Instructions to use HopitAI/hopper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use HopitAI/hopper with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B") model = PeftModel.from_pretrained(base_model, "HopitAI/hopper") - Notebooks
- Google Colab
- Kaggle
Commit History
19 days ago
-
Card: Hopper 12B (trained) Decision Index 47.52
Verified signaturefa02eff
21 days ago
-
Card: overview, models table and quick start; 4B details below; JevBench v1.5.5 standing
Verified signature4bbab19 -
Card: point to Hopper 12B (trained) on branch hopper-12b
Verified signatured753ff6
26 days ago
-
Card: current JevBench position (#7, v1.4.2.2)
Verified signature5d7ff51 -
Card: pointer to Hopper (G) 1.3; weights unchanged
Verified signatureceade03
27 days ago
-
Card: official leaderboard results on JevBench and the Jev Decision Index, and links between Hopper and Hopper (G); weights unchanged
Verified signature9e01ce7
30 days ago
-
Card: long menus (more than 26 options) from code release 1.1.1; weights and map unchanged
Verified signature80262fe -
Set the card's licence field to research-and-demo
Verified signature4e40d7e -
Label the adapter research and demo use; note RACE training-data terms
Verified signatured58a99c
-
Hopper v1.1.0: calibration map replaced by one temperature per answer type; adapter weights unchanged
Verified signature281d393
-
Set task_type to CAUSAL_LM so the Hub parses the adapter config
Verified signaturebe8d454 -
Hopper adapter v1.0.0
Verified signature6e2c0ea -
initial commit
Verified signature45f0d2c