Instructions to use keras/mixtral_8_instruct_7b_en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/mixtral_8_instruct_7b_en with KerasHub:
import keras_hub # Load CausalLM model (optional: use half precision for inference) causal_lm = keras_hub.models.CausalLM.from_preset("hf://keras/mixtral_8_instruct_7b_en", dtype="bfloat16") causal_lm.compile(sampler="greedy") # (optional) specify a sampler # Generate text causal_lm.generate("Keras: deep learning for", max_length=64)import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/mixtral_8_instruct_7b_en") - Keras
How to use keras/mixtral_8_instruct_7b_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/mixtral_8_instruct_7b_en") - Notebooks
- Google Colab
- Kaggle
Download task.json from keras/mixtral_8_instruct_7b_en: direct link, hf CLI and curl.
- Browser
- Download file 2.94 kB
-
https://huggingface.co/keras/mixtral_8_instruct_7b_en/resolve/main/task.json
- Command line
-
hf download hf://keras/mixtral_8_instruct_7b_en/task.json
-
curl -L -o task.json https://huggingface.co/keras/mixtral_8_instruct_7b_en/resolve/main/task.json
2.94 kB
| { | |
| "module": "keras_hub.src.models.mixtral.mixtral_causal_lm", | |
| "class_name": "MixtralCausalLM", | |
| "config": { | |
| "backbone": { | |
| "module": "keras_hub.src.models.mixtral.mixtral_backbone", | |
| "class_name": "MixtralBackbone", | |
| "config": { | |
| "name": "mixtral_backbone", | |
| "trainable": true, | |
| "vocabulary_size": 32000, | |
| "num_layers": 32, | |
| "num_query_heads": 32, | |
| "hidden_dim": 4096, | |
| "intermediate_dim": 14336, | |
| "num_experts": 8, | |
| "top_k": 2, | |
| "router_jitter_noise": 0.0, | |
| "rope_max_wavelength": 1000000.0, | |
| "rope_scaling_factor": 1.0, | |
| "num_key_value_heads": 8, | |
| "router_aux_loss_coef": 0.02, | |
| "sliding_window": null, | |
| "layer_norm_epsilon": 1e-05, | |
| "dropout": 0 | |
| }, | |
| "registered_name": "keras_hub>MixtralBackbone" | |
| }, | |
| "preprocessor": { | |
| "module": "keras_hub.src.models.mixtral.mixtral_causal_lm_preprocessor", | |
| "class_name": "MixtralCausalLMPreprocessor", | |
| "config": { | |
| "name": "mixtral_causal_lm_preprocessor_2", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "float32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "tokenizer": { | |
| "module": "keras_hub.src.models.mixtral.mixtral_tokenizer", | |
| "class_name": "MixtralTokenizer", | |
| "config": { | |
| "name": "mixtral_tokenizer", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "int32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "config_file": "tokenizer.json", | |
| "proto": null, | |
| "sequence_length": null, | |
| "add_bos": false, | |
| "add_eos": false | |
| }, | |
| "registered_name": "keras_hub>MixtralTokenizer" | |
| }, | |
| "config_file": "preprocessor.json", | |
| "sequence_length": 1024, | |
| "add_start_token": true, | |
| "add_end_token": true | |
| }, | |
| "registered_name": "keras_hub>MixtralCausalLMPreprocessor" | |
| }, | |
| "name": "mixtral_causal_lm" | |
| }, | |
| "registered_name": "keras_hub>MixtralCausalLM" | |
| } |