yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-11-04 03:40:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix code cell ordering

Browse Source
This commit is contained in:
rasbt 2024-08-12 19:04:05 -05:00
parent 76e6910a1a
commit 5f0c55ddee
No known key found for this signature in database
GPG Key ID: 3C6E5C7C075611DB
1 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
ch05/01_main-chapter-code/ch05.ipynb
View File

@ -1561,6 +1561,15 @@
"print(inverse_vocab[next_token_id])"
]
},
{
"cell_type": "markdown",
"id": "c63d0a27-830b-42b5-9986-6d1a7de04dd9",
"metadata": {},
"source": [
"- Instead of determining the most likely token via `torch.argmax`, we use `torch.multinomial(probas, num_samples=1)` to determine the most likely token by sampling from the softmax distribution\n",
"- For illustration purposes, let's see what happens when we sample the next token 1,000 times using the original softmax probabilities:"
]
},
{
"cell_type": "code",
"execution_count": 32,
@ -1593,15 +1602,6 @@
"print_sampled_tokens(probas)"
]
},
{
"cell_type": "markdown",
"id": "c63d0a27-830b-42b5-9986-6d1a7de04dd9",
"metadata": {},
"source": [
"- Instead of determining the most likely token via `torch.argmax`, we use `torch.multinomial(probas, num_samples=1)` to determine the most likely token by sampling from the softmax distribution\n",
"- For illustration purposes, let's see what happens when we sample the next token 1,000 times using the original softmax probabilities:"
]
},
{
"cell_type": "markdown",
"id": "32e7d9cf-a26d-4d9a-8664-4af1efa73832",