levossadtchi commited on
Commit
ec77546
·
verified ·
1 Parent(s): 402caaf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -2
README.md CHANGED
@@ -113,8 +113,6 @@ High-level training data summary:
113
  - Data is a mixed corpus pipeline configured in the repository and processed into tokenized shards before training.
114
  - SFT stage uses chat/instruction-style datasets with assistant-targeted supervision.
115
 
116
- The full training pipeline and dataset composition are described in the repository `README.md`.
117
-
118
  All training artifacts are published separately at:
119
 
120
  - [levossadtchi/QED-75M_artifacts](https://huggingface.co/levossadtchi/QED-75M_artifacts)
 
113
  - Data is a mixed corpus pipeline configured in the repository and processed into tokenized shards before training.
114
  - SFT stage uses chat/instruction-style datasets with assistant-targeted supervision.
115
 
 
 
116
  All training artifacts are published separately at:
117
 
118
  - [levossadtchi/QED-75M_artifacts](https://huggingface.co/levossadtchi/QED-75M_artifacts)