Downloads · 30 days
8
9% of all-time downloads
agurung/colar-gemma-3-4b-ff-sft
colar-gemma-3-4b-ff-sft is a machine learning model from agurung. 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.
This repository stores CoLAR exports in a Hugging Face-compatible layout. The repo root works for standard Transformers loading, and extrastate.pt preserves the latent head for latent decoding.
Downloads · 30 days
8
9% of all-time downloads
All-time downloads
87
Public
Parameters
4.3B
20.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors17.2 GB · 92%
From the Hugging Face model README
This repository stores CoLAR exports in a Hugging Face-compatible layout. The repo root works for standard Transformers loading, and extra_state.pt preserves the latent head for latent decoding.
last-ew6ob26ggemma3_colar_sft_last_ew6ob26g| Tag | Local reference | Status |
|---|---|---|
best-epoch02-step35-val_loss=2.5829 | best step35 export | tagged checkpoint |
last-ew6ob26g | canonical last export | current commit |
extra_state.pt for CoLAR latent decodingexport_meta.json from the local exportlatent_metadata.json with archival provenancefrom transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained('agurung/colar-gemma-3-4b-ff-sft', revision='last-ew6ob26g', torch_dtype='auto', device_map='auto')
tokenizer = AutoTokenizer.from_pretrained('agurung/colar-gemma-3-4b-ff-sft', revision='last-ew6ob26g')
For latent decoding, download the same revision and use extra_state.pt together with the repo root model files.