Instructions to use AvoCahDoe/gemma-2-9b-rlmpq-conservative with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AvoCahDoe/gemma-2-9b-rlmpq-conservative with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AvoCahDoe/gemma-2-9b-rlmpq-conservative")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AvoCahDoe/gemma-2-9b-rlmpq-conservative")
model = AutoModelForCausalLM.from_pretrained("AvoCahDoe/gemma-2-9b-rlmpq-conservative", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AvoCahDoe/gemma-2-9b-rlmpq-conservative with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AvoCahDoe/gemma-2-9b-rlmpq-conservative"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AvoCahDoe/gemma-2-9b-rlmpq-conservative",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AvoCahDoe/gemma-2-9b-rlmpq-conservative

SGLang

How to use AvoCahDoe/gemma-2-9b-rlmpq-conservative with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "AvoCahDoe/gemma-2-9b-rlmpq-conservative" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AvoCahDoe/gemma-2-9b-rlmpq-conservative",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "AvoCahDoe/gemma-2-9b-rlmpq-conservative" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AvoCahDoe/gemma-2-9b-rlmpq-conservative",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AvoCahDoe/gemma-2-9b-rlmpq-conservative with Docker Model Runner:
```
docker model run hf.co/AvoCahDoe/gemma-2-9b-rlmpq-conservative
```

gemma-2-9b-rlmpq-conservative / README.md

AvoCahDoe

RL-MPQ Conservative — 2026-06-11T20:32:52.715518

e5cb211 verified about 2 months ago

preview code

Raw

History Blame

2.75 kB

	---
	license: gemma
	base_model: google/gemma-2-9b
	pipeline_tag: text-generation
	language:
	- en
	tags:
	- gemma
	- text-generation
	- rl-mpq
	- mixed-precision
	- quantization
	- fake-quantization
	- conservative
	library_name: transformers
	datasets:
	- wikitext
	widget:
	- text: "The capital of France is"
	---

	# Gemma 2 9B — RL-MPQ Conservative

	Standalone RL-MPQ (Reinforcement Learning Mixed-Precision Quantization) checkpoint for the
	Conservative scenario — a quantized variant of
	[google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b).

	\| Field \| Value \|
	\|-------\|-------\|
	\| Base model \| [google/gemma-2-9b](https://huggingface.co/google/gemma-2-9b) \|
	\| Scenario \| Conservative \|
	\| Avg bits / weight \| 5.1429 \|
	\| Compression vs FP16 \| 3.1111× \|
	\| WikiText-2 PPL \| 116.5244 \|
	\| Layers \| 42 \|
	\| Bit distribution \| `{'4': 30, '8': 12}` \|
	\| Format \| Fake-quant FP16 + `rlmpq_policy.json` \|


	## Usage

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

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

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

	## Other Gemma 2 9B scenarios

	\| Scenario \| Avg bits \| Compression \| WikiText-2 PPL \|
	\|----------\|----------\|-------------\|----------------\|
	\| [Aggressive](https://huggingface.co/AvoCahDoe/gemma-2-9b-rlmpq-aggressive) \| 3.6667 \| 4.3636x \| 162.8437 \|
	\| [Balanced](https://huggingface.co/AvoCahDoe/gemma-2-9b-rlmpq-balanced) \| 4.2857 \| 3.7333x \| 127.0798 \|
	\| [Extreme Survival](https://huggingface.co/AvoCahDoe/gemma-2-9b-rlmpq-extreme-survival) \| 2.7857 \| 5.7436x \| 424.7991 \|
	\| [High Fidelity](https://huggingface.co/AvoCahDoe/gemma-2-9b-rlmpq-high-fidelity) \| 7.0476 \| 2.2703x \| 104.8098 \|

	Grouped archive (all scenarios in one repo):
	[AvoCahDoe/gemma-2-9b-rlmpq](https://huggingface.co/AvoCahDoe/gemma-2-9b-rlmpq)

	## Method

	1. Phase 3 — PPO agent assigns per-layer bit widths under the Conservative reward target.
	2. Phase 4 — Policy replayed on real weights; WikiText-2 perplexity validates quality.
	3. 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

	```bibtex
	@misc{rlmpq_gemma_2_9b_conservative_2026,
	title = {RL-MPQ Conservative: Gemma 2 9B Mixed-Precision Quantization},
	author = {AvoCahDoe},
	year = {2026},
	url = {https://huggingface.co/AvoCahDoe/gemma-2-9b-rlmpq-conservative}
	}
	```