Update HF nvidia collection links in docs (#475)

kevalmorabia97 · web-flow · commit 90b1e68fcf1d · 2025-10-28T22:23:01.000+05:30
Signed-off-by: Keval Morabia &lt;28916987+kevalmorabia97@users.noreply.github.com&gt;
diff --git a/CHANGELOG-Windows.rst b/CHANGELOG-Windows.rst
@@ -29,7 +29,7 @@ Model Optimizer Changelog (Windows)
 - **LLM Quantization with Olive:** Enabled LLM quantization through Olive, streamlining model optimization workflows. Refer `example <https://github.com/microsoft/Olive/tree/main/examples/phi3#quantize-models-with-nvidia-tensorrt-model-optimizer>`_
 - **DirectML Deployment Guide:** Added DML deployment guide. Refer :ref:`DirectML_Deployment`.
 - **MMLU Benchmark for Accuracy Evaluations:** Introduced `MMLU benchmarking <https://github.com/NVIDIA/TensorRT-Model-Optimizer/tree/main/examples/windows/accuracy_benchmark/README.md>`_ for accuracy evaluation of ONNX models on DirectML (DML).
-- **Published quantized ONNX models collection:** Published quantized ONNX models at HuggingFace `NVIDIA collections <https://huggingface.co/collections/nvidia/optimized-onnx-models-for-nvidia-rtx-gpus-67373fe7c006ebc1df310613>`_.
+- **Published quantized ONNX models collection:** Published quantized ONNX models at HuggingFace `NVIDIA collections <https://huggingface.co/collections/nvidia/optimized-onnx-models-for-nvidia-rtx-gpus>`_.
 
 
 \* *This version includes experimental features such as TensorRT deployment of ONNX INT4 models, PyTorch quantization and sparsity. These are currently unverified on Windows.*
diff --git a/README.md b/README.md
@@ -98,7 +98,7 @@ more fine-grained control on installed dependencies or for alternative docker im
 
 ## Pre-Quantized Checkpoints
 
-- Ready-to-deploy checkpoints \[[🤗 Hugging Face - Nvidia TensorRT Model Optimizer Collection](https://huggingface.co/collections/nvidia/model-optimizer-66aa84f7966b3150262481a4)\]
+- Ready-to-deploy checkpoints \[[🤗 Hugging Face - Nvidia TensorRT Model Optimizer Collection](https://huggingface.co/collections/nvidia/inference-optimized-checkpoints-with-model-optimizer)\]
 - Deployable on [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM), [vLLM](https://github.com/vllm-project/vllm) and [SGLang](https://github.com/sgl-project/sglang)
 - More models coming soon!
 
diff --git a/docs/source/deployment/2_directml.rst b/docs/source/deployment/2_directml.rst
@@ -42,4 +42,4 @@ For further details and examples, please refer to the `ONNX Runtime documentatio
 Collection of optimized ONNX models
 ===================================
 
-The ready-to-deploy optimized ONNX models from ModelOpt-Windows are available at HuggingFace `NVIDIA collections <https://huggingface.co/collections/nvidia/optimized-onnx-models-for-nvidia-rtx-gpus-67373fe7c006ebc1df310613>`_. These models can be deployed using DirectML backend. Follow the instructions provided along with the published models for deployment.
+The ready-to-deploy optimized ONNX models from ModelOpt-Windows are available at HuggingFace `NVIDIA collections <https://huggingface.co/collections/nvidia/optimized-onnx-models-for-nvidia-rtx-gpus>`_. These models can be deployed using DirectML backend. Follow the instructions provided along with the published models for deployment.
diff --git a/examples/llm_ptq/README.md b/examples/llm_ptq/README.md
@@ -49,7 +49,7 @@ Similarly, for vLLM or SGLang deployment, please use their installation docs.
 
 ### 1. Quantize (Post Training Quantization)
 
-With the simple API below, you can very easily use Model Optimizer to quantize your model. Model Optimizer achieves this by converting the precision of your model to the desired precision, and then using a small dataset (typically 128-512 samples) to [calibrate](https://nvidia.github.io/TensorRT-Model-Optimizer/guides/_basic_quantization.html) the quantization scaling factors. The accuracy of PTQ is typically robust across different choices of calibration data, by default Model Optimizer uses [`cnn_dailymail`](https://huggingface.co/datasets/abisee/cnn_dailymail). Users can try other datasets by easily modifying the `calib_set`.
+With the simple API below, you can very easily use Model Optimizer to quantize your model. Model Optimizer achieves this by converting the precision of your model to the desired precision, and then using a small dataset (typically 128-512 samples) to [calibrate](https://nvidia.github.io/TensorRT-Model-Optimizer/guides/_basic_quantization.html) the quantization scaling factors. The accuracy of PTQ is typically robust across different choices of calibration data, by default Model Optimizer uses a mix of [`cnn_dailymail`](https://huggingface.co/datasets/abisee/cnn_dailymail) and [`nemotron-post-training-dataset-v2`](https://huggingface.co/datasets/nvidia/Nemotron-Post-Training-Dataset-v2). Users can try other datasets by easily modifying the `calib_set`.
 
 ```python
 import modelopt.torch.quantization as mtq
@@ -432,7 +432,7 @@ After the TensorRT-LLM checkpoint export, you can use the `trtllm-build` build c
 
 ## Pre-Quantized Checkpoints
 
-- Ready-to-deploy checkpoints \[[🤗 Hugging Face - Nvidia TensorRT Model Optimizer Collection](https://huggingface.co/collections/nvidia/model-optimizer-66aa84f7966b3150262481a4)\]
+- Ready-to-deploy checkpoints \[[🤗 Hugging Face - Nvidia TensorRT Model Optimizer Collection](https://huggingface.co/collections/nvidia/inference-optimized-checkpoints-with-model-optimizer)\]
 - Deployable on [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM), [vLLM](https://github.com/vllm-project/vllm) and [SGLang](https://github.com/sgl-project/sglang)
 - More models coming soon!
 
diff --git a/examples/llm_qat/README.md b/examples/llm_qat/README.md
@@ -349,7 +349,7 @@ To perform QLoRA training, run:
 
 ## Pre-Quantized Checkpoints
 
-- Ready-to-deploy checkpoints \[[🤗 Hugging Face - Nvidia TensorRT Model Optimizer Collection](https://huggingface.co/collections/nvidia/model-optimizer-66aa84f7966b3150262481a4)\]
+- Ready-to-deploy checkpoints \[[🤗 Hugging Face - Nvidia TensorRT Model Optimizer Collection](https://huggingface.co/collections/nvidia/inference-optimized-checkpoints-with-model-optimizer)\]
 - Deployable on [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM), [vLLM](https://github.com/vllm-project/vllm) and [SGLang](https://github.com/sgl-project/sglang)
 - More models coming soon!
 
diff --git a/examples/onnx_ptq/README.md b/examples/onnx_ptq/README.md
@@ -275,7 +275,7 @@ trtexec --onnx=/path/to/identity_neural_network.quant.onnx \
 
 ## Pre-Quantized Checkpoints
 
-- Ready-to-deploy checkpoints that can be exported to ONNX format (if supported as per the [Support Matrix](#onnx-export-supported-llm-models)) \[[🤗 Hugging Face - Nvidia TensorRT Model Optimizer Collection](https://huggingface.co/collections/nvidia/model-optimizer-66aa84f7966b3150262481a4)\]
+- Ready-to-deploy checkpoints that can be exported to ONNX format (if supported as per the [Support Matrix](#onnx-export-supported-llm-models)) \[[🤗 Hugging Face - Nvidia TensorRT Model Optimizer Collection](https://huggingface.co/collections/nvidia/inference-optimized-checkpoints-with-model-optimizer)\]
 
 ## Resources
 
diff --git a/examples/pruning/README.md b/examples/pruning/README.md
@@ -183,7 +183,7 @@ You can also look at the NeMo tutorial notebooks [here](https://github.com/NVIDI
 
 Some of the models pruned using Minitron method followed by distillation and post-training are:
 
-- [Minitron Collection on Hugging Face](https://huggingface.co/collections/nvidia/minitron-669ac727dc9c86e6ab7f0f3e)
+- [Minitron Collection on Hugging Face](https://huggingface.co/collections/nvidia/minitron)
 - [NVIDIA-Nemotron-Nano-9B-v2](https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2)
 
 ### FastNAS Pruning for PyTorch Computer Vision Models
diff --git a/examples/speculative_decoding/README.md b/examples/speculative_decoding/README.md
@@ -316,7 +316,7 @@ trainer.save_model("<path to the output directory>")
 
 ## Speculation Module Checkpoints
 
-Ready-to-deploy speculation module checkpoints \[[🤗 Hugging Face - NVIDIA TensorRT Model Optimizer Collection](https://huggingface.co/collections/nvidia/model-optimizer-66aa84f7966b3150262481a4)\]
+Ready-to-deploy speculation module checkpoints \[[🤗 Hugging Face - NVIDIA Speculative Decoding Modules Collection](https://huggingface.co/collections/nvidia/speculative-decoding-modules)\]
 Deployable on [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM) and [SGLang](https://github.com/sgl-project/sglang)!\
 More models coming soon!
 
diff --git a/examples/vlm_ptq/README.md b/examples/vlm_ptq/README.md
@@ -66,7 +66,7 @@ scripts/huggingface_example.sh --model <Hugging Face model card or checkpoint> -
 
 ## Pre-Quantized Checkpoints
 
-- Ready-to-deploy checkpoints \[[🤗 Hugging Face - Nvidia TensorRT Model Optimizer Collection](https://huggingface.co/collections/nvidia/model-optimizer-66aa84f7966b3150262481a4)\]
+- Ready-to-deploy checkpoints \[[🤗 Hugging Face - Nvidia TensorRT Model Optimizer Collection](https://huggingface.co/collections/nvidia/inference-optimized-checkpoints-with-model-optimizer)\]
 - Deployable on [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM), [vLLM](https://github.com/vllm-project/vllm) and [SGLang](https://github.com/sgl-project/sglang)
 - More models coming soon!
 
diff --git a/examples/windows/README.md b/examples/windows/README.md
@@ -16,7 +16,7 @@ A Library to Quantize and Compress Deep Learning Models for Optimized Inference
 ## Latest News
 
 - [2024/11/19] [Microsoft and NVIDIA Supercharge AI Development on RTX AI PCs](https://blogs.nvidia.com/blog/ai-decoded-microsoft-ignite-rtx/)
-- [2024/11/18] [Quantized INT4 ONNX models available on Hugging Face for download](https://huggingface.co/collections/nvidia/optimized-onnx-models-for-nvidia-rtx-gpus-67373fe7c006ebc1df310613)
+- [2024/11/18] [Quantized INT4 ONNX models available on Hugging Face for download](https://huggingface.co/collections/nvidia/optimized-onnx-models-for-nvidia-rtx-gpus)
 
 ## Table of Contents
 
@@ -120,7 +120,7 @@ onnx.save_model(
 For detailed instructions about deployment of quantized models with DirectML backend (ORT-DML), see the [DirectML](https://nvidia.github.io/TensorRT-Model-Optimizer/deployment/2_directml.html#directml-deployment).
 
 > [!Note]
-> The ready-to-deploy optimized ONNX models from ModelOpt-Windows are available at HuggingFace [NVIDIA collections](https://huggingface.co/collections/nvidia/optimized-onnx-models-for-nvidia-rtx-gpus-67373fe7c006ebc1df310613).
+> The ready-to-deploy optimized ONNX models from ModelOpt-Windows are available at HuggingFace [NVIDIA collections](https://huggingface.co/collections/nvidia/optimized-onnx-models-for-nvidia-rtx-gpus).
 
 ## Examples
 
@@ -140,7 +140,7 @@ Please refer to [benchmark results](./Benchmark.md) for performance and accuracy
 
 ## Collection Of Optimized ONNX Models
 
-The ready-to-deploy optimized ONNX models from ModelOpt-Windows are available at [HuggingFace NVIDIA collections](https://huggingface.co/collections/nvidia/optimized-onnx-models-for-nvidia-rtx-gpus-67373fe7c006ebc1df310613). These models can be deployed using DirectML backend. Follow the instructions provided along with the published models for deployment.
+The ready-to-deploy optimized ONNX models from ModelOpt-Windows are available at [HuggingFace NVIDIA collections](https://huggingface.co/collections/nvidia/optimized-onnx-models-for-nvidia-rtx-gpus). These models can be deployed using DirectML backend. Follow the instructions provided along with the published models for deployment.
 
 ## Release Notes
 
