AvoCahDoe/gemma-2-9b-rlmpq-balanced

Gemma 2 9B — RL-MPQ Balanced

Standalone RL-MPQ (Reinforcement Learning Mixed-Precision Quantization) checkpoint for the Balanced scenario — a quantized variant of google/gemma-2-9b.

Collection: RL-MPQ — Gemma 2 9B — all five scenarios for Gemma 2 9B.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "AvoCahDoe/gemma-2-9b-rlmpq-balanced"

model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="float16")
tokenizer = AutoTokenizer.from_pretrained(repo)

Other Gemma 2 9B scenarios

Grouped archive (all scenarios in one repo): AvoCahDoe/gemma-2-9b-rlmpq

Method

1. 1.Phase 3 — PPO agent assigns per-layer bit widths under the Balanced reward target.
2. 2.Phase 4 — Policy replayed on real weights; WikiText-2 perplexity validates quality.
3. 3.Export — Fake-quantized FP16 weights compatible with Hugging Face Transformers.

Files

Citation

@misc{rlmpq_gemma_2_9b_balanced_2026,
  title  = {RL-MPQ Balanced: Gemma 2 9B Mixed-Precision Quantization},
  author = {AvoCahDoe},
  year   = {2026},
  url    = {https://huggingface.co/AvoCahDoe/gemma-2-9b-rlmpq-balanced}
}