Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

keras
/
devstral_small_2_24b_instruct_2512_en

Text Generation
KerasHub
Model card Files Files and versions
xet
Community

Instructions to use keras/devstral_small_2_24b_instruct_2512_en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • KerasHub

    How to use keras/devstral_small_2_24b_instruct_2512_en with KerasHub:

    import keras_hub
    
    # Create a MistralCausalLM model
    task = keras_hub.models.MistralCausalLM.from_preset("hf://keras/devstral_small_2_24b_instruct_2512_en")
    
    import keras_hub
    
    # Create a Backbone model unspecialized for any task
    backbone = keras_hub.models.Backbone.from_preset("hf://keras/devstral_small_2_24b_instruct_2512_en")
    
  • Keras

    How to use keras/devstral_small_2_24b_instruct_2512_en 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://keras/devstral_small_2_24b_instruct_2512_en")
    
  • Notebooks
  • Google Colab
  • Kaggle
devstral_small_2_24b_instruct_2512_en
48.9 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
laxmareddyp's picture
laxmareddyp
Update README.md with new model card content
476c4f9 verified about 19 hours ago
  • assets
    Upload folder using huggingface_hub about 20 hours ago
  • .gitattributes
    1.52 kB
    initial commit about 20 hours ago
  • README.md
    7.95 kB
    Update README.md with new model card content about 19 hours ago
  • config.json
    3.19 kB
    Upload folder using huggingface_hub about 20 hours ago
  • image_converter.json
    1.29 kB
    Upload folder using huggingface_hub about 20 hours ago
  • metadata.json
    198 Bytes
    Upload folder using huggingface_hub about 20 hours ago
  • model.weights.json
    74.3 kB
    Upload folder using huggingface_hub about 20 hours ago
  • model_00000.weights.h5
    10.7 GB
    xet
    Upload folder using huggingface_hub about 20 hours ago
  • model_00001.weights.h5
    10.4 GB
    xet
    Upload folder using huggingface_hub about 20 hours ago
  • model_00002.weights.h5
    10.7 GB
    xet
    Upload folder using huggingface_hub about 20 hours ago
  • model_00003.weights.h5
    10.4 GB
    xet
    Upload folder using huggingface_hub about 20 hours ago
  • model_00004.weights.h5
    6.67 GB
    xet
    Upload folder using huggingface_hub about 20 hours ago
  • preprocessor.json
    40.3 kB
    Upload folder using huggingface_hub about 20 hours ago
  • task.json
    53.2 kB
    Upload folder using huggingface_hub about 20 hours ago
  • tokenizer.json
    29.7 kB
    Upload folder using huggingface_hub about 20 hours ago