Commit ·
7cc6d57
1
Parent(s): b4eea2a
Add PTE files for context sizes 2048, 4096, 8192
Browse files- Llama-3-Soliloquy-8B-v2_kv_sdpa_xnn_qe_4_32_ctx2048.pte → Llama-3-Soliloquy-8B-v2_kv2_sdpa_xnn_qe_4_32_ctx2048.pte +2 -2
- Llama-3-Soliloquy-8B-v2_kv_sdpa_xnn_qe_4_32_ctx4096.pte → Llama-3-Soliloquy-8B-v2_kv2_sdpa_xnn_qe_4_32_ctx4096.pte +2 -2
- Llama-3-Soliloquy-8B-v2_kv_sdpa_xnn_qe_4_32_ctx8192.pte → Llama-3-Soliloquy-8B-v2_kv2_sdpa_xnn_qe_4_32_ctx8192.pte +2 -2
Llama-3-Soliloquy-8B-v2_kv_sdpa_xnn_qe_4_32_ctx2048.pte → Llama-3-Soliloquy-8B-v2_kv2_sdpa_xnn_qe_4_32_ctx2048.pte
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca26494930fe8f5b08ff1e90d4d1243b68bfff782c26a1afe0e43b188128298e
|
| 3 |
+
size 4169560736
|
Llama-3-Soliloquy-8B-v2_kv_sdpa_xnn_qe_4_32_ctx4096.pte → Llama-3-Soliloquy-8B-v2_kv2_sdpa_xnn_qe_4_32_ctx4096.pte
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97fc265ac787eb1888a325252d06577ec40ac3fdeeb1d076812288067e3849cc
|
| 3 |
+
size 4171657888
|
Llama-3-Soliloquy-8B-v2_kv_sdpa_xnn_qe_4_32_ctx8192.pte → Llama-3-Soliloquy-8B-v2_kv2_sdpa_xnn_qe_4_32_ctx8192.pte
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0008a939024f1dc1d52ad0d878969ac1cce004912a160477d725e7aacd4a82c1
|
| 3 |
+
size 4175852192
|