books/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2026-04-10 12:33:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

Dpo vocab size clarification (#628)

Browse Source 
* Llama3 from scratch improvements

* vocab size should be 50257 not 50256

* restore
This commit is contained in:
Sebastian Raschka
2025-04-18 17:20:56 -05:00
committed by GitHub
parent 3eca919a52
commit ec062e1099
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ch07/04_preference-tuning-with-dpo/dpo-from-scratch.ipynb
View File

@@ -2140,7 +2140,7 @@
},
"source": [
"- In other words, `torch.gather` is a selection function\n",
"- When we computed the loss earlier, we used it to retrieve the log probabilities corresponding to the correct token in the 50,256-token vocabulary\n",
"- When we computed the loss earlier, we used it to retrieve the log probabilities corresponding to the correct token in the 50,257-token vocabulary\n",
"- The \"correct\" tokens are the tokens given in the response entry"
]
},
@@ -3112,7 +3112,7 @@
"provenance": []
},
"kernelspec": {
"display_name": ".venv",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@@ -3126,7 +3126,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.6"
"version": "3.10.16"
}
},
"nbformat": 4,