Instructions to use manihani4/portal-vlm-gemma3-lora-1k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use manihani4/portal-vlm-gemma3-lora-1k with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-4b-it") model = PeftModel.from_pretrained(base_model, "manihani4/portal-vlm-gemma3-lora-1k") - Notebooks
- Google Colab
- Kaggle
| { | |
| "name": "gemma3-lora-1k", | |
| "kind": "peft", | |
| "base_model": "google/gemma-3-4b-it", | |
| "base_revision": "093f9f388b31de276ce2de164bdc2081324b9767", | |
| "config": "configs/gemma3_lora_1k.yaml", | |
| "eval_result": "results/gemma3_lora_1k.json", | |
| "description": "Fresh-training reference for the cross-family porting row: grounding LoRA (r16/a32, LM sites) on Gemma-3-4B-it at ~1k examples, canonical 0-1000 dialect.", | |
| "trained_at_commit": "7c81a42", | |
| "source_artifact": "PorTAL-vlm-probe results/adapters/m4_lora_ref_1k", | |
| "files": { | |
| "adapter_config.json": { | |
| "bytes": 5562, | |
| "sha256": "9827f73abf790052cc8a00b848f2a0ad70d3c69e5b3d287508d08d4a464381b9" | |
| }, | |
| "adapter_model.safetensors": { | |
| "bytes": 119280712, | |
| "sha256": "909bc6a7ece99067dff89edfefeae0ce4a30e95f519e763e80d69d3bfdf851fb" | |
| } | |
| }, | |
| "screenspot_overall": 0.158, | |
| "screenspot_web": 0.1007 | |
| } |