Rewrite model card in plain language

README.md

@@ -16,11 +16,11 @@ tags:
 
 # Sol Lassi 600K
 
-Sol Lassi is a 600,000-parameter experiment in training a language model with M-SimOW. It runs with MLX on Apple Silicon. Training started from scratch and used 1 billion token exposures.
+Lassi is an M-SimOW optimizer experiment: 600,000 parameters, trained from scratch with MLX on Apple Silicon. The run reached 1 billion token exposures using a balanced FinePhrase stream.
 
-Lassi is a base model for text completion. Its size makes it useful for optimizer experiments, but completions can repeat, lose coherence, or give incorrect answers. It hasn't been instruction-tuned.
+There are no Open SLM, ArithMark, or Intelligence Index results for this checkpoint. The available loss logs come from individual training minibatches; they don't measure held-out performance.
 
-## Model details
+## Model and training settings
 
 | Setting | Value |
 |---|---|
@@ -35,9 +35,13 @@ Lassi is a base model for text completion. Its size makes it useful for optimize
 | Training exposures | 1,000,000,000 |
 | Weights | MLX NPZ |
 
-## Run a completion
+The data uses FinePhrase's `faq`, `math`, `table`, and `tutorial` configurations. `FinePhrase-balanced-500m-2k-v2` records 500M stream tokens, while the run accumulated 1B exposures.
 
-Download the repository and install the dependencies in `requirements.txt`. Add the downloaded directory to Python's path before importing the loader:
+We trained with 128-token sequences, batch size 32, and seed 7. M-SimOW used momentum beta 0.8 and decoupled weight decay 0.1. The learning rate was 0.006 for the first 500M exposures and 0.003 for the remaining 500M.
+
+## Load and generate
+
+Download the repository, install `requirements.txt`, and add the downloaded directory to Python's import path:
 
 ```bash
 pip install -r requirements.txt
@@ -55,18 +59,10 @@ model, tokenizer = load_model(model_dir)
 print(generate(model, tokenizer, "A tiny language model can", max_new_tokens=48))
 ```
 
-## Data and optimizer settings
-
-Training used a balanced FinePhrase stream from the `faq`, `math`, `table`, and `tutorial` configurations. The FinePhrase-balanced-500m-2k-v2 manifest has 500M stream tokens; the run accumulated 1B exposures.
-
-The sequence length was 128 tokens, with a batch size of 32 and seed 7. M-SimOW used momentum beta 0.8 and decoupled weight decay 0.1. The first 500M exposures used a learning rate of 0.006, followed by 0.003 for the remaining 500M.
-
-## What has been measured
-
-This repository doesn't include an Open SLM, ArithMark, or Intelligence Index evaluation. The loss logs record individual training minibatches, so they don't give a held-out score.
+Lassi is a base model for optimizer tests, with no instruction tuning. Generated text may repeat, stop making sense, or state incorrect facts.
 
 ## Files and license
 
-The weights are in `model.npz`. `modeling_sol_lassi.py` supplies the loader and generator and depends on `keystone_mlx/`. The repository also has the tokenizer and architecture configuration, with run metadata in `training_state.json`.
+`model.npz` contains the weights. The loader and generator in `modeling_sol_lassi.py` depend on `keystone_mlx/`. The tokenizer and architecture configuration are included; `training_state.json` records the run.
 
-The model uses [CC BY 4.0](LICENSE). FinePhrase and its source datasets keep their own terms.
+[CC BY 4.0](LICENSE) covers the model. FinePhrase and its source datasets retain their own terms.