532 requirements.txt /home/nonroot/requirements.txt
#11 merging done
#11 DONE 0.0s

#12 \[linux/amd64 final 3/5] RUN ["uv", "pip", "install", "--no-cache-dir", "-r", "/home/nonroot/requirements.txt"]
#12 0.071 Using Python 3.11.14 environment at: /venv
#12 0.518 Resolved 35 packages in 445ms
#12 0.525 Downloading grpcio (6.3MiB)
#12 0.529 Downloading pygments (1.2MiB)
#12 0.529 Downloading pydantic-core (1.9MiB)
#12 0.529 Downloading pillow (6.7MiB)
#12 0.530 Downloading aiohttp (1.7MiB)
#12 0.530 Downloading ruff (10.8MiB)
#12 0.530 Downloading numpy (16.1MiB)
#12 0.567 Downloading uv (17.0MiB)
#12 0.701  Downloading pydantic-core
#12 0.827  Downloading aiohttp
#12 1.010  Downloading ruff
#12 1.060  Downloading uv
#12 1.061  Downloading grpcio
#12 1.063  Downloading pillow
#12 1.096  Downloading pygments
#12 1.275  Downloading numpy
#12 1.275 Prepared 27 packages in 756ms
#12 1.276 Uninstalled 1 package in 0.91ms
#12 1.297 Installed 27 packages in 20ms
#12 1.297  + aiohappyeyeballs==2.6.1
#12 1.297  + aiohttp==3.13.2
#12 1.297  + aiosignal==1.4.0
#12 1.297  + attrs==25.4.0
#12 1.297  + charset-normalizer==3.4.4
#12 1.297  + clarifai==11.10.2
#12 1.297  + clarifai-grpc==11.10.5
#12 1.297  + clarifai-protocol==0.0.34
#12 1.297  + contextlib2==21.6.0
#12 1.297  + frozenlist==1.8.0
#12 1.297  + googleapis-common-protos==1.72.0
#12 1.297  + grpcio==1.76.0
#12 1.297  + multidict==6.7.0
#12 1.297  + numpy==2.3.5
#12 1.297  + pillow==12.0.0
#12 1.297  + propcache==0.4.1
#12 1.297  + protobuf==6.33.1
#12 1.297  + psutil==7.0.0
#12 1.297  + pydantic-core==2.33.2
#12 1.297  + pygments==2.19.2
#12 1.297  + requests==2.32.5
#12 1.297  + ruff==0.11.4
#12 1.297  + schema==0.7.5
#12 1.297  + tabulate==0.9.0
#12 1.297  + urllib3==2.5.0
#12 1.297  - uv==0.9.9
#12 1.297  + uv==0.7.12
#12 1.297  + yarl==1.22.0
#12 DONE 1.4s

#13 \[linux/amd64 final 4/5] RUN ["uv", "pip", "show", "--no-cache-dir", "clarifai"]
#13 0.081 Using Python 3.11.14 environment at: /venv
#13 0.084 Name: clarifai
#13 0.084 Version: 11.10.2
#13 0.084 Location: /venv/lib/python3.11/site-packages
#13 0.084 Requires: aiohttp, clarifai-grpc, clarifai-protocol, click, fsspec, numpy, packaging, pillow, psutil, pydantic-core, pygments, pyyaml, requests, ruff, schema, tabulate, tqdm, uv
#13 0.084 Required-by: clarifai-protocol
#13 DONE 0.1s

#14 \[linux/amd64 model-assets 2/8] RUN pip install --no-cache-dir clarifai==11.10.2 huggingface_hub
#14 0.837 Collecting clarifai==11.10.2
#14 0.902   Downloading clarifai-11.10.2-py3-none-any.whl.metadata (23 kB)
#14 0.911 Requirement already satisfied: huggingface_hub in /venv/lib/python3.11/site-packages (1.1.4)
#14 0.944 Collecting clarifai-grpc>=11.10.3 (from clarifai==11.10.2)
#14 0.948   Downloading clarifai_grpc-11.10.5-py3-none-any.whl.metadata (4.4 kB)
#14 0.989 Collecting clarifai-protocol>=0.0.33 (from clarifai==11.10.2)
#14 0.994   Downloading clarifai_protocol-0.0.34-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (14 kB)
#14 1.129 Collecting numpy>=1.22.0 (from clarifai==11.10.2)
#14 1.133   Downloading numpy-2.3.5-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (62 kB)
#14 1.150 Requirement already satisfied: tqdm>=4.65.0 in /venv/lib/python3.11/site-packages (from clarifai==11.10.2) (4.67.1)
#14 1.150 Requirement already satisfied: PyYAML>=6.0.1 in /venv/lib/python3.11/site-packages (from clarifai==11.10.2) (6.0.3)
#14 1.158 Collecting schema==0.7.5 (from clarifai==11.10.2)
#14 1.161   Downloading schema-0.7.5-py2.py3-none-any.whl.metadata (34 kB)
#14 1.282 Collecting Pillow>=9.5.0 (from clarifai==11.10.2)
#14 1.285   Downloading pillow-12.0.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (8.8 kB)
#14 1.315 Collecting tabulate>=0.9.0 (from clarifai==11.10.2)
#14 1.318   Downloading tabulate-0.9.0-py3-none-any.whl.metadata (34 kB)
#14 1.322 Requirement already satisfied: fsspec>=2024.6.1 in /venv/lib/python3.11/site-packages (from clarifai==11.10.2) (2025.10.0)
#14 1.323 Requirement already satisfied: click>=8.1.7 in /venv/lib/python3.11/site-packages (from clarifai==11.10.2) (8.3.0)
#14 1.338 Collecting requests>=2.32.3 (from clarifai==11.10.2)
#14 1.341   Downloading requests-2.32.5-py3-none-any.whl.metadata (4.9 kB)
#14 1.718 Collecting aiohttp>=3.10.0 (from clarifai==11.10.2)
#14 1.722   Downloading aiohttp-3.13.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (8.1 kB)
#14 1.869 Collecting uv==0.7.12 (from clarifai==11.10.2)
#14 1.875   Downloading uv-0.7.12-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (11 kB)
#14 2.137 Collecting ruff==0.11.4 (from clarifai==11.10.2) |  thread=8349786304
[INFO] 14:08:47.340894 #14 1.722   Downloading aiohttp-3.13.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (8.1 kB)
#14 1.869 Collecting uv==0.7.12 (from clarifai==11.10.2)
#14 1.875   Downloading uv-0.7.12-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (11 kB)
#14 2.137 Collecting ruff==0.11.4 (from clarifai==11.10.2)
#14 2.142   Downloading ruff-0.11.4-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (25 kB)
#14 2.188 Collecting psutil==7.0.0 (from clarifai==11.10.2)
#14 2.192   Downloading psutil-7.0.0-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (22 kB)
#14 2.206 Collecting pygments>=2.19.2 (from clarifai==11.10.2)
#14 2.209   Downloading pygments-2.19.2-py3-none-any.whl.metadata (2.5 kB)
#14 2.739 Collecting pydantic_core==2.33.2 (from clarifai==11.10.2)
#14 2.743   Downloading pydantic_core-2.33.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.8 kB)
#14 2.744 Requirement already satisfied: packaging==25.0 in /venv/lib/python3.11/site-packages (from clarifai==11.10.2) (25.0)
#14 2.746 Requirement already satisfied: typing-extensions!=4.7.0,>=4.6.0 in /venv/lib/python3.11/site-packages (from pydantic_core==2.33.2->clarifai==11.10.2) (4.15.0)
#14 2.753 Collecting contextlib2>=0.5.5 (from schema==0.7.5->clarifai==11.10.2)
#14 2.757   Downloading contextlib2-21.6.0-py2.py3-none-any.whl.metadata (4.1 kB)
#14 2.759 Requirement already satisfied: filelock in /venv/lib/python3.11/site-packages (from huggingface_hub) (3.20.0)
#14 2.760 Requirement already satisfied: hf-xet<2.0.0,>=1.2.0 in /venv/lib/python3.11/site-packages (from huggingface_hub) (1.2.0)
#14 2.760 Requirement already satisfied: httpx<1,>=0.23.0 in /venv/lib/python3.11/site-packages (from huggingface_hub) (0.28.1)
#14 2.761 Requirement already satisfied: shellingham in /venv/lib/python3.11/site-packages (from huggingface_hub) (1.5.4)
#14 2.762 Requirement already satisfied: typer-slim in /venv/lib/python3.11/site-packages (from huggingface_hub) (0.20.0)
#14 2.768 Requirement already satisfied: anyio in /venv/lib/python3.11/site-packages (from httpx<1,>=0.23.0->huggingface_hub) (4.11.0)
#14 2.768 Requirement already satisfied: certifi in /venv/lib/python3.11/site-packages (from httpx<1,>=0.23.0->huggingface_hub) (2025.11.12)
#14 2.768 Requirement already satisfied: httpcore==1.* in /venv/lib/python3.11/site-packages (from httpx<1,>=0.23.0->huggingface_hub) (1.0.9)
#14 2.769 Requirement already satisfied: idna in /venv/lib/python3.11/site-packages (from httpx<1,>=0.23.0->huggingface_hub) (3.11)
#14 2.770 Requirement already satisfied: h11>=0.16 in /venv/lib/python3.11/site-packages (from httpcore==1.*->httpx<1,>=0.23.0->huggingface_hub) (0.16.0)
#14 2.781 Collecting aiohappyeyeballs>=2.5.0 (from aiohttp>=3.10.0->clarifai==11.10.2)
#14 2.784   Downloading aiohappyeyeballs-2.6.1-py3-none-any.whl.metadata (5.9 kB)
#14 2.791 Collecting aiosignal>=1.4.0 (from aiohttp>=3.10.0->clarifai==11.10.2)
#14 2.794   Downloading aiosignal-1.4.0-py3-none-any.whl.metadata (3.7 kB)
#14 2.805 Collecting attrs>=17.3.0 (from aiohttp>=3.10.0->clarifai==11.10.2)
#14 2.809   Downloading attrs-25.4.0-py3-none-any.whl.metadata (10 kB)
#14 2.855 Collecting frozenlist>=1.1.1 (from aiohttp>=3.10.0->clarifai==11.10.2)
#14 2.859   Downloading frozenlist-1.8.0-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl.metadata (20 kB)
#14 3.011 Collecting multidict<7.0,>=4.5 (from aiohttp>=3.10.0->clarifai==11.10.2)
#14 3.015   Downloading multidict-6.7.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (5.3 kB)
#14 3.054 Collecting propcache>=0.2.0 (from aiohttp>=3.10.0->clarifai==11.10.2)
#14 3.058   Downloading propcache-0.4.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (13 kB)
#14 3.289 Collecting yarl<2.0,>=1.17.0 (from aiohttp>=3.10.0->clarifai==11.10.2)
#14 3.293   Downloading yarl-1.22.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (75 kB)
#14 3.643 Collecting grpcio>=1.53.2 (from clarifai-grpc>=11.10.3->clarifai==11.10.2)
#14 3.647   Downloading grpcio-1.76.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.metadata (3.7 kB)
#14 3.819 Collecting protobuf>=5.29.5 (from clarifai-grpc>=11.10.3->clarifai==11.10.2)
#14 3.824   Downloading protobuf-6.33.1-cp39-abi3-manylinux2014_x86_64.whl.metadata (593 bytes)
#14 3.836 Collecting googleapis-common-protos>=1.57.0 (from clarifai-grpc>=11.10.3->clarifai==11.10.2)
#14 3.840   Downloading googleapis_common_protos-1.72.0-py3-none-any.whl.metadata (9.4 kB)
#14 3.952 Collecting charset_normalizer<4,>=2 (from requests>=2.32.3->clarifai==11.10.2)
#14 3.956   Downloading charset_normalizer-3.4.4-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (37 kB)
#14 3.975 Collecting urllib3<3,>=1.21.1 (from requests>=2.32.3->clarifai==11.10.2)
#14 3.979   Downloading urllib3-2.5.0-py3-none-any.whl.metadata (6.5 kB)
#14 3.987 Requirement already satisfied: sniffio>=1.1 in /venv/lib/python3.11/site-packages (from anyio->httpx<1,>=0.23.0->huggingface_hub) (1.3.1)
#14 3.996 Downloading clarifai-11.10.2-py3-none-any.whl (306 kB)
#14 4.005 Downloading psutil-7.0.0-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (277 kB)
#14 4.014 Downloading pydantic_core-2.33.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.0 MB)
#14 4.043    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.0/2.0 MB 73.4 MB/s  0:00:00
#14 4.050 Downloading ruff-0.11.4-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.3 MB)
#14 4.111    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 11.3/11.3 MB 194.3 MB/s  0:00:00
#14 4.114 Downloading schema-0.7.5-py2.py3-none-any.whl (17 kB)
#14 4.121 Downloading uv-0.7.12-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.8 MB)
#14 4.182    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 17.8/17.8 MB 292.6 MB/s  0:00:00
#14 4.186 Downloading aiohttp-3.13.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (1.7 MB)
#14 4.195    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.7/1.7 MB 229.5 MB/s  0:00:00
#14 4.199 Downloading multidict-6.7.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (246 kB)
#14 4.204 Downloading yarl-1.22.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (365 kB)
#14 4.210 Downloading aiohappyeyeballs-2.6.1-py3-none-any.whl (15 kB)
#14 4.214 Downloading aiosignal-1.4.0-py3-none-any.whl (7.5 kB)
#14 4.218 Downloading attrs-25.4.0-py3-none-any.whl (67 kB)
#14 4.223 Downloading clarifai_grpc-11.10.5-py3-none-any.whl (305 kB)
#14 4.229 Downloading clarifai_protocol-0.0.34-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (409 kB)
#14 4.233 Downloading contextlib2-21.6.0-py2.py3-none-any.whl (13 kB)
#14 4.237 Downloading frozenlist-1.8.0-cp311-cp311-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl (231 kB)
#14 4.241 Downloading googleapis_common_protos-1.72.0-py3-none-any.whl (297 kB)
#14 4.245 Downloading protobuf-6.33.1-cp39-abi3-manylinux2014_x86_64.whl (323 kB)
#14 4.249 Downloading grpcio-1.76.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (6.6 MB)
#14 4.263    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 6.6/6.6 MB 491.7 MB/s  0:00:00
#14 4.267 Downloading numpy-2.3.5-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (16.9 MB)
#14 4.298    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 16.9/16.9 MB 559.0 MB/s  0:00:00
#14 4.302 Downloading pillow-12.0.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (7.0 MB)
#14 4.331    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7.0/7.0 MB 253.1 MB/s  0:00:00
#14 4.335 Downloading propcache-0.4.1-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (210 kB)
#14 4.339 Downloading pygments-2.19.2-py3-none-any.whl (1.2 MB)
#14 4.342    ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.2/1.2 MB 713.1 MB/s  0:00:00
#14 4.345 Downloading requests-2.32.5-py3-none-any.whl (64 kB)
#14 4.349 Downloading charset_normalizer-3.4.4-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (151 kB)
#14 4.352 Downloading urllib3-2.5.0-py3-none-any.whl (129 kB)
#14 4.356 Downloading tabulate-0.9.0-py3-none-any.whl (35 kB)
#14 4.489 Installing collected packages: uv, urllib3, tabulate, ruff, pygments, pydantic_core, psutil, protobuf, propcache, Pillow, numpy, multidict, grpcio, frozenlist, contextlib2, charset_normalizer, attrs, aiohappyeyeballs, yarl, schema, requests, googleapis-common-protos, aiosignal, clarifai-grpc, aiohttp, clarifai-protocol, clarifai
#14 4.489   Attempting uninstall: uv
#14 4.490     Found existing installation: uv 0.9.9
#14 4.492     Uninstalling uv-0.9.9:
#14 4.495       Successfully uninstalled uv-0.9.9 |  thread=8349786304
[INFO] 14:08:50.414074 #14 7.989 8s)
#14 7.991 Successfully installed Pillow-12.0.0 aiohappyeyeballs-2.6.1 aiohttp-3.13.2 aiosignal-1.4.0 attrs-25.4.0 charset_normalizer-3.4.4 clarifai-11.10.2 clarifai-grpc-11.10.5 clarifai-protocol-0.0.34 contextlib2-21.6.0 frozenlist-1.8.0 googleapis-common-protos-1.72.0 grpcio-1.76.0 multidict-6.7.0 numpy-2.3.5 propcache-0.4.1 protobuf-6.33.1 psutil-7.0.0 pydantic_core-2.33.2 pygments-2.19.2 requests-2.32.5 ruff-0.11.4 schema-0.7.5 tabulate-0.9.0 urllib3-2.5.0 uv-0.7.12 yarl-1.22.0
#14 ...

#15 \[linux/arm64 final 3/5] RUN ["uv", "pip", "install", "--no-cache-dir", "-r", "/home/nonroot/requirements.txt"]
#15 1.183 Using Python 3.11.14 environment at: /venv
#15 3.871 Resolved 35 packages in 2.59s
#15 3.954 Downloading aiohttp (1.7MiB)
#15 3.975 Downloading pygments (1.2MiB)
#15 3.981 Downloading uv (15.8MiB)
#15 3.983 Downloading ruff (9.9MiB)
#15 3.984 Downloading pydantic-core (1.8MiB)
#15 3.987 Downloading grpcio (6.1MiB)
#15 3.990 Downloading pillow (6.1MiB)
#15 3.991 Downloading numpy (13.9MiB)
#15 5.116  Downloading pydantic-core
#15 5.649  Downloading aiohttp
#15 6.918  Downloading ruff
#15 7.099  Downloading uv
#15 7.131  Downloading pillow
#15 7.143  Downloading grpcio
#15 7.277  Downloading pygments
#15 8.094  Downloading numpy
#15 8.096 Prepared 27 packages in 4.21s
#15 8.108 Uninstalled 1 package in 10ms
#15 8.232 Installed 27 packages in 124ms
#15 8.236  + aiohappyeyeballs==2.6.1
#15 8.236  + aiohttp==3.13.2
#15 8.236  + aiosignal==1.4.0
#15 8.236  + attrs==25.4.0
#15 8.236  + charset-normalizer==3.4.4
#15 8.236  + clarifai==11.10.2
#15 8.236  + clarifai-grpc==11.10.5
#15 8.237  + clarifai-protocol==0.0.34
#15 8.237  + contextlib2==21.6.0
#15 8.237  + frozenlist==1.8.0
#15 8.237  + googleapis-common-protos==1.72.0
#15 8.237  + grpcio==1.76.0
#15 8.237  + multidict==6.7.0
#15 8.237  + numpy==2.3.5
#15 8.237  + pillow==12.0.0
#15 8.237  + propcache==0.4.1
#15 8.238  + protobuf==6.33.1
#15 8.238  + psutil==7.0.0
#15 8.238  + pydantic-core==2.33.2
#15 8.238  + pygments==2.19.2
#15 8.238  + requests==2.32.5
#15 8.238  + ruff==0.11.4
#15 8.238  + schema==0.7.5
#15 8.238  + tabulate==0.9.0
#15 8.238  + urllib3==2.5.0
#15 8.239  - uv==0.9.9
#15 8.239  + uv==0.7.12
#15 8.239  + yarl==1.22.0
#15 DONE 8.4s

#14 \[linux/amd64 model-assets 2/8] RUN pip install --no-cache-dir clarifai==11.10.2 huggingface_hub
#14 DONE 8.5s

#16 \[linux/arm64 final 4/5] RUN ["uv", "pip", "show", "--no-cache-dir", "clarifai"]
#16 ...

#17 \[linux/amd64 model-assets 3/8] WORKDIR /home/nonroot/main
#17 DONE 0.0s

#18 \[linux/amd64 model-assets 4/8] COPY --link downloader/unused.yaml /home/nonroot/main/1/checkpoints/.cache/unused.yaml
#18 DONE 0.0s

#19 \[linux/amd64 model-assets 5/8] COPY --link config.yaml /home/nonroot/main/
#19 merging done
#19 DONE 0.0s

#20 \[linux/amd64 model-assets 6/8] RUN  ["python", "-m", "clarifai.cli", "model", "download-checkpoints", "/home/nonroot/main", "--out_path", "/home/nonroot/main/1/checkpoints", "--stage", "build"]
#20 0.216 [WARNING] 11:08:43.952582 Could not write configuration to disk. Could be a read only file system. |  thread=140436804668992
#20 0.546 [WARNING] 11:08:44.282684 Config file /home/nonroot/.config/clarifai/config not found, using default config. Run 'clarifai config' on the command line to create a config file. |  thread=140436804668992
#20 0.546 [WARNING] 11:08:44.282803 Config file /home/nonroot/.config/clarifai/config not found, using default config. Run 'clarifai config' on the command line to create a config file. |  thread=140436804668992
#20 0.546 [INFO] 11:08:44.282943 No checkpoints specified in the config file |  thread=140436804668992
#20 DONE 0.6s

#21 \[linux/amd64 model-assets 7/8] COPY --link 1 /home/nonroot/main/1
#21 DONE 0.0s

#22 \[linux/amd64 model-assets 8/8] COPY --link requirements.txt /home/nonroot/main/
#22 merging 0.0s done
#22 DONE 0.0s

#16 \[linux/arm64 final 4/5] RUN ["uv", "pip", "show", "--no-cache-dir", "clarifai"]
#16 ...

#23 \[linux/amd64 final 5/5] COPY --link --chown=65532:65532 --from=model-assets /home/nonroot/main /home/nonroot/main
#23 DONE 0.0s

#16 \[linux/arm64 final 4/5] RUN ["uv", "pip", "show", "--no-cache-dir", "clarifai"]
#16 1.031 Using Python 3.11.14 environment at: /venv
#16 1.079 Name: clarifai
#16 1.079 Version: 11.10.2
#16 1.079 Location: /venv/lib/python3.11/site-packages
#16 1.079 Requires: aiohttp, clarifai-grpc, clarifai-protocol, click, fsspec, numpy, packaging, pillow, psutil, pydantic-core, pygments, pyyaml, requests, ruff, schema, tabulate, tqdm, uv
#16 1.080 Required-by: clarifai-protocol
#16 DONE 1.1s

#24 \[linux/arm64 final 5/5] COPY --link --chown=65532:65532 --from=model-assets /home/nonroot/main /home/nonroot/main
#24 DONE 0.0s

#25 exporting to image
#25 exporting layers |  thread=8349786304
[INFO] 14:08:54.513161 #25 exporting layers 6.6s done
#25 exporting manifest sha256:************7702 done
#25 exporting config sha256:************62fc done
#25 exporting manifest sha256:************1f5e done
#25 exporting config sha256:************4138 done
#25 exporting manifest list sha256:************f85a done
#25 pushing layers
#25 ...

#26 \[auth] sharing credentials for 891377382885.dkr.ecr.us-east-1.amazonaws.com
#26 DONE 0.0s

#25 exporting to image |  thread=8349786304
[INFO] 14:08:58.587380 #25 pushing layers 2.7s done
#25 pushing manifest for ****/prod/pytorch:****829b503e725d@sha256:************f85a
#25 pushing manifest for ****/prod/pytorch:****829b503e725d@sha256:************f85a 1.0s done
#25 DONE 10.3s
2025-11-20 11:08:55.012710 INFO: Done building image!!! |  thread=8349786304
[INFO] 14:08:58.588026 Model build complete! |  thread=8349786304
[INFO] 14:08:58.588121 Build time elapsed 27.0s) |  thread=8349786304
[INFO] 14:08:58.588216 Check out the model at https://clarifai.com/alfrick/my-models/models/friday20th-two version: ffb9c659ead240b69a5f829b503e725d |  thread=8349786304
[INFO] 14:08:58.640505

XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
# Here is a code snippet to use this model:
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
                 |  thread=8349786304
[INFO] 14:08:58.640586 # Clarifai Model Client Script
# Set the environment variables `CLARIFAI_DEPLOYMENT_ID` and `CLARIFAI_PAT` to run this script.
# Example usage:
import os

from clarifai.client import Model
from clarifai.runners.utils import data_types

model = Model(
    "https://clarifai.com/alfrick/my-models/models/friday20th-two",
    deployment_id=os.environ.get("CLARIFAI_DEPLOYMENT_ID", None),  # Only needed for dedicated deployed models
    deployment_user_id=os.environ.get("CLARIFAI_DEPLOYMENT_USER_ID", None),  # Organization or user ID for deployment/nodepool
)

# Example model prediction from different model methods:

response = model.predict(
    text1="What is the future of AI?",
)
print(response)

response = model.generate(
    text1="What is the future of AI?",
)
for res in response:
    print(res)

response = model.stream(
    input_iterator=iter(['What is the future of AI?']),
)
 |  thread=8349786304
[INFO] 14:08:58.640757

XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
                 |  thread=8349786304

🔶 Do you want to deploy the model? [Y/n]: y

🚀 Model Deployment

🖥️  Available Compute Clusters:
1. advanced-cluster-au64  –  No description
Select compute cluster (number): 1

📦  Available Nodepools:
1. advanced-nodepool-ncz5  –  No description
Select nodepool (number): 1

⌨️  Enter Deployment Configuration:
Enter deployment ID [deploy-friday20th-two-b74f6d]:
Enter minimum replicas [1]: 1
Enter maximum replicas [5]: 5

⏳ Deploying model...
[INFO] 14:15:25.845466 Deployment with ID 'deploy-friday20th-two-b74f6d' is created:
code: SUCCESS
description: "Ok"
req_id: "sdk-python-11.10.2-26228389300b4ecb822cd801d35ef19b"
 |  thread=8349786304
✅ Deployment 'deploy-friday20th-two-b74f6d' successfully created for model 'friday20th-two' with version 'ffb9c659ead240b69a5f829b503e725d'.
Model deployed successfully! You can test it now.

🗑️ Do you want to backtrack and clean up? [Y/n]: y

🔄 Starting backtrack process...
Do you want to delete the deployment? [Y/n]: n
Do you want to delete the model version? [y/N]: n

Step 6: Predict With Model ​

Once the model is successfully deployed, you can generate predictions either programmatically or through the UI Playground.

Unary-Unary Predict Call ​

You can make a unary-unary predict call using the model.

from clarifai.client import Model
import os

# Set PAT as an environment variable
#   export CLARIFAI_PAT=YOUR_PAT_HERE # Unix-Like Systems
#   set CLARIFAI_PAT=YOUR_PAT_HERE  # Windows
# Also set CLARIFAI_DEPLOYMENT_ID as an environment variable

# Initialize with your model URL
model = Model(
    url="https://clarifai.com/user-id/app-id/models/model-id",
    deployment_id=os.environ.get("CLARIFAI_DEPLOYMENT_ID", None),
    )

for response in model.predict("Yes, I uploaded it! "):
    print(response)

Example Output

Y
e
s
,

I

u
p
l
o
a
d
e
d

i
t
!

H
e
l
l
o

W
o
r
l
d
!

Unary-Stream Predict Call ​

You can make a unary-stream predict call using the model.

from clarifai.client import Model
import os

for response in model.generate("Yes, I uploaded it! "):
    print(response)

Example Output

Yes, I uploaded it! Generate Hello World 0
Yes, I uploaded it! Generate Hello World 1
Yes, I uploaded it! Generate Hello World 2
Yes, I uploaded it! Generate Hello World 3
Yes, I uploaded it! Generate Hello World 4
Yes, I uploaded it! Generate Hello World 5
Yes, I uploaded it! Generate Hello World 6
Yes, I uploaded it! Generate Hello World 7
Yes, I uploaded it! Generate Hello World 8
Yes, I uploaded it! Generate Hello World 9

Additional Examples ​

tip

You can find various up-to-date model upload examples here, which demonstrate different use cases and optimizations. Here is an example of how to download a model: clarifai model init --github-url https://github.com/Clarifai/runners-examples/tree/main/local-runners/ollama-model-upload.

Build your next AI app, test and tune popular LLMs models, and much more.

Get started for free