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 / config.json

AvoCahDoe

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

e5cb211 verified about 2 months ago

Raw

History Blame

2.56 kB

	{
	"architectures": [
	"Gemma2ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_logit_softcapping": 50.0,
	"bos_token_id": 2,
	"cache_implementation": "hybrid",
	"dtype": "bfloat16",
	"eos_token_id": 1,
	"final_logit_softcapping": 30.0,
	"head_dim": 256,
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 3584,
	"initializer_range": 0.02,
	"intermediate_size": 14336,
	"layer_types": [
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 8192,
	"model_type": "gemma2",
	"num_attention_heads": 16,
	"num_hidden_layers": 42,
	"num_key_value_heads": 8,
	"pad_token_id": 0,
	"query_pre_attn_scalar": 256,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"rope_theta": 10000.0,
	"rope_type": "default",
	"type": "default"
	},
	"sliding_window": 4096,
	"sliding_window_size": 4096,
	"tie_word_embeddings": true,
	"transformers_version": "5.11.0",
	"use_bidirectional_attention": null,
	"use_cache": true,
	"vocab_size": 256000,
	"base_model": "google/gemma-2-9b",
	"quantization": {
	"method": "rl-mpq",
	"format": "fake-quant-fp16",
	"scenario": "Conservative",
	"avg_bits": 5.1429,
	"description": "Per-layer mixed bit-width via PPO-trained policy (not GPTQ/AWQ)"
	},
	"rlmpq": {
	"framework": "RL-NMP-Model-Quantasation",
	"scenario": "Conservative",
	"scenario_label": "Conservative",
	"repo_id": "AvoCahDoe/gemma-2-9b-rlmpq-conservative",
	"grouped_repo": "AvoCahDoe/gemma-2-9b-rlmpq",
	"collection_title": "RL-MPQ \u2014 Gemma 2 9B"
	}
	}