Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- vllm
|
| 4 |
+
- fp8
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
base_model: unsloth/gpt-oss-20b-BF16
|
| 7 |
+
library_name: transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# RedHatAI/gpt-oss-20b-FP8-Dynamic
|
| 11 |
+
|
| 12 |
+
## Model Overview
|
| 13 |
+
- **Model Architecture:** gpt-oss-20b-BF16
|
| 14 |
+
- **Input:** Text
|
| 15 |
+
- **Output:** Text
|
| 16 |
+
- **Model Optimizations:**
|
| 17 |
+
- **Weight quantization:** FP8
|
| 18 |
+
- **Activation quantization:** FP8
|
| 19 |
+
- **Release Date:** 08/13/2025
|
| 20 |
+
- **Version:** 1.0
|
| 21 |
+
- **Model Developers:** RedHatAI
|
| 22 |
+
|
| 23 |
+
Quantized version of [unsloth/gpt-oss-20b-BF16](https://huggingface.co/unsloth/gpt-oss-20b-BF16).
|