Update model card and export table

README.md

@@ -64,7 +64,8 @@ never modified or removed.
 
 | Export | Tokens | Step | Size | val_mix (nats/token) | 0-shot macro | 5-shot macro | Exported (UTC) |
 |---|---:|---:|---:|---:|---:|---:|---|
-| [`127B-tokens_step13242`](https://huggingface.co/chutesai/parallax-8b-lambda/tree/main/exports/127B-tokens_step13242) **(latest)** | 127.7B | 13242 | 2.48 GB | - | - | - | 2026-10-05 02:12 |
+| [`132B-tokens_step13524`](https://huggingface.co/chutesai/parallax-8b-lambda/tree/main/exports/132B-tokens_step13524) **(latest)** | 132.5B | 13524 | 2.47 GB | - | - | - | 2026-10-05 02:48 |
+| [`127B-tokens_step13242`](https://huggingface.co/chutesai/parallax-8b-lambda/tree/main/exports/127B-tokens_step13242) | 127.7B | 13242 | 2.48 GB | - | - | - | 2026-10-05 02:12 |
 | [`123B-tokens_step13016`](https://huggingface.co/chutesai/parallax-8b-lambda/tree/main/exports/123B-tokens_step13016) | 123.6B | 13016 | 2.48 GB | - | - | - | 2026-10-05 01:43 |
 | [`119B-tokens_step12790`](https://huggingface.co/chutesai/parallax-8b-lambda/tree/main/exports/119B-tokens_step12790) | 119.5B | 12790 | 2.48 GB | - | - | - | 2026-10-05 01:13 |
 | [`115B-tokens_step12532`](https://huggingface.co/chutesai/parallax-8b-lambda/tree/main/exports/115B-tokens_step12532) | 115.4B | 12532 | 2.48 GB | - | - | - | 2026-10-05 00:38 |
@@ -114,11 +115,11 @@ never modified or removed.
 
 ## Latest export
 
-`exports/127B-tokens_step13242`: 127.7B training tokens, step 13242.
+`exports/132B-tokens_step13524`: 132.5B training tokens, step 13524.
 
 ```bash
-hf download chutesai/parallax-8b-lambda --include "exports/127B-tokens_step13242/*" --local-dir parallax-8b-lambda
-cd parallax-8b-lambda/exports/127B-tokens_step13242
+hf download chutesai/parallax-8b-lambda --include "exports/132B-tokens_step13524/*" --local-dir parallax-8b-lambda
+cd parallax-8b-lambda/exports/132B-tokens_step13524
 tar -xf packed_experts.tar
 sha256sum -c --quiet SHA256SUMS   # every file of the original export, byte for byte
 ```
@@ -185,4 +186,4 @@ alignment or safety tuning, and it is small and far from converged.
 
 MIT.
 
-<sub>Table updated 2026-10-05 02:21 UTC.</sub>
+<sub>Table updated 2026-10-05 02:56 UTC.</sub>