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
Card: point to Hopper 12B (trained) on branch hopper-12b
Browse files
README.md
CHANGED
|
@@ -30,6 +30,15 @@ datasets:
|
|
| 30 |
|
| 31 |
# Hopper
|
| 32 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
> **Research and demo use only.** This adapter is published for research and demonstration. Its training data included passages from RACE (via the `cais/mmlu` auxiliary set), which its authors release for non-commercial research only and whose terms extend to derived data. Do not use this adapter commercially. A version trained without these passages is in development.
|
| 34 |
|
| 35 |
Hopper is a LoRA adapter (rank 16) for
|
|
|
|
| 30 |
|
| 31 |
# Hopper
|
| 32 |
|
| 33 |
+
> **Also in this repository: Hopper 12B (trained).** A LoRA adapter (rank 32) on
|
| 34 |
+
> [`google/gemma-4-12B-it`](https://huggingface.co/google/gemma-4-12B-it), Apache-2.0, on the branch
|
| 35 |
+
> [`hopper-12b`](https://huggingface.co/HopitAI/hopper/tree/hopper-12b) (revision
|
| 36 |
+
> `4b605f25eb903c2cf4d121040ffb097240b3bc37`), with its own model card, readout map, licence and checksums.
|
| 37 |
+
> Serve it with the code at [github.com/hopit-ai/hopper](https://github.com/hopit-ai/hopper) (tag `12b-1.1.0`):
|
| 38 |
+
> `hopper-serve --base-loader gemma-4-12b-it --adapter HopitAI/hopper@4b605f25eb903c2cf4d121040ffb097240b3bc37`
|
| 39 |
+
> plus its readout map (see that branch's card). The files on this `main` branch are the original 4B Hopper
|
| 40 |
+
> described below.
|
| 41 |
+
|
| 42 |
> **Research and demo use only.** This adapter is published for research and demonstration. Its training data included passages from RACE (via the `cais/mmlu` auxiliary set), which its authors release for non-commercial research only and whose terms extend to derived data. Do not use this adapter commercially. A version trained without these passages is in development.
|
| 43 |
|
| 44 |
Hopper is a LoRA adapter (rank 16) for
|