Downloads · 30 days
6
13% of all-time downloads
Raghav-Singhal/smollm2-1.7b-100B-linear-merge-epe-no_bce-w0.3-normal-w0.7
smollm2-1.7b-100B-linear-merge-epe-no_bce-w0.3-normal-w0.7 is a text generation model from Raghav-Singhal. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Linear weight-merge of two SmolLM2-1.7B pretraining checkpoints (each trained on 100B tokens).
Downloads · 30 days
6
13% of all-time downloads
All-time downloads
45
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
Linear weight-merge of two SmolLM2-1.7B pretraining checkpoints (each trained on 100B tokens).
merged = 0.3 * EPE + 0.7 * NORMAL
| Component | Weight | Source checkpoint |
|---|---|---|
| EPE (no_bce) | 0.3 | epe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce |
| NORMAL | 0.7 | normal-smollm-1p7b-100B-20n-2048sl-960gbsz |