Update live comparison for TR-Hash 500M
Browse files- README.md +5 -3
- index.html +6 -3
README.md
CHANGED
|
@@ -19,13 +19,15 @@ The Space provides:
|
|
| 19 |
- an architecture explorer for the shared SwiGLU and fixed top-2 residual path;
|
| 20 |
- checkpoint-derived tokenizer IDs and expert assignments for selected tokens;
|
| 21 |
- the reported matched-run measurements and their stated limitations;
|
| 22 |
-
- live side-by-side SSE generation from `Pacific-i64/TR-MOE-
|
| 23 |
|
| 24 |
-
The
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## Sources
|
| 27 |
|
| 28 |
- [Paper and reproducibility artifacts](https://github.com/Complexity-ML/tmlr-paper-pool)
|
| 29 |
-
- [TR-MOE-
|
| 30 |
- [Dense-306](https://huggingface.co/Pacific-i64/Dense-306)
|
| 31 |
- [vllm-i64](https://github.com/Complexity-ML/vllm-i64)
|
|
|
|
| 19 |
- an architecture explorer for the shared SwiGLU and fixed top-2 residual path;
|
| 20 |
- checkpoint-derived tokenizer IDs and expert assignments for selected tokens;
|
| 21 |
- the reported matched-run measurements and their stated limitations;
|
| 22 |
+
- live side-by-side SSE generation from `Pacific-i64/TR-HASH-MOE-500M-HF` and `Pacific-i64/Dense-306`.
|
| 23 |
|
| 24 |
+
The historical measurements remain the matched 306.5M study. The live panel now
|
| 25 |
+
compares the current 492.1M TR-Hash release with Dense-306, so its outputs are a
|
| 26 |
+
non-iso-parameter qualitative inspection and not additional experimental evidence.
|
| 27 |
|
| 28 |
## Sources
|
| 29 |
|
| 30 |
- [Paper and reproducibility artifacts](https://github.com/Complexity-ML/tmlr-paper-pool)
|
| 31 |
+
- [TR-HASH-MOE-500M-HF](https://huggingface.co/Pacific-i64/TR-HASH-MOE-500M-HF)
|
| 32 |
- [Dense-306](https://huggingface.co/Pacific-i64/Dense-306)
|
| 33 |
- [vllm-i64](https://github.com/Complexity-ML/vllm-i64)
|
index.html
CHANGED
|
@@ -557,13 +557,13 @@
|
|
| 557 |
</div>
|
| 558 |
<div class="card">
|
| 559 |
<div class="tr-run-head">
|
| 560 |
-
<strong>TR-MOE-
|
| 561 |
<span class="viz-badge" data-routed-state>ready</span>
|
| 562 |
</div>
|
| 563 |
<p class="tr-generation" data-routed-output aria-live="polite">Token-routed output will stream here token by token.</p>
|
| 564 |
</div>
|
| 565 |
</div>
|
| 566 |
-
<div class="tr-status text-small" data-status>
|
| 567 |
</section>
|
| 568 |
</div>
|
| 569 |
|
|
@@ -747,7 +747,7 @@
|
|
| 747 |
denseState.textContent = "connecting";
|
| 748 |
routedState.textContent = "connecting";
|
| 749 |
runButton.textContent = "Stop generation";
|
| 750 |
-
status.textContent = "Connecting to
|
| 751 |
status.classList.add("is-live");
|
| 752 |
|
| 753 |
try {
|
|
@@ -758,6 +758,9 @@
|
|
| 758 |
prompt,
|
| 759 |
max_tokens: 128,
|
| 760 |
temperature: 0.7,
|
|
|
|
|
|
|
|
|
|
| 761 |
stream: true
|
| 762 |
}),
|
| 763 |
signal: controller.signal
|
|
|
|
| 557 |
</div>
|
| 558 |
<div class="card">
|
| 559 |
<div class="tr-run-head">
|
| 560 |
+
<strong>TR-HASH-MOE-500M</strong>
|
| 561 |
<span class="viz-badge" data-routed-state>ready</span>
|
| 562 |
</div>
|
| 563 |
<p class="tr-generation" data-routed-output aria-live="polite">Token-routed output will stream here token by token.</p>
|
| 564 |
</div>
|
| 565 |
</div>
|
| 566 |
+
<div class="tr-status text-small" data-status>TR-Hash 492.1M vs Dense 306.5M · non-iso-parameter qualitative comparison</div>
|
| 567 |
</section>
|
| 568 |
</div>
|
| 569 |
|
|
|
|
| 747 |
denseState.textContent = "connecting";
|
| 748 |
routedState.textContent = "connecting";
|
| 749 |
runButton.textContent = "Stop generation";
|
| 750 |
+
status.textContent = "Connecting to TR-Hash 492.1M and Dense 306.5M CPU endpoints…";
|
| 751 |
status.classList.add("is-live");
|
| 752 |
|
| 753 |
try {
|
|
|
|
| 758 |
prompt,
|
| 759 |
max_tokens: 128,
|
| 760 |
temperature: 0.7,
|
| 761 |
+
top_k: 40,
|
| 762 |
+
top_p: 0.9,
|
| 763 |
+
repetition_penalty: 1.1,
|
| 764 |
stream: true
|
| 765 |
}),
|
| 766 |
signal: controller.signal
|