GPT-OSS-20B.LOCAL

README.md

@@ -13,7 +13,7 @@ tags:
 <p align="center">
   <a href="https://gpt-oss.com"><strong>Try gpt-oss</strong></a> ·
   <a href="https://cookbook.openai.com/topic/gpt-oss"><strong>Guides</strong></a> ·
-  <a href="https://arxiv.org/abs/2508.10925"><strong>Model card</strong></a> ·
+  <a href="https://openai.com/index/gpt-oss-model-card"><strong>Model card</strong></a> ·
   <a href="https://openai.com/index/introducing-gpt-oss/"><strong>OpenAI blog</strong></a>
 </p>
 
@@ -22,7 +22,7 @@ tags:
 Welcome to the gpt-oss series, [OpenAI’s open-weight models](https://openai.com/open-models) designed for powerful reasoning, agentic tasks, and versatile developer use cases.
 
 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 80GB GPU (like NVIDIA H100 or AMD MI300X) (117B parameters with 5.1B active parameters)
+- `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](https://github.com/openai/harmony) and should only be used with the harmony format as it will not work correctly otherwise.
@@ -38,7 +38,7 @@ Both models were trained on our [harmony response format](https://github.com/ope
 * **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.  
 * **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](https://github.com/openai/gpt-oss/tree/main?tab=readme-ov-file#browser), [Python code execution](https://github.com/openai/gpt-oss/tree/main?tab=readme-ov-file#python), and Structured Outputs.
-* **MXFP4 quantization:** The models were post-trained with MXFP4 quantization of the MoE weights, making `gpt-oss-120b` run on a single 80GB GPU (like NVIDIA H100 or AMD MI300X) and the `gpt-oss-20b` model run within 16GB of memory. All evals were performed with the same MXFP4 quantization.
+* **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.
 
 ---
 
@@ -166,17 +166,3 @@ The gpt-oss models are excellent for:
 Both gpt-oss models can be fine-tuned for a variety of specialized use cases.
 
 This smaller model `gpt-oss-20b` can be fine-tuned on consumer hardware, whereas the larger [`gpt-oss-120b`](https://huggingface.co/openai/gpt-oss-120b) can be fine-tuned on a single H100 node.
-
-# Citation
-
-```bibtex
-@misc{openai2025gptoss120bgptoss20bmodel,
-      title={gpt-oss-120b & gpt-oss-20b Model Card}, 
-      author={OpenAI},
-      year={2025},
-      eprint={2508.10925},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2508.10925}, 
-}
-```

chat_template.jinja

@@ -245,9 +245,9 @@
     {%- if developer_message %}
         {{- "# Instructions\n\n" }}
         {{- developer_message }}
-        {{- "\n\n" }}
     {%- endif %}
     {%- if tools -%}
+        {{- "\n\n" }}
         {{- "# Tools\n\n" }}
         {{- render_tool_namespace("functions", tools) }}
     {%- endif -%}

generation_config.json

@@ -3,8 +3,7 @@
   "do_sample": true,
   "eos_token_id": [
     200002,
-    199999,
-    200012
+    199999
   ],
   "pad_token_id": 199999,
   "transformers_version": "4.55.0.dev0"