Add model card with the MiniMax-H3 Community License
Browse files
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: minimax-h3-community-license-agreement
|
| 4 |
+
license_link: https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE
|
| 5 |
+
base_model: MiniMaxAI/MiniMax-H3
|
| 6 |
+
base_model_relation: quantized
|
| 7 |
+
tags: [nf4, lora-training]
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# MiniMax-H3 — NF4 for LoRA training
|
| 11 |
+
|
| 12 |
+
NF4 (4-bit) version of [MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3) (transformer, Qwen3-VL-32B text encoder and VAEs, 41 GB instead of 498 GB), used by [AcademiaSD LoRAlab Trainer Studio](https://github.com/AcademiaSD/AcademiaSD_LoRAlab-TrainerStudio) to train MiniMax-H3 LoRAs and RefMods on consumer GPUs. The trainer downloads it automatically.
|
| 13 |
+
|
| 14 |
+
These weights are a derivative of MiniMax-H3 and are distributed under the same **MiniMax-H3 Community License Agreement**. Read it before using the model or the LoRAs trained with it.
|