Instructions to use kerasformers/qwen2-7b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasFormers
How to use kerasformers/qwen2-7b-instruct with KerasFormers:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Keras
How to use kerasformers/qwen2-7b-instruct with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://kerasformers/qwen2-7b-instruct") - Notebooks
- Google Colab
- Kaggle
| { | |
| "metadata": { | |
| "total_size": 15231233024.0 | |
| }, | |
| "weight_map": { | |
| "/decoder_layers/qwen2_decoder_layer/attention/key/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer/attention/output_proj/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer/attention/query/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer/attention/value/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer/attention_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer/mlp/down/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer/mlp/gate/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer/mlp/up/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer/mlp_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_1/attention/key/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_1/attention/output_proj/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_1/attention/query/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_1/attention/value/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_1/attention_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_1/mlp/down/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_1/mlp/gate/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_1/mlp/up/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_1/mlp_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_2/attention/key/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_2/attention/output_proj/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_2/attention/query/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_2/attention/value/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_2/attention_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_2/mlp/down/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_2/mlp/gate/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_2/mlp/up/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_2/mlp_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_3/attention/key/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_3/attention/output_proj/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_3/attention/query/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_3/attention/value/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_3/attention_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_3/mlp/down/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_3/mlp/gate/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_3/mlp/up/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_3/mlp_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_4/attention/key/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_4/attention/output_proj/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_4/attention/query/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_4/attention/value/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_4/attention_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_4/mlp/down/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_4/mlp/gate/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_4/mlp/up/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_4/mlp_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_5/attention/key/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_5/attention/output_proj/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_5/attention/query/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_5/attention/value/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_5/attention_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_5/mlp/down/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_5/mlp/gate/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_5/mlp/up/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_5/mlp_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_6/attention/key/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_6/attention/output_proj/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_6/attention/query/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_6/attention/value/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_6/attention_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_6/mlp/down/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_6/mlp/gate/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_6/mlp/up/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_6/mlp_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_7/attention/key/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_7/attention/output_proj/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_7/attention/query/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_7/attention/value/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_7/attention_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_7/mlp/down/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_7/mlp/gate/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_7/mlp/up/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_7/mlp_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_8/attention/key/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_8/attention/output_proj/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_8/attention/query/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_8/attention/value/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_8/attention_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_8/mlp/down/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_8/mlp/gate/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_8/mlp/up/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_8/mlp_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_9/attention/key/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_9/attention/output_proj/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_9/attention/query/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_9/attention/value/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_9/attention_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_9/mlp/down/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_9/mlp/gate/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_9/mlp/up/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_9/mlp_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_10/attention/key/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_10/attention/output_proj/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_10/attention/query/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_10/attention/value/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_10/attention_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_10/mlp/down/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_10/mlp/gate/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_10/mlp/up/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_10/mlp_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_11/attention/key/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_11/attention/output_proj/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_11/attention/query/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_11/attention/value/vars": [ | |
| "model_00000.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_11/attention_norm/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_11/mlp/down/vars": "model_00000.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_11/mlp/gate/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_11/mlp/up/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_11/mlp_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_12/attention/key/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_12/attention/output_proj/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_12/attention/query/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_12/attention/value/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_12/attention_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_12/mlp/down/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_12/mlp/gate/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_12/mlp/up/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_12/mlp_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_13/attention/key/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_13/attention/output_proj/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_13/attention/query/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_13/attention/value/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_13/attention_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_13/mlp/down/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_13/mlp/gate/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_13/mlp/up/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_13/mlp_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_14/attention/key/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_14/attention/output_proj/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_14/attention/query/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_14/attention/value/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_14/attention_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_14/mlp/down/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_14/mlp/gate/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_14/mlp/up/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_14/mlp_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_15/attention/key/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_15/attention/output_proj/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_15/attention/query/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_15/attention/value/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_15/attention_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_15/mlp/down/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_15/mlp/gate/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_15/mlp/up/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_15/mlp_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_16/attention/key/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_16/attention/output_proj/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_16/attention/query/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_16/attention/value/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_16/attention_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_16/mlp/down/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_16/mlp/gate/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_16/mlp/up/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_16/mlp_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_17/attention/key/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_17/attention/output_proj/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_17/attention/query/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_17/attention/value/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_17/attention_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_17/mlp/down/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_17/mlp/gate/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_17/mlp/up/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_17/mlp_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_18/attention/key/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_18/attention/output_proj/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_18/attention/query/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_18/attention/value/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_18/attention_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_18/mlp/down/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_18/mlp/gate/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_18/mlp/up/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_18/mlp_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_19/attention/key/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_19/attention/output_proj/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_19/attention/query/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_19/attention/value/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_19/attention_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_19/mlp/down/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_19/mlp/gate/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_19/mlp/up/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_19/mlp_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_20/attention/key/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_20/attention/output_proj/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_20/attention/query/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_20/attention/value/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_20/attention_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_20/mlp/down/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_20/mlp/gate/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_20/mlp/up/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_20/mlp_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_21/attention/key/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_21/attention/output_proj/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_21/attention/query/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_21/attention/value/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_21/attention_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_21/mlp/down/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_21/mlp/gate/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_21/mlp/up/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_21/mlp_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_22/attention/key/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_22/attention/output_proj/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_22/attention/query/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_22/attention/value/vars": [ | |
| "model_00001.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_22/attention_norm/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_22/mlp/down/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_22/mlp/gate/vars": "model_00001.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_22/mlp/up/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_22/mlp_norm/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_23/attention/key/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_23/attention/output_proj/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_23/attention/query/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_23/attention/value/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_23/attention_norm/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_23/mlp/down/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_23/mlp/gate/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_23/mlp/up/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_23/mlp_norm/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_24/attention/key/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_24/attention/output_proj/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_24/attention/query/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_24/attention/value/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_24/attention_norm/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_24/mlp/down/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_24/mlp/gate/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_24/mlp/up/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_24/mlp_norm/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_25/attention/key/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_25/attention/output_proj/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_25/attention/query/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_25/attention/value/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_25/attention_norm/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_25/mlp/down/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_25/mlp/gate/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_25/mlp/up/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_25/mlp_norm/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_26/attention/key/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_26/attention/output_proj/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_26/attention/query/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_26/attention/value/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_26/attention_norm/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_26/mlp/down/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_26/mlp/gate/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_26/mlp/up/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_26/mlp_norm/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_27/attention/key/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_27/attention/output_proj/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_27/attention/query/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_27/attention/value/vars": [ | |
| "model_00002.weights.h5" | |
| ], | |
| "/decoder_layers/qwen2_decoder_layer_27/attention_norm/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_27/mlp/down/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_27/mlp/gate/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_27/mlp/up/vars": "model_00002.weights.h5", | |
| "/decoder_layers/qwen2_decoder_layer_27/mlp_norm/vars": "model_00002.weights.h5", | |
| "/final_norm/vars": "model_00002.weights.h5", | |
| "/layers/embedding/vars": "model_00002.weights.h5", | |
| "/layers/dense/vars": "model_00002.weights.h5" | |
| } | |
| } |