Add Qwen3 Coder Next artifacts

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+conversion_config_mixed_precision.json filter=lfs diff=lfs merge=lfs -text
+conversion_config_tFP8_calib_based.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -28,11 +28,9 @@ The quantized models are evaluated on 10% of the [WikiText-2 raw v1](https://hug
 
 | Model Configuration              | Absolute Perplexity | Relative Perplexity Drop vs. BF16 | Details                                                     |
 |----------------------------------|---------------------|-----------------------------------|-------------------------------------------------------------|
-| BF16                             | ????                | –                                 | The baseline model trained in BF16                          |
-| calibration_free_tFP16           | ????                | ???? %                            | calibration-free tFP16 quantization                         |
-| calibration_based_tFP16          | ????                | ???? %                            | calibration-based tFP16 quantization                        |
-| layerwise_mixed_precision        | ????                | ???? %                            | calibration-based mixed-precision: tFP8, outliers in tFP16  |
-| calibration_free_dynamic_tFP8    | ????                | ???? %                            | calibration-free tFP8 dynamic quantization                  |
+| BF16                             | 6.351               | –                                 | The baseline model trained in BF16                          |
+| layerwise_mixed_precision        | 6.365               | 0.23 %                            | calibration-based mixed-precision: tFP8, outliers in tFP16  |
+| calibration_based_tFP16          | 6.498               | 2.33 %                            | calibration-free tFP8 dynamic quantization                  |
 
 ## 🚀 Getting Started
 Refer to the Tensordyne Hugging Face Hub tutorial in our [hosted documentation](https://resources.tensordyne.ai/sdk/) for instructions on using the artifacts provided in this repository.  

conversion_config_mixed_precision.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e5a7b022d44413a453780c46baf58e58ce8662991557b4ae10e51a446e5eb4
+size 60106414

conversion_config_tFP8_calib_based.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:890ca2ccf418229e80722b8ebcc586e6dc29a1884186ad76871c06300e73e6ca
+size 60103205