|
Download MODIFICATIONS.md from EliovpAI/MiniMax-H3-Image-FP8-Paiton-RDNA4: direct link, hf CLI and curl.
- Browser
- Download file 2.02 kB
-
https://huggingface.co/EliovpAI/MiniMax-H3-Image-FP8-Paiton-RDNA4/resolve/main/MODIFICATIONS.md
- Command line
-
hf download hf://EliovpAI/MiniMax-H3-Image-FP8-Paiton-RDNA4/MODIFICATIONS.md
-
curl -L -o MODIFICATIONS.md https://huggingface.co/EliovpAI/MiniMax-H3-Image-FP8-Paiton-RDNA4/resolve/main/MODIFICATIONS.md
2.02 kB
| # Modified files | |
| Every file below except `tokenizer/tokenizer.json` is a modified file of MiniMax-H3-Image (Section III.2 of the | |
| MiniMax-H3-Image Community License). Source: [MiniMaxAI/MiniMax-H3-Image](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image/tree/00dd081ebdd33315adf2c4d84f64aa327ddf3039), | |
| revision `00dd081ebdd33315adf2c4d84f64aa327ddf3039`. Changes made by ElioVP (Paiton), 11 Nov 2026. | |
| | File | Made from | Change | | |
| | --- | --- | --- | | |
| | `dit/dit.bin`, `dit/dit.idx` | `transformer/`, `pdd_fused_heads.safetensors`, `pdd_config.json` | The attention and feed-forward projections of the 50 transformer blocks and the 2 token-refiner blocks are rounded to FP8 (e4m3) with one scale per output channel, using GPTQ rounding calibrated on 887,724 tokens from 18 prompts. Rows are reordered for the Paiton kernels. The timestep embedding and the AdaLN and output-norm modulation are evaluated in advance for the fixed 6-step schedule and stored as tables. The input, output and text projections are stored in float32. Packed into one file with an index. | | |
| | `dit/vae_latents.bin` | `vae/config.json` | The latent mean and standard deviation, as float32 | | |
| | `te/L00.bin` to `te/L49.bin` | `text_encoder/` | Decoder layers 0 to 49 of the Qwen3-VL text encoder, projections rounded to FP8 (e4m3) with one scale per output channel (round to nearest); the other layer weights are repacked unchanged. Layers 50 to 63 and the language-model head are left out because the model reads the hidden state after layer 50. | | |
| | `te/embed.bf16`, `te/vision.bin` | `text_encoder/` | Token embedding and vision tower, bf16, repacked | | |
| | `vae/dec8.bin` | `vae/diffusion_pytorch_model.safetensors` | VAE decoder, block weights in int8 with one scale per output channel, the rest in bf16 and float32; `post_quant_conv` folded into the input projection | | |
| | `vae/enc.bin` | `vae/diffusion_pytorch_model.safetensors` | VAE encoder in bf16 and float32, repacked | | |
| | `tokenizer/tokenizer.json` | `tokenizer/tokenizer.json` | Unmodified | | |