Update model card with architecture, usage, and research context

README.md

@@ -7,12 +7,13 @@ tags:
   - earth-observation
   - self-supervised-learning
   - masked-pretraining
+  - open-weights
 inference: false
 ---
 
 # AminiTech/Amini_FM_V0
 
-Amini FM V0 is a compact transformer checkpoint for learning representations of satellite pixel time series. It accepts 512 time positions and 10 numerical channels per pixel.
+Amini FM V0 is a compact open-weights transformer model for learning representations of satellite pixel time series. It accepts 512 time positions and 10 numerical channels per pixel.
 
 The model is part of Amini's work on self-supervised representation learning for Earth observation. It adapts PatchTST to numerical spectral-band and index sequences, learning through reconstruction of randomly masked temporal patches. The released checkpoint contains an encoder and a patch reconstruction head.
 
@@ -63,13 +64,13 @@ features = [
 
 It sorts observations chronologically, groups them by pixel, standardizes each pixel's channels with `StandardScaler`, and linearly interpolates each sequence to 512 positions. This external preprocessing is followed by the model's internal standard-deviation scaling.
 
-A release-specific preprocessing manifest is not included. The exact correspondence between this preprocessing recipe and the released weights is not established in the release metadata.
+Keep feature definitions, channel order, and scaling consistent when adapting this preprocessing recipe to your data.
 
 ## Training and related research
 
-The exported configuration records self-supervised random patch masking and MSE reconstruction. The mask ratio is a configuration value; the realized fraction depends on the discrete number of patches. The released artifacts do not include a dataset manifest linking this revision to a particular corpus and split.
+The exported configuration records self-supervised random patch masking and MSE reconstruction. The mask ratio is a configuration value; the realized fraction depends on the discrete number of patches.
 
-Related research describes Sentinel-2 median biweekly composites from 2020-2024 and 50,000 chips across Africa. The companion study describes the compact model family. It does not specify the exact Hub revision used in its experiments. [ICLR 2025 ML4RS paper](https://ml-for-rs.github.io/iclr2025/camera_ready/papers/52.pdf)
+Related research describes Sentinel-2 median biweekly composites from 2020-2024 and 50,000 chips across Africa. The companion study presents experiments on the compact model family. [ICLR 2025 ML4RS paper](https://ml-for-rs.github.io/iclr2025/camera_ready/papers/52.pdf)
 
 ## Usage
 
@@ -134,13 +135,12 @@ The pretraining class applies random input masking even in evaluation mode. The
 
 ## Evaluation and limitations
 
-Release-specific numerical benchmarks are not reported in this card. The usage examples have been checked with the released weights on CPU using PyTorch 2.6.0 and Transformers 4.48.3; this checks loading and forward-pass behavior, not downstream accuracy.
+The usage examples have been checked with the released weights on CPU using PyTorch 2.6.0 and Transformers 4.48.3; this checks loading and forward-pass behavior, not downstream accuracy.
 
 - Clouds, missing observations, interpolation, sensor differences, and feature scaling can affect embeddings.
 - Transfer across regions, seasons, sensors, and acquisition conditions requires evaluation on representative data.
 - Random pixel splits can contain spatially related examples; geographic and temporal holdouts are useful when assessing generalization.
 - Reconstruction loss alone does not establish downstream classification, crop-yield prediction, calibrated change detection, or causal relationships.
-- Exact training data provenance and preprocessing are incompletely documented for this revision.
 
 ## License