Minor tweaks

Co-authored-by: vb <[email protected]>

Author: pcuenca

articles/gpt-oss/run-colab.ipynb

@@ -8,9 +8,9 @@
       "source": [
         "# Run OpenAI gpt-oss 20B in a FREE Google Colab\n",
         "\n",
-        "OpenAI released `gpt-oss` [120B](https://hf.co/openai/gpt-oss-120b) and [20B](https://hf.co/openai/gpt-oss-120b). Both the models are Apache 2.0 licensed.\n",
+        "OpenAI released `gpt-oss` [120B](https://hf.co/openai/gpt-oss-120b) and [20B](https://hf.co/openai/gpt-oss-120b). Both models are Apache 2.0 licensed.\n",
         "\n",
-        "Specifically `gpt-oss-20b` was made for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters).\n",
+        "Specifically, `gpt-oss-20b` was made for lower latency and local or specialized use cases (21B parameters with 3.6B active parameters).\n",
         "\n",
         "Since the models were trained in native MXFP4 quantization it makes it easy to run the 20B even in resource constrained environments like Google Colab.\n",
         "\n",
@@ -32,7 +32,7 @@
         "id": "zMRXDOpY1Q3Q"
       },
       "source": [
-        "Since the support is bleeding edge. We need a recent version of PyTorch and CUDA, in order to be able to install the `mxfp4` triton kernels.\n",
+        "Since support for mxfp4 in transformers is bleeding edge, we need a recent version of PyTorch and CUDA, in order to be able to install the `mxfp4` triton kernels.\n",
         "\n",
         "We also need to install transformers from source, and we uninstall `torchvision` and `torchaudio` to remove dependency conflicts."
       ]
@@ -572,7 +572,7 @@
       "source": [
         "## Try out other prompts and ideas!\n",
         "\n",
-        "Checkout our blogpost for other ideas: [hf.co/blog/welcome-openai-gpt-oss](hf.co/blog/welcome-openai-gpt-oss)"
+        "Check out our blogpost for other ideas: [hf.co/blog/welcome-openai-gpt-oss](hf.co/blog/welcome-openai-gpt-oss)"
       ]
     }
   ],