GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
nabin2004
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
nabin2004
Model Tree
google/gemma-4-E2B-it
Input Modalities
Output Modalities
Supported Functionality
This adapter is trained on top of google/gemma-4-E2B-it. You must accept the Gemma license and set HF_TOKEN to download the base weights.
Fine-tuned on nabin2004/AOS-Trajectories using the AOS Phase 1 SFT trainer (apps/sft).
python
import osimport torchfrom peft import PeftModelfrom transformers import AutoModelForImageTextToText, AutoTokenizer, BitsAndBytesConfigtoken = os.environ["HF_TOKEN"]base_id = "google/gemma-4-E2B-it"adapter_id = "nabin2004/AOS-gemma4-manim-sft"bnb = BitsAndBytesConfig(load_in_4bit=True,bnb_4bit_use_double_quant=True,bnb_4bit_quant_type="nf4",bnb_4bit_compute_dtype=torch.bfloat16,)base = AutoModelForImageTextToText.from_pretrained(base_id,quantization_config=bnb,device_map="auto",torch_dtype=torch.bfloat16,token=token,)model = PeftModel.from_pretrained(base, adapter_id, token=token)tokenizer = AutoTokenizer.from_pretrained(adapter_id, token=token)model.eval()
The adapter is trained on multi-turn Code Agent tool calls, not single-turn prose. Use the AOS inference script:
bash
cd apps/sftuv run python infer.py \--adapter-dir nabin2004/AOS-gemma4-manim-sft \--prompt "Create a short Manim scene explaining eigenvectors in 2D."
Colab:
bash
uv run --package sft python apps/sft/infer.py \--adapter-dir nabin2004/AOS-gemma4-manim-sft \--colab \--prompt "Create a short Manim scene explaining eigenvectors in 2D."
| File | Description |
|---|---|
adapter_config.json | PEFT LoRA configuration |
adapter_model.safetensors | LoRA weights |
tokenizer_config.json | Training chat template (includes {% generation %} markers) |
bash
cd apps/sftuv run python run.py --colab --epochs 1 --report-to none --push-to-hub
Or upload an existing adapter:
bash
export HF_TOKEN=hf_...uv run python upload_adapter.py --adapter-dir ./gemma4-manim-ft