⌘K

Models Leaderboard Activity Rescue Submit ZK Inference

Models Leaderboard Activity Rescue Submit ZK Inference

ResourcesArticles How it works 𝕏 @ThePirateFace

Language中文

Theme

Mission Worth rescuing Donate ProvenanceAgents Terms Listing policy Privacy

qikp/gemma-3-110m-english-only-old · Pirate Face

qikp/gemma-3-110m-english-only-old

Source: 🤗text-generationgemma110M params441 MBsafetensors✓ 1 checksumupdated 208d ago

Gemma 3 110M English Only

This is Gemma 3 270M with the pika 3 tokenizer used and with retrained embedding and output layers, afterwards a gentle retrain.

Chat template

Note: This uses the Zephyr chat template.

Training

It was trained on these using 1 epoch, sparse adam optimizer, and 32 batch size:

HuggingFaceTB/cosmopedia-20k
HuggingFaceTB/smol-smoltalk (first 23,000 rows)
HuggingFaceTB/everyday-conversations-llama3.1-2k

Limitations

The quality of this model needs to be better tested. It will also poorly handle non-English languages.

CommentsShare your thoughts and shape the future of sovereign AI.

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

Files and sources

✓SourceAvailable on 🤗

2Checksums1 awaiting witness

3TorrentNot listed

4SwarmNot checked

Source revision: b493c66d12c6…
Witnessed: Not yet
Weight files: 1
Model size: 441 MB
Downloads · last month: 18
Publisher: Unclaimed

Public checksum record coming on the next sync

Seed this model

Have the files? Submit a torrent.

Submit a torrent →

or

>_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 qikp/gemma-3-110m-english-only-old ./model-folder