Skip to content
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

update links to reflect new naming #96

Merged
merged 1 commit into from
Aug 1, 2024
Merged

update links to reflect new naming #96

Show file tree
Hide file tree
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
6 changes: 3 additions & 3 deletions notebooks/hfdemo/patch_tsmixer_getting_started.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -301,7 +301,7 @@
"source": [
"## Testing with a `PatchTSMixer` model that was trained on the training part of the `ETTh1` data\n",
"\n",
"A pre-trained model (on `ETTh1` data) is available at [ibm/patchtsmixer-etth1-forecasting](https://huggingface.co/ibm/patchtsmixer-etth1-forecasting)."
"A pre-trained model (on `ETTh1` data) is available at [ibm-granite/granite-timeseries-patchtsmixer](https://huggingface.co/ibm-granite/granite-timeseries-patchtsmixer)."
]
},
{
Expand All @@ -322,7 +322,7 @@
"source": [
"print(\"Loading pretrained model\")\n",
"inference_forecast_model = PatchTSMixerForPrediction.from_pretrained(\n",
" \"ibm/patchtsmixer-etth1-forecasting\"\n",
" \"ibm-granite/granite-timeseries-patchtsmixer\"\n",
")\n",
"print(\"Done\")"
]
Expand Down Expand Up @@ -885,7 +885,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.4"
"version": "3.10.13"
}
},
"nbformat": 4,
Expand Down
4 changes: 2 additions & 2 deletions notebooks/hfdemo/patch_tst_getting_started.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -289,7 +289,7 @@
"source": [
"## Testing with a `PatchTST` model that was trained on the training part of the `ETTh1` data\n",
"\n",
"A pre-trained model (on `ETTh1` data) is available at [ibm/patchtst-etth1-forecasting](https://huggingface.co/ibm/patchtst-etth1-forecasting)."
"A pre-trained model (on `ETTh1` data) is available at [ibm-granite/granite-timeseries-patchtst](https://huggingface.co/ibm-granite/granite-timeseries-patchtst)."
]
},
{
Expand All @@ -310,7 +310,7 @@
"source": [
"print(\"Loading pretrained model\")\n",
"inference_forecast_model = PatchTSTForPrediction.from_pretrained(\n",
" \"ibm/patchtst-etth1-forecasting\"\n",
" \"ibm-granite/granite-timeseries-patchtst\"\n",
")\n",
"print(\"Done\")"
]
Expand Down
14 changes: 7 additions & 7 deletions notebooks/hfdemo/ttm_getting_started.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
"\n",
"Note: Alternatively, this notebook can be modified to try the TTM-1024-96 model.\n",
"\n",
"Pre-trained TTM models will be fetched from the [Hugging Face TTM Model Repository](https://huggingface.co/ibm/TTM)."
"Pre-trained TTM models will be fetched from the [Hugging Face TTM Model Repository](https://huggingface.co/ibm-granite/granite-timeseries-ttm-v1)."
]
},
{
Expand Down Expand Up @@ -141,12 +141,12 @@
" # Load model\n",
" if prediction_filter_length is None:\n",
" zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\n",
" \"ibm/TTM\", revision=TTM_MODEL_REVISION\n",
" \"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION\n",
" )\n",
" else:\n",
" if prediction_filter_length <= forecast_length:\n",
" zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\n",
" \"ibm/TTM\", revision=TTM_MODEL_REVISION, prediction_filter_length=prediction_filter_length\n",
" \"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION, prediction_filter_length=prediction_filter_length\n",
" )\n",
" else:\n",
" raise ValueError(f\"`prediction_filter_length` should be <= `forecast_length\")\n",
Expand Down Expand Up @@ -214,22 +214,22 @@
" if \"ett\" in dataset_name:\n",
" if prediction_filter_length is None:\n",
" finetune_forecast_model = TinyTimeMixerForPrediction.from_pretrained(\n",
" \"ibm/TTM\", revision=TTM_MODEL_REVISION, head_dropout=0.7\n",
" \"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION, head_dropout=0.7\n",
" )\n",
" elif prediction_filter_length <= forecast_length:\n",
" finetune_forecast_model = TinyTimeMixerForPrediction.from_pretrained(\n",
" \"ibm/TTM\", revision=TTM_MODEL_REVISION, head_dropout=0.7, prediction_filter_length=prediction_filter_length\n",
" \"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION, head_dropout=0.7, prediction_filter_length=prediction_filter_length\n",
" )\n",
" else:\n",
" raise ValueError(f\"`prediction_filter_length` should be <= `forecast_length\")\n",
" else:\n",
" if prediction_filter_length is None:\n",
" finetune_forecast_model = TinyTimeMixerForPrediction.from_pretrained(\n",
" \"ibm/TTM\", revision=TTM_MODEL_REVISION,\n",
" \"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION,\n",
" )\n",
" elif prediction_filter_length <= forecast_length:\n",
" finetune_forecast_model = TinyTimeMixerForPrediction.from_pretrained(\n",
" \"ibm/TTM\", revision=TTM_MODEL_REVISION, prediction_filter_length=prediction_filter_length\n",
" \"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION, prediction_filter_length=prediction_filter_length\n",
" )\n",
" else:\n",
" raise ValueError(f\"`prediction_filter_length` should be <= `forecast_length\")\n",
Expand Down
10 changes: 5 additions & 5 deletions notebooks/tutorial/ttm_tutorial.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
"\n",
"Note: Alternatively, this notebook can be modified to try the TTM-1024-96 model.\n",
"\n",
"Pre-trained TTM models will be fetched from the [Hugging Face TTM Model Repository](https://huggingface.co/ibm/TTM)."
"Pre-trained TTM models will be fetched from the [Hugging Face TTM Model Repository](https://huggingface.co/ibm-granite/granite-timeseries-ttm-v1)."
]
},
{
Expand Down Expand Up @@ -49,7 +49,7 @@
],
"source": [
"# Clone the ibm/tsfm\n",
"! git clone https://github.com/IBM/tsfm.git"
"! git clone https://github.com/IBM-granite/granite-tsfm.git"
]
},
{
Expand Down Expand Up @@ -1014,7 +1014,7 @@
}
],
"source": [
"zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm/TTM\", revision=TTM_MODEL_REVISION)\n",
"zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION)\n",
"zeroshot_model"
]
},
Expand Down Expand Up @@ -1300,7 +1300,7 @@
}
],
"source": [
"finetune_forecast_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm/TTM\", revision=TTM_MODEL_REVISION, head_dropout=0.7)\n",
"finetune_forecast_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION, head_dropout=0.7)\n",
"finetune_forecast_model"
]
},
Expand Down Expand Up @@ -1650,7 +1650,7 @@
"### Q 19.\tZero-shot on channel 0 and 2 for etth1\n",
"In your notebook, add `prediction_channel_indices=[0,2]` during model loading to forecast only 0th and 2nd channels. In this case, execute the following code and note the output shape.\n",
"```\n",
"zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm/TTM\", revision=TTM_MODEL_REVISION, prediction_channel_indices=[0,2])\n",
"zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION, prediction_channel_indices=[0,2])\n",
"output = zeroshot_model.forward(test_dataset[0]['past_values'].unsqueeze(0), return_loss=False)\n",
"output.prediction_outputs.shape\n",
"```"
Expand Down
20 changes: 10 additions & 10 deletions notebooks/tutorial/ttm_tutorial_with_ans.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@
"\n",
"Note: Alternatively, this notebook can be modified to try the TTM-1024-96 model.\n",
"\n",
"Pre-trained TTM models will be fetched from the [Hugging Face TTM Model Repository](https://huggingface.co/ibm/TTM)."
"Pre-trained TTM models will be fetched from the [Hugging Face TTM Model Repository](https://huggingface.co/ibm-granite/granite-timeseries-ttm-v1)."
]
},
{
Expand All @@ -43,7 +43,7 @@
],
"source": [
"# Clone the ibm/tsfm\n",
"! git clone https://github.com/IBM/tsfm.git"
"! git clone https://github.com/IBM-granite/granite-tsfm.git"
]
},
{
Expand Down Expand Up @@ -1009,7 +1009,7 @@
}
],
"source": [
"zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm/TTM\", revision=TTM_MODEL_REVISION)\n",
"zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION)\n",
"zeroshot_model"
]
},
Expand Down Expand Up @@ -1295,7 +1295,7 @@
}
],
"source": [
"finetune_forecast_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm/TTM\", revision=TTM_MODEL_REVISION, head_dropout=0.7)\n",
"finetune_forecast_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION, head_dropout=0.7)\n",
"finetune_forecast_model"
]
},
Expand Down Expand Up @@ -1694,7 +1694,7 @@
}
],
"source": [
"zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm/TTM\", revision=TTM_MODEL_REVISION)\n",
"zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION)\n",
"temp_dir = tempfile.mkdtemp()\n",
"# zeroshot_trainer\n",
"zeroshot_trainer = Trainer(\n",
Expand Down Expand Up @@ -1755,7 +1755,7 @@
}
],
"source": [
"zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm/TTM\", revision=TTM_MODEL_REVISION, prediction_filter_length=24)\n",
"zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION, prediction_filter_length=24)\n",
"temp_dir = tempfile.mkdtemp()\n",
"# zeroshot_trainer\n",
"zeroshot_trainer = Trainer(\n",
Expand Down Expand Up @@ -1959,7 +1959,7 @@
}
],
"source": [
"finetune_forecast_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm/TTM\", revision=TTM_MODEL_REVISION, head_dropout=0.7)\n",
"finetune_forecast_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION, head_dropout=0.7)\n",
"finetune_forecast_model"
]
},
Expand Down Expand Up @@ -2201,7 +2201,7 @@
"metadata": {},
"outputs": [],
"source": [
"finetune_forecast_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm/TTM\", revision=TTM_MODEL_REVISION, head_dropout=0.7, loss=\"mae\")"
"finetune_forecast_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION, head_dropout=0.7, loss=\"mae\")"
]
},
{
Expand Down Expand Up @@ -2425,7 +2425,7 @@
"### Q 19.\tZero-shot on channel 0 and 2 for etth1\n",
"In your notebook, add `prediction_channel_indices=[0,2]` during model loading to forecast only 0th and 2nd channels. In this case, execute the following code and note the output shape.\n",
"```\n",
"zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm/TTM\", revision=TTM_MODEL_REVISION, prediction_channel_indices=[0,2])\n",
"zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION, prediction_channel_indices=[0,2])\n",
"output = zeroshot_model.forward(test_dataset[0]['past_values'].unsqueeze(0), return_loss=False)\n",
"output.prediction_outputs.shape\n",
"```"
Expand All @@ -2449,7 +2449,7 @@
}
],
"source": [
"zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm/TTM\", revision=TTM_MODEL_REVISION, prediction_channel_indices=[0,2])\n",
"zeroshot_model = TinyTimeMixerForPrediction.from_pretrained(\"ibm-granite/granite-timeseries-ttm-v1\", revision=TTM_MODEL_REVISION, prediction_channel_indices=[0,2])\n",
"output = zeroshot_model.forward(test_dataset[0]['past_values'].unsqueeze(0), return_loss=False)\n",
"output.prediction_outputs.shape"
]
Expand Down
Loading