Downloads · 30 days
7
5% of all-time downloads
Raghav-Singhal/tulu3sft-epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-bce-tmpl-epe
tulu3sft-epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-bce-tmpl-epe is a machine learning model from Raghav-Singhal. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Full-model SFT of EPE base epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz on allenai/tulu-3-sft-mixture (939,344 rows, response-only masked).
Downloads · 30 days
7
5% of all-time downloads
All-time downloads
145
Public
Parameters
1.7B
3.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.4 GB · 100%
From the Hugging Face model README
Full-model SFT of EPE base epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz on allenai/tulu-3-sft-mixture (939,344 rows, response-only masked).
[49153, 49188) are masked to -inf in the logits before cross-entropy so the next-token head does not compete with the constitution BCE head during SFT.default = standard SmolLM2 <|im_start|>assistant\n; epe = angle-bracketed <|im_start|><assistant>\n).epe_sft_shifted_ntp_charter_mask_v4, loss_scaling=hf_distributed_token_average.