Instructions to use pzarzycki/hrm-text-1b-code-tools-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use pzarzycki/hrm-text-1b-code-tools-sft with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://pzarzycki/hrm-text-1b-code-tools-sft") - KerasHub
How to use pzarzycki/hrm-text-1b-code-tools-sft with KerasHub:
import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://pzarzycki/hrm-text-1b-code-tools-sft") - Keras
How to use pzarzycki/hrm-text-1b-code-tools-sft with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://pzarzycki/hrm-text-1b-code-tools-sft") - Notebooks
- Google Colab
- Kaggle
Download training-loss.png from pzarzycki/hrm-text-1b-code-tools-sft: direct link, hf CLI and curl.
- Browser
- Download file 136 kB
-
https://huggingface.co/pzarzycki/hrm-text-1b-code-tools-sft/resolve/main/training-loss.png
- Command line
-
hf download hf://pzarzycki/hrm-text-1b-code-tools-sft/training-loss.png
-
curl -L -o training-loss.png https://huggingface.co/pzarzycki/hrm-text-1b-code-tools-sft/resolve/main/training-loss.png
136 kB

- Xet hash:
- f3fec9261f4cba9cad3d6d860ff37e5b268ee10c9d130fecc4438677da91187e
- Size of remote file:
- 136 kB
- SHA256:
- 15832813f10821a56045cfbf0dbcf7c3eddbacb0d7dda2bb7c1de56862c199c2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.