Instructions to use Delower/molmistral-foundation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use Delower/molmistral-foundation 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://Delower/molmistral-foundation") - Notebooks
- Google Colab
- Kaggle
Download gate_scan.json from Delower/molmistral-foundation: direct link, hf CLI and curl.
- Browser
- Download file 560 Bytes
-
https://huggingface.co/Delower/molmistral-foundation/resolve/main/gate_scan.json
- Command line
-
hf download hf://Delower/molmistral-foundation/gate_scan.json
-
curl -L -o gate_scan.json https://huggingface.co/Delower/molmistral-foundation/resolve/main/gate_scan.json
560 Bytes
| { | |
| "weights_file": "/home/hatch/workspace/foundation_llm/job794_weights/archive/best_foundation_bundle.keras", | |
| "size_bytes": 611953638, | |
| "vocab_size": 621, | |
| "load_ok": true, | |
| "n_params": 21831680, | |
| "weight_scan": { | |
| "n_tensors": 112, | |
| "n_values": 21831680, | |
| "n_nonfinite": 2, | |
| "bad_tensors": [ | |
| { | |
| "name": "embeddings", | |
| "shape": [ | |
| 621, | |
| 512 | |
| ], | |
| "n_nonfinite": 2 | |
| } | |
| ] | |
| }, | |
| "eval_256": { | |
| "loss": 0.272176057100296, | |
| "accuracy": 0.2651774287223816, | |
| "n_rows": 256 | |
| } | |
| } |