Created
July 15, 2024 00:14
-
-
Save joelburget/fd18a958add96a108a0455633da2e1aa to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"execution_count": 16, | |
"id": "b0374368-eb08-4ceb-8c8e-c8f409aa7213", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"import torch\n", | |
"from transformers import AutoModel" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 2, | |
"id": "94c38ffa-afbf-4056-a0f0-9015a3e18fc9", | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"application/vnd.jupyter.widget-view+json": { | |
"model_id": "4a33d7f3c8534fdb9f59d733343101b9", | |
"version_major": 2, | |
"version_minor": 0 | |
}, | |
"text/plain": [ | |
"Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]" | |
] | |
}, | |
"metadata": {}, | |
"output_type": "display_data" | |
} | |
], | |
"source": [ | |
"hf_model = AutoModel.from_pretrained(\"joelb/Mixtral-8x7B-1l\")" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 17, | |
"id": "090a1f47-a067-4c0d-ba1a-a50db075957c", | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"w = hf_model.layers[0].block_sparse_moe.experts[0].w3.weight\n", | |
"w2 = w.T.contiguous().T\n", | |
"i = torch.randn(3, 4096)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 18, | |
"id": "32aad9b4-9b9b-4f96-9222-450e0c3789f6", | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"tensor(False)" | |
] | |
}, | |
"execution_count": 18, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"torch.all(i @ w.T == i @ w2.T)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 19, | |
"id": "ddabe036-b8e6-486e-8fd9-ca2d6eabf195", | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"((4096, 1), (1, 14336))" | |
] | |
}, | |
"execution_count": 19, | |
"metadata": {}, | |
"output_type": "execute_result" | |
} | |
], | |
"source": [ | |
"w.stride(), w2.stride()" | |
] | |
} | |
], | |
"metadata": { | |
"kernelspec": { | |
"display_name": "Python 3 (ipykernel)", | |
"language": "python", | |
"name": "python3" | |
}, | |
"language_info": { | |
"codemirror_mode": { | |
"name": "ipython", | |
"version": 3 | |
}, | |
"file_extension": ".py", | |
"mimetype": "text/x-python", | |
"name": "python", | |
"nbconvert_exporter": "python", | |
"pygments_lexer": "ipython3", | |
"version": "3.11.9" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 5 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment