Downloads · 30 days
10
2% of all-time downloads
gemma-4-E2B-it-jmh-simpleRL-merged
bookxd/gemma-4-E2B-it-jmh-simpleRL-merged
gemma-4-E2B-it-jmh-simpleRL-merged is a text generation model from bookxd. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as gemma.
Full merged weights (LoRA baked in) from the first online GRPO stage (simpleRL).
All-time downloads
658
Public
Parameters
5.1B
10.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors10.2 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- gemma
- Model type
- gemma4
- Access
- Public
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026
- SHA
- 6000690e
Try a prompt
Base models
Model card
From the Hugging Face model README
gemma-4-E2B-it JMH simpleRL (merged)
Full merged weights (LoRA baked in) from the first online GRPO stage (simpleRL).
- Base: google/gemma-4-E2B-it
- Adapter source: bookxd/gemma-4-E2B-it-jmh-simpleRL
- Merge: KV-share-safe state-dict merge (Gemma 4 compatible with vLLM)
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "bookxd/gemma-4-E2B-it-jmh-simpleRL-merged"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto")
- Task
- Text Generation
- Library
- transformers
- Type
- gemma4
- License
- gemma
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026