From 0a8f5f29d3cf79fb6d2e7431f190282fd086991e Mon Sep 17 00:00:00 2001 From: cwhitelam <79796271+cwhitelam@users.noreply.github.com> Date: Tue, 5 Aug 2025 17:28:41 -0400 Subject: [PATCH] Correct small grammar issues for better comprehension (#21) * Correct small grammar issues for better comprehension * Update README.md --------- Co-authored-by: Christopher Whitelam Co-authored-by: Dominik Kundel --- README.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 518e6f0..3144d7a 100644 --- a/README.md +++ b/README.md @@ -18,16 +18,16 @@ We're releasing two flavors of these open models: - `gpt-oss-120b` — for production, general purpose, high reasoning use cases that fit into a single H100 GPU (117B parameters with 5.1B active parameters) - `gpt-oss-20b` — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters) -Both models were trained on our [harmony response format][harmony] and should only be used with the harmony format as it will not work correctly otherwise. +Both models were trained using our [harmony response format][harmony] and should only be used with this format; otherwise, they will not work correctly. ### Highlights - **Permissive Apache 2.0 license:** Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment. - **Configurable reasoning effort:** Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs. -- **Full chain-of-thought:** Gain complete access to the model's reasoning process, facilitating easier debugging and increased trust in outputs. It's not intended to be shown to end users. +- **Full chain-of-thought:** Provides complete access to the model's reasoning process, facilitating easier debugging and greater trust in outputs. This information is not intended to be shown to end users. - **Fine-tunable:** Fully customize models to your specific use case through parameter fine-tuning. - **Agentic capabilities:** Use the models' native capabilities for function calling, [web browsing](#browser), [Python code execution](#python), and Structured Outputs. -- **Native MXFP4 quantization:** The models are trained with native MXFP4 precision for the MoE layer, making `gpt-oss-120b` run on a single H100 GPU and the `gpt-oss-20b` model run within 16GB of memory. +- **Native MXFP4 quantization:** The models are trained with native MXFP4 precision for the MoE layer, allowing `gpt-oss-120b` to run on a single H100 GPU and `gpt-oss-20b` to run within 16GB of memory.. ### Inference examples @@ -402,7 +402,7 @@ To improve performance the tool caches requests so that the model can revisit a ### Python -The model was trained to use using a python tool to perform calculations and other actions as part of its chain-of-thought. During the training the model used a stateful tool which makes running tools between CoT loops easier. This reference implementation, however, uses a stateless mode. As a result the PythonTool defines its own tool description to override the definition in [`openai-harmony`][harmony]. +The model was trained to use a python tool to perform calculations and other actions as part of its chain-of-thought. During the training the model used a stateful tool which makes running tools between CoT loops easier. This reference implementation, however, uses a stateless mode. As a result the PythonTool defines its own tool description to override the definition in [`openai-harmony`][harmony]. > [!WARNING] > This implementation runs in a permissive Docker container which could be problematic in cases like prompt injections. It's serving as an example and you should consider implementing your own container restrictions in production.