Downloads · 30 days
0
jsanzolac/bpe_glove_512_lora_v1
bpe_glove_512_lora_v1 is a machine learning model from jsanzolac. 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.
LoRA drifts on top of frozen jsanzolac/bpeglove512 BPE-GloVe-512 embeddings, distilled from Qwen/Qwen3-Embedding-8B (MRL-truncated to 512 dims).
Downloads · 30 days
0
Access
Public
Updated May 18, 2026
Repo size
4 GB
Likes
0
Public
Click a slice to open those files.
.txt439 MB · 70%
From the Hugging Face model README
LoRA drifts on top of frozen jsanzolac/bpe_glove_512 BPE-GloVe-512 embeddings, distilled
from Qwen/Qwen3-Embedding-8B (MRL-truncated to 512 dims).
Variant 1 loss: λ_c·InfoNCE + λ_D·||ρ_T - ρ_S||_F² with λ_c=1.0, λ_D=0.1.
Each rank_<r>/ folder contains:
checkpoint_final.ptconfig.jsonvectors_drifted.txttrain_log.jsonlRanks shipped: [512, 256, 128, 64, 32, 16, 8, 4, 2]