Card: research notes moved to moss-image-mlx/research/turbo

README.md

@@ -21,7 +21,7 @@ tags:
 
 A fast sampler for [OpenMOSS-Team/MOSS-Image-SFT](https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT) on Macs. It uses **15 network passes instead of 100**: about **2 minutes** per ~1 MP image on an M4 Pro instead of about 12½ (**6.2×**). It stays close to the image the full 50-step model draws for the same seed, including its textures and lettering.
 
-**Code:** [moss-image-mlx](https://github.com/felix-ab/moss-image-mlx) (`--turbo`) · **Write-up:** [how I designed and measured it](https://github.com/felix-ab/moss-image-turbo-research/blob/main/docs/technical-writeup.md) · **Base tiers:** [8bit](https://huggingface.co/VisualInference/MOSS-Image-SFT-MLX-8bit), [compact](https://huggingface.co/VisualInference/MOSS-Image-SFT-MLX-compact)
+**Code:** [moss-image-mlx](https://github.com/felix-ab/moss-image-mlx) (`--turbo`) · **Write-up:** [how I designed and measured it](https://github.com/felix-ab/moss-image-mlx/blob/main/research/turbo/docs/technical-writeup.md) · **Base tiers:** [8bit](https://huggingface.co/VisualInference/MOSS-Image-SFT-MLX-8bit), [compact](https://huggingface.co/VisualInference/MOSS-Image-SFT-MLX-compact)
 
 ![Wet river pebbles at actual size: the full model at 50 steps above, --turbo below, same prompt and seed](assets/hero.jpg)
 
@@ -62,7 +62,7 @@ I compared `--turbo` with the full model's own image (50 steps, CFG 3, with the
 | Brightness, relative to the full model | +0.011 | 0 |
 | English text read back correctly by OCR (n = 4) | 94.7% | 93.4% |
 
-The package's sampler reproduces the research images bit for bit. [how-the-numbers-work.md](https://github.com/felix-ab/moss-image-turbo-research/blob/main/docs/how-the-numbers-work.md) defines each measure.
+The package's sampler reproduces the research images bit for bit. [how-the-numbers-work.md](https://github.com/felix-ab/moss-image-mlx/blob/main/research/turbo/docs/how-the-numbers-work.md) defines each measure.
 
 ![Four pairs, full model left and --turbo right, same seed: a beekeeper, a novel cover, a Chinese tea wrapper and a croissant](assets/pairs.jpg)
 
@@ -81,7 +81,7 @@ Training cost about $37 on rented A100s.
 
 ![Lichen on a stone wall: the full model, then the full model's saved states after 42, 35 and 14 steps finished with 2, 3 and 6 DMD steps](assets/repetition_test.jpg)
 
-So this LoRA learns to follow the full model's own path for each seed, and the full model finishes the image. The [technical write-up](https://github.com/felix-ab/moss-image-turbo-research/blob/main/docs/technical-writeup.md) has the evidence for each decision and what failed; the [research repo](https://github.com/felix-ab/moss-image-turbo-research) has the full lab notebook.
+So this LoRA learns to follow the full model's own path for each seed, and the full model finishes the image. The [technical write-up](https://github.com/felix-ab/moss-image-mlx/blob/main/research/turbo/docs/technical-writeup.md) has the evidence for each decision and what failed; the [research repo](https://github.com/felix-ab/moss-image-mlx/tree/main/research/turbo) has the full lab notebook.
 
 ## Limitations