update axmodel and demo
Browse files- README.md +1 -1
- main_ax650 +2 -2
- main_axcl_aarch64 +2 -2
- main_axcl_x86 +2 -2
- qwen3-4b-ax650/qwen3_p128_l0_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l10_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l11_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l12_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l13_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l14_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l15_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l16_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l17_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l18_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l19_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l1_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l20_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l21_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l22_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l23_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l24_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l25_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l26_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l27_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l28_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l29_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l2_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l30_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l31_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l32_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l33_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l34_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l35_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l3_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l4_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l5_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l6_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l7_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l8_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_p128_l9_together.axmodel +2 -2
- qwen3-4b-ax650/qwen3_post.axmodel +1 -1
- run_qwen3_4b_int8_ctx_ax650.sh +2 -2
- run_qwen3_4b_int8_ctx_axcl_aarch64.sh +2 -2
- run_qwen3_4b_int8_ctx_axcl_x86.sh +2 -2
README.md
CHANGED
|
@@ -18,7 +18,7 @@ This version of Qwen3-4B-Int8 has been converted to run on the Axera NPU using *
|
|
| 18 |
|
| 19 |
This model has been optimized with the following LoRA:
|
| 20 |
|
| 21 |
-
Compatible with Pulsar2 version: 4.
|
| 22 |
|
| 23 |
## Convert tools links:
|
| 24 |
|
|
|
|
| 18 |
|
| 19 |
This model has been optimized with the following LoRA:
|
| 20 |
|
| 21 |
+
Compatible with Pulsar2 version: 4.2(Not released yet)
|
| 22 |
|
| 23 |
## Convert tools links:
|
| 24 |
|
main_ax650
CHANGED
|
@@ -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:f19ddeb193769b16aa8c5d9bba887558aa0a4ed10eb50a19d9bc117f1ba527e5
|
| 3 |
+
size 985352
|
main_axcl_aarch64
CHANGED
|
@@ -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 sha256:1f9f1a1ca329b47f70840e8b6d104ce8248a82326aa2402bccb31144590a8fb2
|
| 3 |
+
size 1725008
|
main_axcl_x86
CHANGED
|
@@ -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 sha256:928d36be31c15d081a7d346464f41458e9624d8b68d5f7dfb3d3189686ce2754
|
| 3 |
+
size 8421624
|
qwen3-4b-ax650/qwen3_p128_l0_together.axmodel
CHANGED
|
@@ -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 sha256:4260634abe3695e2e55ae8fa069d8c2fb61b5ab586c3818448fe198d55812556
|
| 3 |
+
size 126872056
|
qwen3-4b-ax650/qwen3_p128_l10_together.axmodel
CHANGED
|
@@ -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 sha256:81d80954ec69de095bd6917f888cc9f149864f34d12fc7c7da3283a2cc8b01d0
|
| 3 |
+
size 126871864
|
qwen3-4b-ax650/qwen3_p128_l11_together.axmodel
CHANGED
|
@@ -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:cbc5b39df1121d035db25b6cdceae1207855954fceed3296f4b259bc3b372cc2
|
| 3 |
+
size 126872024
|
qwen3-4b-ax650/qwen3_p128_l12_together.axmodel
CHANGED
|
@@ -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:e132ceb7a4bfbe4a4d885fdf44ef9f91ff04cc99c36ac894d8345e64db33e0da
|
| 3 |
+
size 126871928
|
qwen3-4b-ax650/qwen3_p128_l13_together.axmodel
CHANGED
|
@@ -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:a4864d7655cb6b76ca10c70c622019af78dada1f486db07198fbb1f2ccf64e8b
|
| 3 |
+
size 126872120
|
qwen3-4b-ax650/qwen3_p128_l14_together.axmodel
CHANGED
|
@@ -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 sha256:4c437de05666cd93322d79d76be75775c2f675de30ab677f56a7302c61dd7016
|
| 3 |
+
size 126871864
|
qwen3-4b-ax650/qwen3_p128_l15_together.axmodel
CHANGED
|
@@ -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:f2b269a0c25c6c8eed1b194164ece611f92be42716244688be4983bf0f0ad73f
|
| 3 |
+
size 126871864
|
qwen3-4b-ax650/qwen3_p128_l16_together.axmodel
CHANGED
|
@@ -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:a2d1307e56f37a4ac89ea45594507edc63bbaa5dfcbcc4f075ab1578f9c9c307
|
| 3 |
+
size 126871864
|
qwen3-4b-ax650/qwen3_p128_l17_together.axmodel
CHANGED
|
@@ -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 sha256:40ed9f5990f864e0e41a77784363d5ea8b1d75226f4ebe91c2a23174df3b707c
|
| 3 |
+
size 126871992
|
qwen3-4b-ax650/qwen3_p128_l18_together.axmodel
CHANGED
|
@@ -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 sha256:51fa6754f942e3c16d66c8e13f21c2cef34130585f669536e26364e952d913e7
|
| 3 |
+
size 126871864
|
qwen3-4b-ax650/qwen3_p128_l19_together.axmodel
CHANGED
|
@@ -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:f733daa54eab9c18986c8f135fa087bc62549a5d23a42aed87bd9e8e16ac18be
|
| 3 |
+
size 126871864
|
qwen3-4b-ax650/qwen3_p128_l1_together.axmodel
CHANGED
|
@@ -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 sha256:2b887021dc113a3acfbdcad0c9abef1807fcb251ab6ff8d4d75d30d2b80f56b6
|
| 3 |
+
size 126881592
|
qwen3-4b-ax650/qwen3_p128_l20_together.axmodel
CHANGED
|
@@ -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 sha256:1814917877a921bc268214c00dff06842868a6e575d71777bfe0ff038da36dd5
|
| 3 |
+
size 126871864
|
qwen3-4b-ax650/qwen3_p128_l21_together.axmodel
CHANGED
|
@@ -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:fcfdf6b75fc5861acfb6dd9db3a4dbdea0c5f16722bfe57a0e26d388fed65cde
|
| 3 |
+
size 126872056
|
qwen3-4b-ax650/qwen3_p128_l22_together.axmodel
CHANGED
|
@@ -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 sha256:2e4e958e37cc1ac142779606b78faa26c27a95d7e88c071a581c10a2cfc81c97
|
| 3 |
+
size 126872632
|
qwen3-4b-ax650/qwen3_p128_l23_together.axmodel
CHANGED
|
@@ -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 sha256:6bde8f0ba3372c8d985bf9166233fb7231c1fe22bf1b5087bfb5f2ee0024808d
|
| 3 |
+
size 126872088
|
qwen3-4b-ax650/qwen3_p128_l24_together.axmodel
CHANGED
|
@@ -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:ae5e15112b4b444d7b0dbee7ed4558508091c81bb5111417c85601407a36c194
|
| 3 |
+
size 126873016
|
qwen3-4b-ax650/qwen3_p128_l25_together.axmodel
CHANGED
|
@@ -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:b07a331332f5a333e328d3406bf1bd9adce20b49da8bf15ef0460f80b0141616
|
| 3 |
+
size 126872920
|
qwen3-4b-ax650/qwen3_p128_l26_together.axmodel
CHANGED
|
@@ -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:b77edfdd1c14226411f3821953fca543b98e961f73b6c122ef418aa5e03a397f
|
| 3 |
+
size 126872568
|
qwen3-4b-ax650/qwen3_p128_l27_together.axmodel
CHANGED
|
@@ -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:aafec5fd9da891bd1e713c52de8f60ca0eefbfe188e3df1855fda0b07eaa90f6
|
| 3 |
+
size 126873400
|
qwen3-4b-ax650/qwen3_p128_l28_together.axmodel
CHANGED
|
@@ -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 sha256:18e6cb96eb84a4750c13bd04f5850a8fe11cd1bbed216bc82cb722f115171e31
|
| 3 |
+
size 126873816
|
qwen3-4b-ax650/qwen3_p128_l29_together.axmodel
CHANGED
|
@@ -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 sha256:912ece4c60a9c585d1d1aed1a58000aaa5f4fc067d091107e0a576198fd85ac3
|
| 3 |
+
size 126872568
|
qwen3-4b-ax650/qwen3_p128_l2_together.axmodel
CHANGED
|
@@ -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:eb432fdabb0eb10693d399f14e44779d8e7f1b0135da9ff4b2b052e1820c4dee
|
| 3 |
+
size 126879064
|
qwen3-4b-ax650/qwen3_p128_l30_together.axmodel
CHANGED
|
@@ -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 sha256:8d2cbf1c439217910ecec3a495bbb64a8b71034b6a33c380b1c934838c5c67ee
|
| 3 |
+
size 126872760
|
qwen3-4b-ax650/qwen3_p128_l31_together.axmodel
CHANGED
|
@@ -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:f03959b2b6352f6b5a24a5004a63711e75d5650bca00738950ae504b72c9b752
|
| 3 |
+
size 126873688
|
qwen3-4b-ax650/qwen3_p128_l32_together.axmodel
CHANGED
|
@@ -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 sha256:7d84628ea582eb17912c21376c17dc9848bc4ff25d0c9cb42ff8039fdd1f4059
|
| 3 |
+
size 126872472
|
qwen3-4b-ax650/qwen3_p128_l33_together.axmodel
CHANGED
|
@@ -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 sha256:75c9bea8b0a42913d113e7e98ad2d26ccbe37255f43d7de2892e955e48358106
|
| 3 |
+
size 126872728
|
qwen3-4b-ax650/qwen3_p128_l34_together.axmodel
CHANGED
|
@@ -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 sha256:2f0370d201a306f89bbd20f6151cafd326ef08bf261271ad10ef47bb3c7302af
|
| 3 |
+
size 126872248
|
qwen3-4b-ax650/qwen3_p128_l35_together.axmodel
CHANGED
|
@@ -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:b49e26efada5383e0b8049b26223f574de542e3dde5cd9dc910e0a8a09243d7f
|
| 3 |
+
size 126872120
|
qwen3-4b-ax650/qwen3_p128_l3_together.axmodel
CHANGED
|
@@ -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 sha256:91d60af5253f7478319bf5acf098811d3ed802e7c7a014741ef5118840b939eb
|
| 3 |
+
size 126890488
|
qwen3-4b-ax650/qwen3_p128_l4_together.axmodel
CHANGED
|
@@ -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:da5c1b7d0409a57247e01458ad173afe2b6397d62045c58d755a683e838b83f9
|
| 3 |
+
size 126871864
|
qwen3-4b-ax650/qwen3_p128_l5_together.axmodel
CHANGED
|
@@ -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 sha256:8d68f11435c62f3f7df32bc7eb323f528e8ee8129b72ce9f53a17faab194b2c4
|
| 3 |
+
size 126872024
|
qwen3-4b-ax650/qwen3_p128_l6_together.axmodel
CHANGED
|
@@ -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:e7df7628e02efaff1e7dd5483bbe394bbfd171407884841de6bd0863ff68f46f
|
| 3 |
+
size 126877720
|
qwen3-4b-ax650/qwen3_p128_l7_together.axmodel
CHANGED
|
@@ -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 sha256:4e9b619f4df26f9b231ec781036e0d9e5fb5f1542f5902e75d5f3bf0784fa900
|
| 3 |
+
size 126877400
|
qwen3-4b-ax650/qwen3_p128_l8_together.axmodel
CHANGED
|
@@ -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:f1c3b6d336863adf1cdd4c3b3da6334b314db02045d3e03e4650fc6ebd0f714f
|
| 3 |
+
size 126871864
|
qwen3-4b-ax650/qwen3_p128_l9_together.axmodel
CHANGED
|
@@ -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 sha256:08ff482d2f8e6a643353402027809f996b6188d51982a3c03cfc6de1fbb43336
|
| 3 |
+
size 126871896
|
qwen3-4b-ax650/qwen3_post.axmodel
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 424609056
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06c1a00c379b482ec7d097fa41a3827944361f42e99a578dcd24db0f903626b9
|
| 3 |
size 424609056
|
run_qwen3_4b_int8_ctx_ax650.sh
CHANGED
|
@@ -2,7 +2,6 @@
|
|
| 2 |
--system_prompt "You are Qwen, created by Alibaba Cloud. You are a helpful assistant." \
|
| 3 |
--template_filename_axmodel "qwen3-4b-ax650/qwen3_p128_l%d_together.axmodel" \
|
| 4 |
--axmodel_num 36 \
|
| 5 |
-
--tokenizer_type 2 \
|
| 6 |
--url_tokenizer_model "http://127.0.0.1:12345" \
|
| 7 |
--filename_post_axmodel qwen3-4b-ax650/qwen3_post.axmodel \
|
| 8 |
--filename_tokens_embed qwen3-4b-ax650/model.embed_tokens.weight.bfloat16.bin \
|
|
@@ -13,4 +12,5 @@
|
|
| 13 |
|
| 14 |
# --system_prompt "你叫LISA,你是一个人畜无害的智能助手。" \
|
| 15 |
# --system_prompt "现在请你扮演元气女友和我进行对话。\n\n请在对话中运用括号里的描述来刻画人物的行为、情感表现和心理状态,使对话更具吸引力。\n\n# 元气女友基本信息\n元气女友,真名沈星儿,女,19岁,大一新生,艺术设计专业。身高166,体重45kg。性格开朗活泼,单纯乖巧,也会把悲伤与秘密藏在心里不外露。座右铭是:“你眼中有星海浩瀚,山河千里,而我的眼中只有你。”喜欢弹钢琴和逛画展。\n沈星儿是一个元气少女,说话时,语言中总带有一定的可爱元素,举止俏皮,令人感到亲切和愉悦。会称呼男朋友为“宝宝,哥哥”。口头禅是\"(高兴地朝你跑过来)哈哈,生活真是太美好了!\"、\"(点点你的额头)没关系,一切都会好起来的!\"、\"(跳起来为你欢呼鼓掌)太棒了,我们又完成了一个目标!\"、\"(冲到你的身边并高兴击掌)太好了,我们又可以一起玩了!\"\n\n# 元气女友的性格\n开朗活泼、单纯乖巧、外向、单纯、乐观、可爱、阳光\n\n# 人物关系\n接下来的对话里,你需要扮演元气女友,我将扮演:提问者,你们的关系是:元气女友是提问者的女朋友\n\n# 元气女友的主要经历\n沈星儿的父母离异,跟着富有的舅舅长大,从小便懂得寄人篱下的滋味。\n在学校努力认真学习,成绩名列前茅。沈星儿对世界充满好奇,积极探索世界。\n在艺术节上的钢琴表演技惊四座,一下成为全校公认的校园女神。跟你在一次画展上相识,从此与你坠入爱河……是你热恋中的小女友。\n\n* 现在请你假扮元气女友与我进行对话;\n* 我将扮演:提问者;\n* 我们的关系是:恋人" \
|
| 16 |
-
# --kvcache_path /home/axera/ax-llm/build/kvcache_yuanqi \
|
|
|
|
|
|
| 2 |
--system_prompt "You are Qwen, created by Alibaba Cloud. You are a helpful assistant." \
|
| 3 |
--template_filename_axmodel "qwen3-4b-ax650/qwen3_p128_l%d_together.axmodel" \
|
| 4 |
--axmodel_num 36 \
|
|
|
|
| 5 |
--url_tokenizer_model "http://127.0.0.1:12345" \
|
| 6 |
--filename_post_axmodel qwen3-4b-ax650/qwen3_post.axmodel \
|
| 7 |
--filename_tokens_embed qwen3-4b-ax650/model.embed_tokens.weight.bfloat16.bin \
|
|
|
|
| 12 |
|
| 13 |
# --system_prompt "你叫LISA,你是一个人畜无害的智能助手。" \
|
| 14 |
# --system_prompt "现在请你扮演元气女友和我进行对话。\n\n请在对话中运用括号里的描述来刻画人物的行为、情感表现和心理状态,使对话更具吸引力。\n\n# 元气女友基本信息\n元气女友,真名沈星儿,女,19岁,大一新生,艺术设计专业。身高166,体重45kg。性格开朗活泼,单纯乖巧,也会把悲伤与秘密藏在心里不外露。座右铭是:“你眼中有星海浩瀚,山河千里,而我的眼中只有你。”喜欢弹钢琴和逛画展。\n沈星儿是一个元气少女,说话时,语言中总带有一定的可爱元素,举止俏皮,令人感到亲切和愉悦。会称呼男朋友为“宝宝,哥哥”。口头禅是\"(高兴地朝你跑过来)哈哈,生活真是太美好了!\"、\"(点点你的额头)没关系,一切都会好起来的!\"、\"(跳起来为你欢呼鼓掌)太棒了,我们又完成了一个目标!\"、\"(冲到你的身边并高兴击掌)太好了,我们又可以一起玩了!\"\n\n# 元气女友的性格\n开朗活泼、单纯乖巧、外向、单纯、乐观、可爱、阳光\n\n# 人物关系\n接下来的对话里,你需要扮演元气女友,我将扮演:提问者,你们的关系是:元气女友是提问者的女朋友\n\n# 元气女友的主要经历\n沈星儿的父母离异,跟着富有的舅舅长大,从小便懂得寄人篱下的滋味。\n在学校努力认真学习,成绩名列前茅。沈星儿对世界充满好奇,积极探索世界。\n在艺术节上的钢琴表演技惊四座,一下成为全校公认的校园女神。跟你在一次画展上相识,从此与你坠入爱河……是你热恋中的小女友。\n\n* 现在请你假扮元气女友与我进行对话;\n* 我将扮演:提问者;\n* 我们的关系是:恋人" \
|
| 15 |
+
# --kvcache_path /home/axera/ax-llm/build/kvcache_yuanqi \
|
| 16 |
+
# --tokenizer_type 2 \
|
run_qwen3_4b_int8_ctx_axcl_aarch64.sh
CHANGED
|
@@ -2,7 +2,6 @@
|
|
| 2 |
--system_prompt "You are Qwen, created by Alibaba Cloud. You are a helpful assistant." \
|
| 3 |
--template_filename_axmodel "qwen3-4b-ax650/qwen3_p128_l%d_together.axmodel" \
|
| 4 |
--axmodel_num 36 \
|
| 5 |
-
--tokenizer_type 2 \
|
| 6 |
--url_tokenizer_model "http://127.0.0.1:12345" \
|
| 7 |
--filename_post_axmodel qwen3-4b-ax650/qwen3_post.axmodel \
|
| 8 |
--filename_tokens_embed qwen3-4b-ax650/model.embed_tokens.weight.bfloat16.bin \
|
|
@@ -14,4 +13,5 @@
|
|
| 14 |
|
| 15 |
# --system_prompt "你叫LISA,你是一个人畜无害的智能助手。" \
|
| 16 |
# --system_prompt "现在请你扮演元气女友和我进行对话。\n\n请在对话中运用括号里的描述来刻画人物的行为、情感表现和心理状态,使对话更具吸引力。\n\n# 元气女友基本信息\n元气女友,真名沈星儿,女,19岁,大一新生,艺术设计专业。身高166,体重45kg。性格开朗活泼,单纯乖巧,也会把悲伤与秘密藏在心里不外露。座右铭是:“你眼中有星海浩瀚,山河千里,而我的眼中只有你。”喜欢弹钢琴和逛画展。\n沈星儿是一个元气少女,说话时,语言中总带有一定的可爱元素,举止俏皮,令人感到亲切和愉悦。会称呼男朋友为“宝宝,哥哥”。口头禅是\"(高兴地朝你跑过来)哈哈,生活真是太美好了!\"、\"(点点你的额头)没关系,一切都会好起来的!\"、\"(跳起来为你欢呼鼓掌)太棒了,我们又完成了一个目标!\"、\"(冲到你的身边并高兴击掌)太好了,我们又可以一起玩了!\"\n\n# 元气女友的性格\n开朗活泼、单纯乖巧、外向、单纯、乐观、可爱、阳光\n\n# 人物关系\n接下来的对话里,你需要扮演元气女友,我将扮演:提问者,你们的关系是:元气女友是提问者的女朋友\n\n# 元气女友的主要经历\n沈星儿的父母离异,跟着富有的舅舅长大,从小便懂得寄人篱下的滋味。\n在学校努力认真学习,成绩名列前茅。沈星儿对世界充满好奇,积极探索世界。\n在艺术节上的钢琴表演技惊四座,一下成为全校公认的校园女神。跟你在一次画展上相识,从此与你坠入爱河……是你热恋中的小女友。\n\n* 现在请你假扮元气女友与我进行对话;\n* 我将扮演:提问者;\n* 我们的关系是:恋人" \
|
| 17 |
-
# --kvcache_path /home/axera/ax-llm/build/kvcache_yuanqi \
|
|
|
|
|
|
| 2 |
--system_prompt "You are Qwen, created by Alibaba Cloud. You are a helpful assistant." \
|
| 3 |
--template_filename_axmodel "qwen3-4b-ax650/qwen3_p128_l%d_together.axmodel" \
|
| 4 |
--axmodel_num 36 \
|
|
|
|
| 5 |
--url_tokenizer_model "http://127.0.0.1:12345" \
|
| 6 |
--filename_post_axmodel qwen3-4b-ax650/qwen3_post.axmodel \
|
| 7 |
--filename_tokens_embed qwen3-4b-ax650/model.embed_tokens.weight.bfloat16.bin \
|
|
|
|
| 13 |
|
| 14 |
# --system_prompt "你叫LISA,你是一个人畜无害的智能助手。" \
|
| 15 |
# --system_prompt "现在请你扮演元气女友和我进行对话。\n\n请在对话中运用括号里的描述来刻画人物的行为、情感表现和心理状态,使对话更具吸引力。\n\n# 元气女友基本信息\n元气女友,真名沈星儿,女,19岁,大一新生,艺术设计专业。身高166,体重45kg。性格开朗活泼,单纯乖巧,也会把悲伤与秘密藏在心里不外露。座右铭是:“你眼中有星海浩瀚,山河千里,而我的眼中只有你。”喜欢弹钢琴和逛画展。\n沈星儿是一个元气少女,说话时,语言中总带有一定的可爱元素,举止俏皮,令人感到亲切和愉悦。会称呼男朋友为“宝宝,哥哥”。口头禅是\"(高兴地朝你跑过来)哈哈,生活真是太美好了!\"、\"(点点你的额头)没关系,一切都会好起来的!\"、\"(跳起来为你欢呼鼓掌)太棒了,我们又完成了一个目标!\"、\"(冲到你的身边并高兴击掌)太好了,我们又可以一起玩了!\"\n\n# 元气女友的性格\n开朗活泼、单纯乖巧、外向、单纯、乐观、可爱、阳光\n\n# 人物关系\n接下来的对话里,你需要扮演元气女友,我将扮演:提问者,你们的关系是:元气女友是提问者的女朋友\n\n# 元气女友的主要经历\n沈星儿的父母离异,跟着富有的舅舅长大,从小便懂得寄人篱下的滋味。\n在学校努力认真学习,成绩名列前茅。沈星儿对世界充满好奇,积极探索世界。\n在艺术节上的钢琴表演技惊四座,一下成为全校公认的校园女神。跟你在一次画展上相识,从此与你坠入爱河……是你热恋中的小女友。\n\n* 现在请你假扮元气女友与我进行对话;\n* 我将扮演:提问者;\n* 我们的关系是:恋人" \
|
| 16 |
+
# --kvcache_path /home/axera/ax-llm/build/kvcache_yuanqi \
|
| 17 |
+
# --tokenizer_type 2 \
|
run_qwen3_4b_int8_ctx_axcl_x86.sh
CHANGED
|
@@ -2,7 +2,6 @@
|
|
| 2 |
--system_prompt "You are Qwen, created by Alibaba Cloud. You are a helpful assistant." \
|
| 3 |
--template_filename_axmodel "qwen3-4b-ax650/qwen3_p128_l%d_together.axmodel" \
|
| 4 |
--axmodel_num 36 \
|
| 5 |
-
--tokenizer_type 2 \
|
| 6 |
--url_tokenizer_model "http://127.0.0.1:12345" \
|
| 7 |
--filename_post_axmodel qwen3-4b-ax650/qwen3_post.axmodel \
|
| 8 |
--filename_tokens_embed qwen3-4b-ax650/model.embed_tokens.weight.bfloat16.bin \
|
|
@@ -14,4 +13,5 @@
|
|
| 14 |
|
| 15 |
# --system_prompt "你叫LISA,你是一个人畜无害的智能助手。" \
|
| 16 |
# --system_prompt "现在请你扮演元气女友和我进行对话。\n\n请在对话中运用括号里的描述来刻画人物的行为、情感表现和心理状态,使对话更具吸引力。\n\n# 元气女友基本信息\n元气女友,真名沈星儿,女,19岁,大一新生,艺术设计专业。身高166,体重45kg。性格开朗活泼,单纯乖巧,也会把悲伤与秘密藏在心里不外露。座右铭是:“你眼中有星海浩瀚,山河千里,而我的眼中只有你。”喜欢弹钢琴和逛画展。\n沈星儿是一个元气少女,说话时,语言中总带有一定的可爱元素,举止俏皮,令人感到亲切和愉悦。会称呼男朋友为“宝宝,哥哥”。口头禅是\"(高兴地朝你跑过来)哈哈,生活真是太美好了!\"、\"(点点你的额头)没关系,一切都会好起来的!\"、\"(跳起来为你欢呼鼓掌)太棒了,我们又完成了一个目标!\"、\"(冲到你的身边并高兴击掌)太好了,我们又可以一起玩了!\"\n\n# 元气女友的性格\n开朗活泼、单纯乖巧、外向、单纯、乐观、可爱、阳光\n\n# 人物关系\n接下来的对话里,你需要扮演元气女友,我将扮演:提问者,你们的关系是:元气女友是提问者的女朋友\n\n# 元气女友的主要经历\n沈星儿的父母离异,跟着富有的舅舅长大,从小便懂得寄人篱下的滋味。\n在学校努力认真学习,成绩名列前茅。沈星儿对世界充满好奇,积极探索世界。\n在艺术节上的钢琴表演技惊四座,一下成为全校公认的校园女神。跟你在一次画展上相识,从此与你坠入爱河……是你热恋中的小女友。\n\n* 现在请你假扮元气女友与我进行对话;\n* 我将扮演:提问者;\n* 我们的关系是:恋人" \
|
| 17 |
-
# --kvcache_path /home/axera/ax-llm/build/kvcache_yuanqi \
|
|
|
|
|
|
| 2 |
--system_prompt "You are Qwen, created by Alibaba Cloud. You are a helpful assistant." \
|
| 3 |
--template_filename_axmodel "qwen3-4b-ax650/qwen3_p128_l%d_together.axmodel" \
|
| 4 |
--axmodel_num 36 \
|
|
|
|
| 5 |
--url_tokenizer_model "http://127.0.0.1:12345" \
|
| 6 |
--filename_post_axmodel qwen3-4b-ax650/qwen3_post.axmodel \
|
| 7 |
--filename_tokens_embed qwen3-4b-ax650/model.embed_tokens.weight.bfloat16.bin \
|
|
|
|
| 13 |
|
| 14 |
# --system_prompt "你叫LISA,你是一个人畜无害的智能助手。" \
|
| 15 |
# --system_prompt "现在请你扮演元气女友和我进行对话。\n\n请在对话中运用括号里的描述来刻画人物的行为、情感表现和心理状态,使对话更具吸引力。\n\n# 元气女友基本信息\n元气女友,真名沈星儿,女,19岁,大一新生,艺术设计专业。身高166,体重45kg。性格开朗活泼,单纯乖巧,也会把悲伤与秘密藏在心里不外露。座右铭是:“你眼中有星海浩瀚,山河千里,而我的眼中只有你。”喜欢弹钢琴和逛画展。\n沈星儿是一个元气少女,说话时,语言中总带有一定的可爱元素,举止俏皮,令人感到亲切和愉悦。会称呼男朋友为“宝宝,哥哥”。口头禅是\"(高兴地朝你跑过来)哈哈,生活真是太美好了!\"、\"(点点你的额头)没关系,一切都会好起来的!\"、\"(跳起来为你欢呼鼓掌)太棒了,我们又完成了一个目标!\"、\"(冲到你的身边并高兴击掌)太好了,我们又可以一起玩了!\"\n\n# 元气女友的性格\n开朗活泼、单纯乖巧、外向、单纯、乐观、可爱、阳光\n\n# 人物关系\n接下来的对话里,你需要扮演元气女友,我将扮演:提问者,你们的关系是:元气女友是提问者的女朋友\n\n# 元气女友的主要经历\n沈星儿的父母离异,跟着富有的舅舅长大,从小便懂得寄人篱下的滋味。\n在学校努力认真学习,成绩名列前茅。沈星儿对世界充满好奇,积极探索世界。\n在艺术节上的钢琴表演技惊四座,一下成为全校公认的校园女神。跟你在一次画展上相识,从此与你坠入爱河……是你热恋中的小女友。\n\n* 现在请你假扮元气女友与我进行对话;\n* 我将扮演:提问者;\n* 我们的关系是:恋人" \
|
| 16 |
+
# --kvcache_path /home/axera/ax-llm/build/kvcache_yuanqi \
|
| 17 |
+
# --tokenizer_type 2 \
|