|
Download BASE-MODIFICATIONS.md from Avdpro/Meridian-H3-8bit-MLX: direct link, hf CLI and curl.
- Browser
- Download file 1.63 kB
-
https://huggingface.co/Avdpro/Meridian-H3-8bit-MLX/resolve/main/BASE-MODIFICATIONS.md
- Command line
-
hf download hf://Avdpro/Meridian-H3-8bit-MLX/BASE-MODIFICATIONS.md
-
curl -L -o BASE-MODIFICATIONS.md https://huggingface.co/Avdpro/Meridian-H3-8bit-MLX/resolve/main/BASE-MODIFICATIONS.md
1.63 kB
| # Modifications to MiniMax H3 | |
| These files are MODIFIED versions of the MiniMax H3 Works, redistributed under | |
| the MiniMax H3 Community License Agreement (see LICENSE and NOTICE). | |
| Modified by: mlx-serve (https://github.com/ddalcu/mlx-serve) | |
| What changed: | |
| * `transformer.safetensors` and `text_encoder.safetensors` are QUANTIZED from | |
| the original bfloat16 releases to MLX affine 8-bit, group size 64. Gathered | |
| embedding tables and the checkpoint's fp32 islands (patch projections, output | |
| heads, time embedder, rope inverse frequencies) are left dense. | |
| * `video_vae.safetensors` and `audio_vae.safetensors` are byte-for-byte copies | |
| of the originals, unmodified. | |
| * The tokenizer files are byte-for-byte copies from `MiniMaxAI/MiniMax-H3` | |
| (`FL2VA/processor/`), relocated into this directory so the model is | |
| self-contained. | |
| * `config.json` is new, written by mlx-serve's converter to describe the | |
| layout above. It is not from the original release. | |
| * `turbo_lora.safetensors` is NOT from MiniMax and is not a modification of | |
| their Works. It is an unmodified, renamed copy of | |
| `minimax_h3_turbo_4step_ema_ckpt850.safetensors` from | |
| https://huggingface.co/larryvrh/MiniMax-H3-Turbo-Lora, Copyright (c) | |
| larryvrh, licensed under the Apache License, Version 2.0. Being a LoRA | |
| trained on MiniMax H3, it is also a derivative of the Works and remains | |
| subject to the MiniMax H3 Community License Agreement. | |
| No MiniMax weights were retrained, distilled, pruned or otherwise altered | |
| beyond the numeric quantization described above. The Turbo adapter is a | |
| separate file that is added at runtime; it does not modify them. | |