Skip to content

add cuda support to test section and fix pipeline path #3

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

Open
MYusufY wants to merge 2 commits into
base: main
Choose a base branch
from
Open

add cuda support to test section and fix pipeline path #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7aae186
add cuda support to testing section and fix the output path issue
MYusufY Aug 27, 2025
14bfffc
fix my_qwen path
MYusufY Aug 27, 2025
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
18 changes: 7 additions & 11 deletions LLM Fine Tuning Workflow.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -527,7 +527,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"id": "71240af4-b792-4903-94c8-159936e3f14e",
"metadata": {},
"outputs": [
Expand Down Expand Up @@ -557,16 +557,20 @@
"source": [
"from transformers import AutoTokenizer, AutoModelForCausalLM\n",
"from peft import PeftModel, PeftConfig\n",
"import torch\n",
"\n",
"path = \"./my-qwen\"\n",
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
"\n",
"path = \"./my_qwen\"\n",
"\n",
"config = PeftConfig.from_pretrained(path)\n",
"base = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, trust_remote_code=True)\n",
"model = PeftModel.from_pretrained(base, path)\n",
"model = model.to(device)\n",
"\n",
"tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)\n",
"\n",
"inputs = tokenizer(\"Who is Mariya Sha?\", return_tensors=\"pt\").to(model.device)\n",
"inputs = tokenizer(\"Who is Mariya Sha?\", return_tensors=\"pt\").to(device)\n",
"\n",
"output = model.generate(\n",
" input_ids=inputs[\"input_ids\"], \n",
Expand All @@ -586,14 +590,6 @@
"The model officially knows that I am a wise and powerful wizard from Middle-earth! 😉\n",
"Fine tuning worked!!! "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9a3f139c-2380-4029-9bf6-103f6d79a5c5",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
Expand Down
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ Please note!! The `pipeline` code presented at the end of video (and in the last
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel, PeftConfig

path = "./my-qwen"
path = "./my_qwen"

config = PeftConfig.from_pretrained(path)
base = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, trust_remote_code=True)
Expand Down