Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
quantized_by: bartowski
|
| 3 |
+
pipeline_tag: text-generation
|
| 4 |
+
base_model_relation: quantized
|
| 5 |
+
base_model: openai/gpt-oss-120b
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
## Llamacpp experimental Quantizations of gpt-oss-120b by Open AI
|
| 9 |
+
|
| 10 |
+
Using llama.cpp branch `gpt-oss-mxfp4`, PR here: https://github.com/ggml-org/llama.cpp/pull/15091
|
| 11 |
+
|
| 12 |
+
You must use that branch in order to run the model
|
| 13 |
+
|
| 14 |
+
Original model: https://huggingface.co/openai/gpt-oss-120b
|
| 15 |
+
|
| 16 |
+
This is a single static quant in the new MXFP4 format, rest of sizes will come after PR is merged
|