Article
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
MultiverseComputingCAI
• • 23
Iker García-Ferrero
Iker
AI & ML interests
NLP, multilingual models, information extraction
Recent Activity
commentedon a paper 17 days ago
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss upvoted an article 18 days ago
Making Knowledge Distillation Cheap Enough to Run at ScaleOrganizations
published an article 3 days ago
commented a
paper 17 days ago
upvoted an article 18 days ago
Article
Making Knowledge Distillation Cheap Enough to Run at Scale
MultiverseComputingCAI
• • 39 submitted a
paper to Daily Papers 18 days ago
published an article 18 days ago
Article
Making Knowledge Distillation Cheap Enough to Run at Scale
MultiverseComputingCAI
• • 39 updated a
model 21 days ago
updated a
Space 21 days ago
authored 5
papers 22 days ago
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss
Paper • 2608.03796 • Published • 16
Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics
Paper • 2512.16602 • Published
Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque
Paper • 2506.07597 • Published
GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction
Paper • 2506.00649 • Published • 4
Cross-Lingual Transfer for Low-Resource Natural Language Processing
Paper • 2502.02722 • Published
upvoted a paper 22 days ago
liked a
dataset 3 months ago
updated a
model 7 months ago
updated 4
models 8 months ago
Iker/Latxa-Llama-3.1-8B-Instruct-w4a4_nvfp4
Text Generation • 5B • Updated • 8
Iker/Latxa-Qwen3-VL-2B-Instruct-w8a8_fp8
Image-Text-to-Text • 2B • Updated • 7
Iker/Latxa-Qwen3-VL-2B-Instruct-w4a16_nvfp4
Image-Text-to-Text • 2B • Updated • 9
Iker/Latxa-Qwen3-VL-4B-Instruct-w4a16_nvfp4
Image-Text-to-Text • 4B • Updated • 7 • 1
published a
model 8 months ago