Image-Text-to-Text
PEFT
Safetensors
android
android-world
ui-automation
accessibility
vision-language
lora
reinforcement-learning
Instructions to use dmitchelljackson/cerebellum-qwen35-history-actions-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use dmitchelljackson/cerebellum-qwen35-history-actions-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-0.8B") model = PeftModel.from_pretrained(base_model, "dmitchelljackson/cerebellum-qwen35-history-actions-lora") - Notebooks
- Google Colab
- Kaggle
Download harness_code/rl_harness/__init__.py from dmitchelljackson/cerebellum-qwen35-history-actions-lora: direct link, hf CLI and curl.
- Browser
- Download file 49 Bytes
-
https://huggingface.co/dmitchelljackson/cerebellum-qwen35-history-actions-lora/resolve/main/harness_code/rl_harness/__init__.py
- Command line
-
hf download hf://dmitchelljackson/cerebellum-qwen35-history-actions-lora/harness_code/rl_harness/__init__.py
-
curl -L -o __init__.py https://huggingface.co/dmitchelljackson/cerebellum-qwen35-history-actions-lora/resolve/main/harness_code/rl_harness/__init__.py
49 Bytes
| """RL rollout harness pieces for Cerebellum.""" | |