WalidBouss/proj_only_llava_deepseek_r1_distill_llama3_8b_reasoning_visual_cot_1000_samples_10_epochs Updated 5 days ago
WalidBouss/proj_only_llava_deepseek_r1_distill_llama3_8b_reasoning_visual_cot_1000_samples_10_epochs Updated 5 days ago
WalidBouss/proj_only_llava_deepseek_r1_distill_llama3_8b_reasoning_visual_cot_1000_samples Updated 5 days ago โข 5
WalidBouss/proj_only_llava_deepseek_r1_distill_llama3_8b_reasoning_visual_cot_10000_samples Updated 5 days ago โข 4
WalidBouss/proj_only_llava_deepseek_r1_distill_llama3_8b_reasoning_visual_cot_10000_samples Updated 5 days ago โข 4
WalidBouss/proj_only_llava_deepseek_r1_distill_llama3_8b_reasoning_visual_cot_1000_samples Updated 5 days ago โข 5
๐ Interpretability & Analysis of LMs Collection Outstanding research in LM interpretability and evaluation, summarized โข 105 items โข Updated 19 days ago โข 97
view article Article Falcon 2: An 11B parameter pretrained language model and VLM, trained on over 5000B tokens tokens and 11 languages May 24, 2024 โข 25
LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity Paper โข 2404.03214 โข Published Apr 4, 2024 โข 2
LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity Paper โข 2404.03214 โข Published Apr 4, 2024 โข 2
Grounding Everything: Emerging Localization Properties in Vision-Language Transformers Paper โข 2312.00878 โข Published Dec 1, 2023 โข 2