Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: nvidia/Llama-3.1-NemoGuard-8B-Topic-Control
|
| 4 |
+
tags: [qualcomm, hexagon, npu, qnn, qhexrt, v81, llama, guardrail, topic-control]
|
| 5 |
+
---
|
| 6 |
+
# Llama-3.1-NemoGuard-8B-Topic-Control — Hexagon NPU (v81)
|
| 7 |
+
QHexRT-runnable, arch-pinned QNN bundle of NVIDIA's NemoGuard topic-control guardrail for **Hexagon v81**
|
| 8 |
+
(SM8850, soc_model 87). LoRA on Llama-3.1-8B-Instruct, merged onto an ungated base, converted via QHexRT's
|
| 9 |
+
**dense decode-split** (8 chained `decode_p*` parts + `llama_generate_sharded`). **Device-validated W8
|
| 10 |
+
greedy-EXACT vs HF gold @ ~3.6 tok/s.** See `runanywhere/nemotron_nano_8b_HNPU` for the run recipe.
|