Khmer dataset
12.11.12
kimleang123
AI & ML interests
NLP | CV | LLM
Recent Activity
liked a model 2 days ago
aisingapore/SEA-LION-E5-Embedding-600M liked a dataset 3 days ago
open-index/hacker-news liked a dataset 3 days ago
OpenMOSS-Team/OmniActionOrganizations
-
Transfer Learning for Text Diffusion Models
Paper • 2401.17181 • Published • 17 -
LLM2CLIP: Powerful Language Model Unlock Richer Visual Representation
Paper • 2411.04997 • Published • 39 -
HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering
Paper • 2509.09713 • Published • 25 -
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
Paper • 2301.08243 • Published • 7
Khmer fine-tuned models. All the models under my repo were conducted under ViLa Lab, ITC, Cambodia
-
kimleang123/fine-tuned-KQA-mistral-7B-v0.3-lora-128-256
Text Generation • 7B • Updated -
kimleang123/fine-tuned-KQA-mistral-7B-v3-QLoRA
Text Generation • 7B • Updated -
kimleang123/fine-tuned-KQA-qwen2-7B-QLoRA
Text Generation • 8B • Updated -
kimleang123/fine-tuned-KQA-qwen2-7B-lora-128-256
Text Generation • 8B • Updated
Khmer dataset
Khmer fine-tuned models. All the models under my repo were conducted under ViLa Lab, ITC, Cambodia
-
kimleang123/fine-tuned-KQA-mistral-7B-v0.3-lora-128-256
Text Generation • 7B • Updated -
kimleang123/fine-tuned-KQA-mistral-7B-v3-QLoRA
Text Generation • 7B • Updated -
kimleang123/fine-tuned-KQA-qwen2-7B-QLoRA
Text Generation • 8B • Updated -
kimleang123/fine-tuned-KQA-qwen2-7B-lora-128-256
Text Generation • 8B • Updated
-
Transfer Learning for Text Diffusion Models
Paper • 2401.17181 • Published • 17 -
LLM2CLIP: Powerful Language Model Unlock Richer Visual Representation
Paper • 2411.04997 • Published • 39 -
HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering
Paper • 2509.09713 • Published • 25 -
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
Paper • 2301.08243 • Published • 7