smcleish/clrs_gemma_2b_100k_finetune_with_traces

Source: 🤗text-generationmit2.5B params5.0 GBsafetensors✓ 3 checksumsupdated 690d ago

Model Details

google/gemma-2b model finetuned on 100,000 CLRS-Text examples.

Training Details

Learning Rate: 1e-4, 150 warmup steps then cosine decayed to 5e-06 using AdamW optimiser
Batch size: 128
Loss taken over answer only, not on question.

CommentsShare your thoughts and shape the future of sovereign AI.

@smcleish is unclaimedSign in with the matching Hugging Face account or an organization member account to verify this handle.Claim @smcleish

Files and sources

✓SourceAvailable on 🤗

✓Checksums3 recorded

3TorrentNot listed

4SwarmNot checked

Source revision: 082438fd51cc…
Witnessed: 6 Nov 2026, 18:30 UTC
Weight files: 3
Model size: 5.0 GB
Downloads · last month: 10
Publisher: Unclaimed

View provenance entry #46207 →

Seed this model

Have the files? Submit a torrent.

Submit a torrent →

>_Package the files with one command

Have the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo smcleish/clrs_gemma_2b_100k_finetune_with_traces ./model-folder