Invoice document layout detection: annotated dataset, fine-tuned YOLOv8 models (nano & medium), and an interactive Gradio demo.
El boubkraoui Farid
AvoCahDoe
·
AI & ML interests
None yet
Recent Activity
published a model 2 days ago
AvoCahDoe/invoice-layout-yolo11x published a model 2 days ago
AvoCahDoe/invoice-layout-yolo11m published a model 2 days ago
AvoCahDoe/invoice-layout-yolov8xOrganizations
None yet
RL-MPQ fake-quant LLaVA-Next Mistral-7B. Aggressive @ 2.81 bpw. VLMEvalKit MMMU/MMBench/ScienceQA.
RL-MPQ fake-quant LLaVA-1.5-13B (Llama-2-13B backbone). High Fidelity, Balanced, Aggressive. VLMEvalKit MMMU/MMBench/ScienceQA.
-
AvoCahDoe/llava-1.5-13b-rlmpq-high-fidelity
Image-Text-to-Text • 13B • Updated • 111 -
AvoCahDoe/llava-1.5-13b-rlmpq-balanced
Image-Text-to-Text • 13B • Updated • 70 -
AvoCahDoe/llava-1.5-13b-rlmpq-aggressive
Image-Text-to-Text • 13B • Updated • 81 -
AvoCahDoe/llava-15-rlmpq-vlm-eval-results
Viewer • Updated • 14 • 610
5 RL-MPQ fake-quant Qwen 2.5 7B scenarios. Mixed-precision fake-quant checkpoints for thesis.
-
AvoCahDoe/qwen2-5-7b-rlmpq-aggressive
Text Generation • 8B • Updated • 15 -
AvoCahDoe/qwen2-5-7b-rlmpq-balanced
Text Generation • 8B • Updated • 12 -
AvoCahDoe/qwen2-5-7b-rlmpq-conservative
Text Generation • 8B • Updated • 15 -
AvoCahDoe/qwen2-5-7b-rlmpq-extreme-survival
Text Generation • 8B • Updated • 10
5 RL-MPQ fake-quant Llama 3 8B scenarios: High Fidelity through Extreme Survival. Thesis checkpoints.
-
AvoCahDoe/llama-3-8b-rlmpq-aggressive
Text Generation • 8B • Updated • 27 -
AvoCahDoe/llama-3-8b-rlmpq-balanced
Text Generation • 8B • Updated • 40 -
AvoCahDoe/llama-3-8b-rlmpq-conservative
Text Generation • 8B • Updated • 31 -
AvoCahDoe/llama-3-8b-rlmpq-extreme-survival
Text Generation • 8B • Updated • 30
5 RL-MPQ fake-quant Mistral 7B scenarios. Per-layer mixed precision via PPO-trained policies.
-
AvoCahDoe/mistral-7b-rlmpq-aggressive
Text Generation • 7B • Updated • 34 -
AvoCahDoe/mistral-7b-rlmpq-balanced
Text Generation • 7B • Updated • 34 -
AvoCahDoe/mistral-7b-rlmpq-conservative
Text Generation • 7B • Updated • 25 -
AvoCahDoe/mistral-7b-rlmpq-extreme-survival
Text Generation • 7B • Updated • 36
5 RL-MPQ fake-quant Llama 3.1 8B scenarios: High Fidelity through Extreme Survival. Extension checkpoints.
-
AvoCahDoe/llama-3-1-8b-rlmpq-aggressive
Text Generation • 8B • Updated • 36 -
AvoCahDoe/llama-3-1-8b-rlmpq-balanced
Text Generation • 8B • Updated • 37 -
AvoCahDoe/llama-3-1-8b-rlmpq-conservative
Text Generation • 8B • Updated • 31 -
AvoCahDoe/llama-3-1-8b-rlmpq-extreme-survival
Text Generation • 8B • Updated • 35
RL-MPQ fake-quant Qwen2-VL-7B (qwen2_5_7b Balanced policy). 3.39 bpw. VLMEvalKit exact-match eval.
RL-MPQ fake-quant LLaVA-1.5-7B (Llama-2-7B backbone). Extreme_Survival @ 2.97 bpw. VLMEvalKit exact-match eval.
RL-MPQ fake-quantized LLaVA-1.5-13B vision-language models and their VLMEvalKit benchmark results (MMMU, MMBench, ScienceQA).
-
AvoCahDoe/llava-1.5-13b-rlmpq-high-fidelity
Image-Text-to-Text • 13B • Updated • 111 -
AvoCahDoe/llava-1.5-13b-rlmpq-balanced
Image-Text-to-Text • 13B • Updated • 70 -
AvoCahDoe/llava-1.5-13b-rlmpq-aggressive
Image-Text-to-Text • 13B • Updated • 81 -
AvoCahDoe/llava-15-rlmpq-vlm-eval-results
Viewer • Updated • 14 • 610
5 RL-MPQ fake-quant Llama 2 7B scenarios: High Fidelity, Conservative, Balanced, Aggressive, Extreme Survival.
-
AvoCahDoe/llama-2-7b-rlmpq-aggressive
Text Generation • 7B • Updated • 23 -
AvoCahDoe/llama-2-7b-rlmpq-balanced
Text Generation • 7B • Updated • 51 -
AvoCahDoe/llama-2-7b-rlmpq-conservative
Text Generation • 7B • Updated • 29 -
AvoCahDoe/llama-2-7b-rlmpq-extreme-survival
Text Generation • 7B • Updated • 26
5 RL-MPQ fake-quant Llama 2 13B scenarios: High Fidelity, Conservative, Balanced, Aggressive, Extreme Survival.
-
AvoCahDoe/llama-2-13b-rlmpq-aggressive
Text Generation • 13B • Updated • 35 -
AvoCahDoe/llama-2-13b-rlmpq-balanced
Text Generation • 13B • Updated • 31 -
AvoCahDoe/llama-2-13b-rlmpq-conservative
Text Generation • 13B • Updated • 35 -
AvoCahDoe/llama-2-13b-rlmpq-extreme-survival
Text Generation • 13B • Updated • 31
5 RL-MPQ fake-quant Gemma 2 9B scenarios. Per-layer bit-width policies from Phase 3 PPO.
-
AvoCahDoe/gemma-2-9b-rlmpq-aggressive
Text Generation • 9B • Updated • 27 -
AvoCahDoe/gemma-2-9b-rlmpq-balanced
Text Generation • 9B • Updated • 28 -
AvoCahDoe/gemma-2-9b-rlmpq-conservative
Text Generation • 9B • Updated • 36 -
AvoCahDoe/gemma-2-9b-rlmpq-extreme-survival
Text Generation • 9B • Updated • 30
5 RL-MPQ fake-quant JetMoE 8B scenarios. Mixed-precision MoE fake-quant extension checkpoints.
Invoice document layout detection: annotated dataset, fine-tuned YOLOv8 models (nano & medium), and an interactive Gradio demo.
RL-MPQ fake-quant Qwen2-VL-7B (qwen2_5_7b Balanced policy). 3.39 bpw. VLMEvalKit exact-match eval.
RL-MPQ fake-quant LLaVA-Next Mistral-7B. Aggressive @ 2.81 bpw. VLMEvalKit MMMU/MMBench/ScienceQA.
RL-MPQ fake-quant LLaVA-1.5-7B (Llama-2-7B backbone). Extreme_Survival @ 2.97 bpw. VLMEvalKit exact-match eval.
RL-MPQ fake-quant LLaVA-1.5-13B (Llama-2-13B backbone). High Fidelity, Balanced, Aggressive. VLMEvalKit MMMU/MMBench/ScienceQA.
-
AvoCahDoe/llava-1.5-13b-rlmpq-high-fidelity
Image-Text-to-Text • 13B • Updated • 111 -
AvoCahDoe/llava-1.5-13b-rlmpq-balanced
Image-Text-to-Text • 13B • Updated • 70 -
AvoCahDoe/llava-1.5-13b-rlmpq-aggressive
Image-Text-to-Text • 13B • Updated • 81 -
AvoCahDoe/llava-15-rlmpq-vlm-eval-results
Viewer • Updated • 14 • 610
RL-MPQ fake-quantized LLaVA-1.5-13B vision-language models and their VLMEvalKit benchmark results (MMMU, MMBench, ScienceQA).
-
AvoCahDoe/llava-1.5-13b-rlmpq-high-fidelity
Image-Text-to-Text • 13B • Updated • 111 -
AvoCahDoe/llava-1.5-13b-rlmpq-balanced
Image-Text-to-Text • 13B • Updated • 70 -
AvoCahDoe/llava-1.5-13b-rlmpq-aggressive
Image-Text-to-Text • 13B • Updated • 81 -
AvoCahDoe/llava-15-rlmpq-vlm-eval-results
Viewer • Updated • 14 • 610
5 RL-MPQ fake-quant Qwen 2.5 7B scenarios. Mixed-precision fake-quant checkpoints for thesis.
-
AvoCahDoe/qwen2-5-7b-rlmpq-aggressive
Text Generation • 8B • Updated • 15 -
AvoCahDoe/qwen2-5-7b-rlmpq-balanced
Text Generation • 8B • Updated • 12 -
AvoCahDoe/qwen2-5-7b-rlmpq-conservative
Text Generation • 8B • Updated • 15 -
AvoCahDoe/qwen2-5-7b-rlmpq-extreme-survival
Text Generation • 8B • Updated • 10
5 RL-MPQ fake-quant Llama 2 7B scenarios: High Fidelity, Conservative, Balanced, Aggressive, Extreme Survival.
-
AvoCahDoe/llama-2-7b-rlmpq-aggressive
Text Generation • 7B • Updated • 23 -
AvoCahDoe/llama-2-7b-rlmpq-balanced
Text Generation • 7B • Updated • 51 -
AvoCahDoe/llama-2-7b-rlmpq-conservative
Text Generation • 7B • Updated • 29 -
AvoCahDoe/llama-2-7b-rlmpq-extreme-survival
Text Generation • 7B • Updated • 26
5 RL-MPQ fake-quant Llama 3 8B scenarios: High Fidelity through Extreme Survival. Thesis checkpoints.
-
AvoCahDoe/llama-3-8b-rlmpq-aggressive
Text Generation • 8B • Updated • 27 -
AvoCahDoe/llama-3-8b-rlmpq-balanced
Text Generation • 8B • Updated • 40 -
AvoCahDoe/llama-3-8b-rlmpq-conservative
Text Generation • 8B • Updated • 31 -
AvoCahDoe/llama-3-8b-rlmpq-extreme-survival
Text Generation • 8B • Updated • 30
5 RL-MPQ fake-quant Llama 2 13B scenarios: High Fidelity, Conservative, Balanced, Aggressive, Extreme Survival.
-
AvoCahDoe/llama-2-13b-rlmpq-aggressive
Text Generation • 13B • Updated • 35 -
AvoCahDoe/llama-2-13b-rlmpq-balanced
Text Generation • 13B • Updated • 31 -
AvoCahDoe/llama-2-13b-rlmpq-conservative
Text Generation • 13B • Updated • 35 -
AvoCahDoe/llama-2-13b-rlmpq-extreme-survival
Text Generation • 13B • Updated • 31
5 RL-MPQ fake-quant Mistral 7B scenarios. Per-layer mixed precision via PPO-trained policies.
-
AvoCahDoe/mistral-7b-rlmpq-aggressive
Text Generation • 7B • Updated • 34 -
AvoCahDoe/mistral-7b-rlmpq-balanced
Text Generation • 7B • Updated • 34 -
AvoCahDoe/mistral-7b-rlmpq-conservative
Text Generation • 7B • Updated • 25 -
AvoCahDoe/mistral-7b-rlmpq-extreme-survival
Text Generation • 7B • Updated • 36
5 RL-MPQ fake-quant Gemma 2 9B scenarios. Per-layer bit-width policies from Phase 3 PPO.
-
AvoCahDoe/gemma-2-9b-rlmpq-aggressive
Text Generation • 9B • Updated • 27 -
AvoCahDoe/gemma-2-9b-rlmpq-balanced
Text Generation • 9B • Updated • 28 -
AvoCahDoe/gemma-2-9b-rlmpq-conservative
Text Generation • 9B • Updated • 36 -
AvoCahDoe/gemma-2-9b-rlmpq-extreme-survival
Text Generation • 9B • Updated • 30
5 RL-MPQ fake-quant Llama 3.1 8B scenarios: High Fidelity through Extreme Survival. Extension checkpoints.
-
AvoCahDoe/llama-3-1-8b-rlmpq-aggressive
Text Generation • 8B • Updated • 36 -
AvoCahDoe/llama-3-1-8b-rlmpq-balanced
Text Generation • 8B • Updated • 37 -
AvoCahDoe/llama-3-1-8b-rlmpq-conservative
Text Generation • 8B • Updated • 31 -
AvoCahDoe/llama-3-1-8b-rlmpq-extreme-survival
Text Generation • 8B • Updated • 35
5 RL-MPQ fake-quant JetMoE 8B scenarios. Mixed-precision MoE fake-quant extension checkpoints.