Update README.md

README.md

@@ -1,6 +1,34 @@
 ---
 license: apache-2.0
 ---
+# First off, progress report
+
+As disappointing at this is, **I could not fully converge the geolip-svd-transformer yet**.
+
+I deeply apologize for my inability to handle this task, and I will be doing my very best to implement the structure in a unilaterally useful
+scaling methodology using synthetic pretrained information as guideposts.
+
+I have NOT given up this structure. I am expanding the entire differentiation underlying the system.
+
+I have begun a heavy series of sweeps to test huge amounts of synthetic shapes, structural variances, coloration differentiations, and structural variants
+in a series of intended pretrain convergences that will manifest into the synthetic pixel solver structure.
+
+These weight sets will begin in notebook form, and evolve into structural SVD weight infusions that will intentionally
+amplify learning speed to introduce huge amounts of potential autosolving encoder structures intentionally targeting
+very very small sizes.
+
+INTENTIONALLY small. These are going to be imperfect, but there will be MANY OPTIONS.
+
+The "auto" spectrum will have a series of prefabricated "init" spectrums, intentionally meant to allow
+skipping huge amounts of early pretraining using organized spectral attuned SVD attenuation mechanisms.
+
+There will be multiple capable patchworks, multiple capable potentials, and multiple capable substructure options
+each with their own benefits, own negatives, and own convergence speeds.
+
+The goal here, is to synthetic shape expand the structural invariance of systems like this, to introduce
+prefabricated utility-driven patchworks using SVD as a catalyst.
+
+
 # geolip-svd-transformer API
 
 ```python
@@ -69,31 +97,44 @@ former = svd_transformer(
 
 )
 ```
+# What Works
 
-There are multiple torch-access components meant to be utilized with this structure, so be aware there will be many ways to use this transformer in line with 
-torch standard use. There is no rigid backing structure to it, just install the geolip-core and you're set - once I actually get the experimental branch live.
+**Huggingface Transformers**
+If you snap transformers to process the tokens, it will work. Transformers are a beast and have tons of years of power capacity. 
+Using huggingface transformers will definitely work as a setting, they just add substantial overhead and eliminate a piece of the experiment.
 
-As disappointing at this is, **I could not converge the geolip-svd-transformer yet**.
+**Conv2d, Conv3d**
+Using CONV will definitely work as a setting. The convergence is high accuracy when correctly aligned with Cifar100, TinyImageNet, Imagenet128, and multiple datasets.
 
-I deeply apologize for my inability to handle this task, and I will be doing my very best to implement the structure in a unilaterally useful
-scaling methodology using synthetic pretrained information as guideposts.
+**Kymatio Scatterpoint2D**
+This requires some conv but not much, and this produces corresponding powerhouse behavior stronger than Conv alone when adjudicating large amounts of
+SVD information with the attention alignment spectrum.
 
-I have NOT given up this structure. I am expanding the entire differentiation underlying the system.
+# What Needs To Work
+**Using MLP will reach fair accuracy and not use CONV or TRANSFORMERS.**
+I have seen **around 60% on cifar100** with no traditional encoders, but the system was crutching the M_path to fill the gaps after enough epochs of the SVD path.
+This structure is under the microscope now.
 
-I have begun a heavy series of sweeps to test huge amounts of synthetic shapes, structural variances, coloration differentiations, and structural variants
-in a series of intended pretrain convergences that will manifest into the synthetic pixel solver structure.
+Instability allows SGD optimization to heavily benefit some image tasks while it fails completely on text tasks.
 
-These weight sets will begin in notebook form, and evolve into structural SVD weight infusions that will intentionally
-amplify learning speed to introduce huge amounts of potential autosolving encoder structures intentionally targeting
-very very small sizes.
+**Out Projection SUVt tokens are iffy**
+The out projection is an MLP multiscale projection that took a while to set up, and it produces approximate transformer QKV with useful SUVt tokens downstream. 
 
-INTENTIONALLY small. These are going to be imperfect, but there will be MANY OPTIONS.
+**Many activations corrupt geometry**
+They are in there for experimentation. Feel free to experiment.
 
-The "auto" spectrum will have a series of prefabricated "init" spectrums, intentionally meant to allow
-skipping huge amounts of early pretraining using organized spectral attuned SVD attenuation mechanisms.
+**without the expanded triton core spectrum larger systems suffer with triton**
+Claude code is having trouble with this one as a full task, I'll need to build it in pieces. I've had OpenClaw working on it but the outcome
+isn't looking good. The 4x4 and 5x4 won't converge, while the 6x6 crashes the system entirely instead of building it.
 
-There will be multiple capable patchworks, multiple capable potentials, and multiple capable substructure options
-each with their own benefits, own negatives, and own convergence speeds.
+I'll need to wait for a fix for claude code, this is a known issue apparently.
 
-The goal here, is to synthetic shape expand the structural invariance of systems like this, to introduce
-prefabricated utility-driven patchworks using SVD as a catalyst.
+
+## Additionally
+
+There are multiple torch-access components meant to be utilized with this structure, so be aware there will be many ways to use this transformer in line with 
+torch standard use. There is no rigid backing structure to it, just install the geolip-core and you're set - once I actually get the experimental branch live.
+
+Claude loves to inline invalid eigh gram svd instead of actually using the imports, so I need to make sure claude respects the structure every single time.
+
+Experiments are slow going, I need more hardware.