Skip to content

Nits in "Fine-tuning a Multilingual Reasoner with Hugging Face" recipe #1999

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 6, 2025
Merged

Nits in "Fine-tuning a Multilingual Reasoner with Hugging Face" recipe #1999

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 4 additions & 5 deletions articles/gpt-oss/fine-tune-transfomers.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -190,10 +190,10 @@
"source": [
"|||\n",
"| :---- | :--|\n",
"| `developer` | The developer message is used to provide custom instructions for the model (what we usually call the `system` role) |\n",
"| `user` | The user message is used to provide the input to the model |\n",
"| `developer` | The developer message is used to provide custom instructions for the model (what we usually call the `system` role). |\n",
"| `user` | The user message is used to provide the input to the model. |\n",
"| `assistant` | Output by the model which can either be a tool call or a message output. The output might also be associated with a particular “channel” identifying what the intent of the message is. |\n",
"| `analysis` | These are messages that are being used by the model for its chain-of thought |\n",
"| `analysis` | These are messages that are being used by the model for its chain-of-thought |\n",
"| `final` | Messages tagged in the final channel are messages intended to be shown to the end-user and represent the responses from the model. |\n",
"| `messages` | The list of messages that combine the content of the above to produce a full conversation. This is the input to the model. |"
]
Expand Down Expand Up @@ -345,7 +345,7 @@
"\n",
"To do so, we will use a technique called [LoRA](https://huggingface.co/learn/llm-course/chapter11/4) (Low-Rank Adaptation) to fine-tune the model. This technique allows us to tune a few specific layers of the model, which is particularly useful for large models like `openai/gpt-oss-20b`.\n",
"\n",
"First we need wrap the model as a `PeftModel` and define the LoRA configuration. We will use the `LoraConfig` class from the [PEFT library](https://github.com/huggingface/peft) to do this:"
"First we need to wrap the model as a `PeftModel` and define the LoRA configuration. We will use the `LoraConfig` class from the [PEFT library](https://github.com/huggingface/peft) to do this:"
]
},
{
Expand Down Expand Up @@ -604,7 +604,6 @@
"metadata": {},
"outputs": [],
"source": [
"\n",
"REASONING_LANGUAGE = \"Chinese\" # or Hindi, or any other language...\n",
"SYSTEM_PROMPT = f\"reasoning language: {REASONING_LANGUAGE}\"\n",
"USER_PROMPT = \"What is the national symbol of Canada?\"\n",
Expand Down