1.1 GB

Ctrl+K

1 contributor

v2 domain SFT: early-stopped at step 1100 (val_loss 1.886), trained on the expanded 40k-example dataset -- see README for honest limitations (not a confirmed improvement over v1 on hard questions)

5c8f2b2 verified about 20 hours ago

.gitattributes

1.52 kB
initial commit 1 day ago
README.md

4.25 kB
v2 domain SFT: early-stopped at step 1100 (val_loss 1.886), trained on the expanded 40k-example dataset -- see README for honest limitations (not a confirmed improvement over v1 on hard questions) about 20 hours ago
chat_template.jinja

945 Bytes
Upload folder using huggingface_hub 1 day ago
config.json

1.17 kB
Upload folder using huggingface_hub 1 day ago
generation_config.json

195 Bytes
Upload folder using huggingface_hub 1 day ago
model.safetensors

1.09 GB
xet

v2 domain SFT: early-stopped at step 1100 (val_loss 1.886), trained on the expanded 40k-example dataset -- see README for honest limitations (not a confirmed improvement over v1 on hard questions) about 20 hours ago
tokenizer.json

8.51 MB
Upload folder using huggingface_hub 1 day ago
tokenizer_config.json

440 Bytes
Upload folder using huggingface_hub 1 day ago