Instructions to use bookxd/gemma-4-E2B-it-jmh-simpleRL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bookxd/gemma-4-E2B-it-jmh-simpleRL with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-4-E2B-it")
model = PeftModel.from_pretrained(base_model, "bookxd/gemma-4-E2B-it-jmh-simpleRL")

Transformers

How to use bookxd/gemma-4-E2B-it-jmh-simpleRL with Transformers:

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

pipe = pipeline("text-generation", model="bookxd/gemma-4-E2B-it-jmh-simpleRL")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bookxd/gemma-4-E2B-it-jmh-simpleRL", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bookxd/gemma-4-E2B-it-jmh-simpleRL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bookxd/gemma-4-E2B-it-jmh-simpleRL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bookxd/gemma-4-E2B-it-jmh-simpleRL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bookxd/gemma-4-E2B-it-jmh-simpleRL

SGLang

How to use bookxd/gemma-4-E2B-it-jmh-simpleRL 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 "bookxd/gemma-4-E2B-it-jmh-simpleRL" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bookxd/gemma-4-E2B-it-jmh-simpleRL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "bookxd/gemma-4-E2B-it-jmh-simpleRL" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bookxd/gemma-4-E2B-it-jmh-simpleRL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bookxd/gemma-4-E2B-it-jmh-simpleRL with Docker Model Runner:
```
docker model run hf.co/bookxd/gemma-4-E2B-it-jmh-simpleRL
```

gemma-4-E2B-it JMH simpleRL (LoRA)

LoRA adapter from the first online GRPO stage of the JMH benchmark generation pipeline (simpleRL: compile + runtime + regex anti-pattern rewards only).

Base model: google/gemma-4-E2B-it
Training: GRPO (Dr.GRPO, colocated vLLM 0.23), 80 steps, 113 curated Java subjects
Reward: compile (0.34) + runtime (0.33) + regex anti-pattern (0.33)
Corpus: Apache Commons Numbers/Statistics/Codec/Text, RoaringBitmap, Jackson Core

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = "google/gemma-4-E2B-it"
adapter = "bookxd/gemma-4-E2B-it-jmh-simpleRL"

tokenizer = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="bfloat16", device_map="auto")
model = PeftModel.from_pretrained(model, adapter)

Use with the jmhbench chat prompt contract from the JMH Training Pipeline.

Training stack

PyTorch 2.11.0+cu130, Transformers 5.10.1, TRL 1.7.1, vLLM 0.23.0, PEFT 0.19.1
LoRA r=16, alpha=32 on attention + MLP projections
Final step reward ≈ 0.41, reward_std ≈ 0.24 (80/80 steps)

Downloads last month: -

Model tree for bookxd/gemma-4-E2B-it-jmh-simpleRL

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Adapter

(118)

this model