The weights are bfloat16 now; say so instead of explaining float32

README.md

@@ -51,10 +51,13 @@ out = model.generate(inputs["input_ids"].to("cuda"), max_new_tokens=128)
 print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
 ```
 
-`dtype=torch.bfloat16` is worth passing explicitly. The weights are stored as
-float32 because the release verification compares logits exactly and that
-comparison is only meaningful in float32; the model was trained in bfloat16 and
-loses nothing by being loaded that way.
+The weights are stored in bfloat16, the precision the model was trained in and the
+precision the forward pass casts to regardless. They were published as float32 at first,
+because release verification compares logits exactly and that is only meaningful in float32 —
+but that made the files twice the size for no information: 47% of the parameters were already
+bfloat16-exact, and under bfloat16 the two files produce bitwise identical logits. Loading in
+float32 is still possible and shifts the top-8 probabilities by up to 1.7e-03, a mode the
+model was never trained in.
 
 Measured on a single RTX 5070 (12 GB, SDPA path): **~91 tokens/second**, ~3.3 GB
 resident.