Mistral 7B — RL-MPQ Balanced
Standalone RL-MPQ (Reinforcement Learning Mixed-Precision Quantization) checkpoint for the Balanced scenario — a quantized variant of mistralai/Mistral-7B-v0.1.
| Field | Value |
|---|---|
| Base model | mistralai/Mistral-7B-v0.1 |
| Scenario | Balanced |
| Avg bits / weight | 3.3438 |
| Compression vs FP16 | 4.785× |
| WikiText-2 PPL | 5.3053 |
| Layers | 32 |
| Bit distribution | {'3': 21, '4': 11} |
| Format | Fake-quant FP16 + rlmpq_policy.json |
Collection: RL-MPQ — Mistral 7B — all five scenarios for Mistral 7B.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "AvoCahDoe/mistral-7b-rlmpq-balanced"
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="float16")
tokenizer = AutoTokenizer.from_pretrained(repo)
Other Mistral 7B scenarios
| Scenario | Avg bits | Compression | WikiText-2 PPL |
|---|---|---|---|
| Aggressive | 2.8125 | 5.6889x | 10.025 |
| Conservative | 3.8125 | 4.1967x | 5.1877 |
| Extreme Survival | 2.5625 | 6.2439x | 46.2801 |
| High Fidelity | 4.4375 | 3.6056x | 4.8901 |
Grouped archive (all scenarios in one repo): AvoCahDoe/mistral-7b-rlmpq
Method
- Phase 3 — PPO agent assigns per-layer bit widths under the Balanced reward target.
- Phase 4 — Policy replayed on real weights; WikiText-2 perplexity validates quality.
- Export — Fake-quantized FP16 weights compatible with Hugging Face Transformers.
Files
| File | Description |
|---|---|
config.json | Llama architecture + RL-MPQ metadata |
model.safetensors | Fake-quantized weights |
rlmpq_policy.json | Per-layer bit-width policy |
rlmpq_metrics.json | Validation & PPL summary |
Citation
@misc{rlmpq_mistral_7b_balanced_2026,
title = {RL-MPQ Balanced: Mistral 7B Mixed-Precision Quantization},
author = {AvoCahDoe},
year = {2026},
url = {https://huggingface.co/AvoCahDoe/mistral-7b-rlmpq-balanced}
}