Re-convert with fixed rotary q/k permutation (baseRT-internal#114); NIAH-validated at 2k/8k. Q4 now uses the default-q4 quality profile (embeddings/head at higher precision).
Browse files
Llama-3.2-3B-Instruct-Q8.base
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3320125440
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b26f0dd86648cec9d1f7f30dbf986c59077395dffe8607a28640a2e8d251177a
|
| 3 |
size 3320125440
|