RL-MPQ — Mistral 7B - 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 — Mistral 7B

updated Jun 11

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 Jun 11 • 6

Note Aggressive: 2.8125 bits/weight, 5.6889x vs FP16, WikiText-2 PPL 10.025. RL-MPQ PPO fake-quant of mistralai/Mistral-7B-v0.1.
AvoCahDoe/mistral-7b-rlmpq-balanced

Text Generation • 7B • Updated Jun 11 • 7

Note Balanced: 3.3438 bits/weight, 4.785x vs FP16, WikiText-2 PPL 5.3053. RL-MPQ PPO fake-quant of mistralai/Mistral-7B-v0.1.
AvoCahDoe/mistral-7b-rlmpq-conservative

Text Generation • 7B • Updated Jun 11 • 4

Note Conservative: 3.8125 bits/weight, 4.1967x vs FP16, WikiText-2 PPL 5.1877. RL-MPQ PPO fake-quant of mistralai/Mistral-7B-v0.1.
AvoCahDoe/mistral-7b-rlmpq-extreme-survival

Text Generation • 7B • Updated Jun 11 • 7

Note Extreme Survival: 2.5625 bits/weight, 6.2439x vs FP16, WikiText-2 PPL 46.2801. RL-MPQ PPO fake-quant of mistralai/Mistral-7B-v0.1.
AvoCahDoe/mistral-7b-rlmpq-high-fidelity

Text Generation • 7B • Updated Jun 11 • 2

Note High Fidelity: 4.4375 bits/weight, 3.6056x vs FP16, WikiText-2 PPL 4.8901. RL-MPQ PPO fake-quant of mistralai/Mistral-7B-v0.1.