A curated collection of datasets in French, designed to evaluate biases in LLMs
Irina Proskurina PRO
iproskurina
AI & ML interests
LLMs: quantization, pre-training
Recent Activity
updated
a model 3 days ago
iproskurina/Phi-4-mini-instruct-sparse14-alpha-0-ss-ultrachat2 updated
a model 3 days ago
iproskurina/Phi-4-mini-instruct-sparse14-alpha-1-ss-ultrachat2 updated
a model 3 days ago
iproskurina/sparsity_stage_Phi_4_mini_instruct_1_4_wanda Organizations
Attention graph features extracted from LMs fine-tuned on linguistic acceptability corpora
A collection of models submitted to the BabyLM23 competition
