RL-MPQ VLM — LLaVA-1.5-13B - a AvoCahDoe Collection

AvoCahDoe 's Collections

Invoice Layout Extraction

RL-MPQ VLM — Qwen2-VL-7B

RL-MPQ VLM — LLaVA-Next Mistral-7B

RL-MPQ VLM — LLaVA-1.5-7B

RL-MPQ VLM — LLaVA-1.5-13B

RL-MPQ LLaVA-1.5-13B VLM Evaluation

RL-MPQ — Qwen 2.5 7B

RL-MPQ — Llama 2 7B

RL-MPQ — Llama 3 8B

RL-MPQ — Llama 2 13B

RL-MPQ — Mistral 7B

RL-MPQ — Gemma 2 9B

RL-MPQ — Llama 3.1 8B

RL-MPQ — JetMoE 8B

RL-MPQ VLM — LLaVA-1.5-13B

updated Jun 13

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 Jun 13 • 21

Note RL-MPQ High Fidelity (6.7 bpw) — avg 56.1%
AvoCahDoe/llava-1.5-13b-rlmpq-balanced

Image-Text-to-Text • 13B • Updated Jun 13 • 18

Note RL-MPQ Balanced (4.4 bpw) — avg 56.1%
AvoCahDoe/llava-1.5-13b-rlmpq-aggressive

Image-Text-to-Text • 13B • Updated Jun 13 • 18

Note RL-MPQ Aggressive (3.75 bpw) — avg 56.2%, best Δ vs FP16
AvoCahDoe/llava-15-rlmpq-vlm-eval-results

Viewer • Updated Jun 18 • 14 • 373

Note Eval results: llama13b_aggressive group (FP16/INT4/RL-MPQ × 3 benchmarks)