diff --git a/checkpoints/Qwen3.5-2B/0.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/0.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..868d3dd88f2698a18af65e2ec6690bd3112e0f0e --- /dev/null +++ b/checkpoints/Qwen3.5-2B/0.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a362e7f2db815a9430bd735f19cc7e6f3f4655511406dca5f47661a1de7fd2e +size 25625746 diff --git a/checkpoints/Qwen3.5-2B/0.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/0.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc2dd00b3b95e665bebaab8c95df2d2b19bd337c --- /dev/null +++ b/checkpoints/Qwen3.5-2B/0.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d07fab744bc427156a25b33030d188480cbc4828b106401dcc9749dab00d9697 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/0.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/0.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a8d691899ddc75f3e6a4c0a850803c26d33d6c6 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/0.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6be7638405e66640307d52ac9ecb8988e27ed7d60b4d57fd78494fda92dd1bb +size 8586329 diff --git a/checkpoints/Qwen3.5-2B/0.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/0.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ff88672f2a02e96c2ad988424f106bd3791adf6b --- /dev/null +++ b/checkpoints/Qwen3.5-2B/0.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9cb90723fa505f3488f15edac09f18ef086f4317b662acb4aa1006cc6a8765f +size 25748372 diff --git a/checkpoints/Qwen3.5-2B/0.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/0.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7cad544fe88cccbc2e1cbe8a361a7d85f1b6979b --- /dev/null +++ b/checkpoints/Qwen3.5-2B/0.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c9326e1a597751a413ccbdf405ec70e674111313c6897e789bf1b92e1451f4a +size 25625492 diff --git a/checkpoints/Qwen3.5-2B/0.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/0.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba2b9c119b339f973d0d9b8d6b3236b899bd1a44 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/0.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aaef4533a1c8c2e34f70722a61f061f2b7f189949d556b72c8057177112d0af +size 25625454 diff --git a/checkpoints/Qwen3.5-2B/1.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/1.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0812f386aa96bbd76a6736522e2e1bf8b319796 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/1.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4854b3bbc4d08bf6ddf9b236bfd268ed498c5d33d76051619f286c0f889c013 +size 25625746 diff --git a/checkpoints/Qwen3.5-2B/1.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/1.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae61ca3c00a0e444e0448221386c63f70551f4b4 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/1.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88fa58d28309df5503be1ec255340388f0e3d5c00818bca6d21bc16d2ed85043 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/1.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/1.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd5af47744f992ee26a65a2eb72fe17fbddfbbd8 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/1.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fa28e9464098cca81fede61584db5518b2eea1848e17f3b35c304feaa8f2621 +size 8586329 diff --git a/checkpoints/Qwen3.5-2B/1.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/1.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c811c93dabdf7a46ac312b646fb5a1422107d496 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/1.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4970a07d60930112034fd6cece6c54a00a63ee26a369aff2906cfe94d2967d6 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B/1.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/1.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f852d5150832dfc02b0673a2dc8e43171400c72 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/1.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dc5573ecbf7be14555673440d8d5da3bba2752a75e14179ef8c01d263caba14 +size 25625492 diff --git a/checkpoints/Qwen3.5-2B/1.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/1.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b444ba0be46e4dc23069232c7a2f81a2fa07896e --- /dev/null +++ b/checkpoints/Qwen3.5-2B/1.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64a7ad85406d1c9537ea2630d92dc68f695e81f68f596c36ca6512888d8fd6c2 +size 25625454 diff --git a/checkpoints/Qwen3.5-2B/10.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/10.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..8187af8ffe3ce34336b8f7fa92a99256646fc8d6 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/10.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d4abb10032586621d488970283dfbf7546acf0e3522fe7b38bf488adc5d7cc6 +size 25625765 diff --git a/checkpoints/Qwen3.5-2B/10.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/10.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..bab165e2e9dcd8b93aeee00ac11d4867359b2e95 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/10.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5c1169a9293ab1bf15b04a67b1fecadbcc2f23d251f90b3b67409b195196213 +size 8586367 diff --git a/checkpoints/Qwen3.5-2B/10.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/10.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7177a506e9af0c518eddce2cfefd1375d1f3cba0 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/10.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d98ef9ccdf9cbe2d06cfbf8b5d11b586e30864c270a0498a119ae65cc3f4b20b +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/10.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/10.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..652d937e37713d8bac6dbdc47b13e29e5f47e0ed --- /dev/null +++ b/checkpoints/Qwen3.5-2B/10.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a77d0dffd4170018cf1f4e96280bbac631e23e74640743bfd0e75b5b9efbd24f +size 25748391 diff --git a/checkpoints/Qwen3.5-2B/10.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/10.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..40ec98fb38643f4b6fd3dc64a916389e7724ec11 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/10.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8834bc0791ebf9ca1e87ab6d782380a7cb5dc0649ef97453e95b2bac710e31ee +size 25625511 diff --git a/checkpoints/Qwen3.5-2B/10.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/10.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..12aa01531ed5d77e3b255c3a833dff4b22bcbd3d --- /dev/null +++ b/checkpoints/Qwen3.5-2B/10.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:100cd0acd88bcdc318bb7a58a415e21d2b6121481c6373876ed5f0d9e7e77598 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B/11.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/11.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..69d185fe5d6215a44aabd303cc8da5873930ca27 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/11.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec07b05c3b80f2b921f969d34c3ab32bd3d8c99f4158f1abb227a67c840b60de +size 25748391 diff --git a/checkpoints/Qwen3.5-2B/11.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/11.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8801b098bb5984fbbe4429c86973ea3ee2fa132e --- /dev/null +++ b/checkpoints/Qwen3.5-2B/11.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75da5bb1ae86044b3d41846959b5965be4be45159b05a5ef84b0b30ea67af4bf +size 25625511 diff --git a/checkpoints/Qwen3.5-2B/11.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/11.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..be22234117e13ee2aa1e47a3e6399ff81ad00aae --- /dev/null +++ b/checkpoints/Qwen3.5-2B/11.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f23610939740031f0d2a9d0be30214a6752380fda522d3be742374b80e826875 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B/11.self_attn.k_proj.pt b/checkpoints/Qwen3.5-2B/11.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6dcdd0ae81041a0547e42e8eb7775317fe2c7251 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/11.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d18f169706a026d9338505ac95d5cbdcd890c1cdafc7e3bf08d6cddf85d7f6e +size 2196448 diff --git a/checkpoints/Qwen3.5-2B/11.self_attn.o_proj.pt b/checkpoints/Qwen3.5-2B/11.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4e4c9290873e8edb503cd8193994e172cd4944ae --- /dev/null +++ b/checkpoints/Qwen3.5-2B/11.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75c2fa4e164fc5ad9a0cfa27cca2c49de8c4474ec2c8972366d88e8df72ce483 +size 8586208 diff --git a/checkpoints/Qwen3.5-2B/11.self_attn.q_proj.pt b/checkpoints/Qwen3.5-2B/11.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d1b0385660c757ebad6f0d94c88b28b6aea1273 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/11.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:283963577799a3e26f3bd8d32668e924e599cf7521bec39fb2a23486ddd22d38 +size 17105888 diff --git a/checkpoints/Qwen3.5-2B/11.self_attn.v_proj.pt b/checkpoints/Qwen3.5-2B/11.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..533c0b2faafdbfddca3e777db898a5430b1c6f15 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/11.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b5684dc8265929fcd9f33e9470e7776469a42d5779d19b5b0a8908878e5c7c +size 2196448 diff --git a/checkpoints/Qwen3.5-2B/12.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/12.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..1ba6ca4dae0a258df1fe321cba9a05eea08417ff --- /dev/null +++ b/checkpoints/Qwen3.5-2B/12.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d52249ac0a0aabc5ef1432334c125cb1b0de6b38016f99efaf662972782ea184 +size 25625765 diff --git a/checkpoints/Qwen3.5-2B/12.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/12.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..be18846fe915b61c578d6cea6509edac0699c25c --- /dev/null +++ b/checkpoints/Qwen3.5-2B/12.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75e35f17c80d3e3419d92eea3ddbb0b41be556716ade455943ea31be44f37034 +size 8586367 diff --git a/checkpoints/Qwen3.5-2B/12.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/12.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f2cf4b4cb998a72c826aadf96bbd8416b3846927 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/12.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f0d910ac6acae4201bccd28818ec6b51041fa5c21198695ddc58bf5ca97ed0b +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/12.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/12.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa5b5a73961a50ae1663c22044ead5f1dbac3b0f --- /dev/null +++ b/checkpoints/Qwen3.5-2B/12.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9647c60f62a5f3ed25fbe8fc5865682a79541ee9fa898f1387b8be4fb11aa6b7 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B/12.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/12.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae1965e3f265d77b0aa6b7f264ac4cecc06ac9c3 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/12.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b79da8e156af21dd181e5b01c33cda98c54e748cdb78cd30f993bcb93e778f98 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B/12.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/12.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..49886218221cf8759188d9deac6a5788744c6765 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/12.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd06e10fd80cbc7e3f116cc21ea6515afe4bb985f337f8dcb2f0e04921315e60 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B/13.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/13.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..8d21f2d3427aafee47b93dc2ded7da6bd6f2ec7d --- /dev/null +++ b/checkpoints/Qwen3.5-2B/13.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ff83bfc96ac0eedd948f2c16649ef113701f3778195bc99f59d512e4f0f426 +size 25625765 diff --git a/checkpoints/Qwen3.5-2B/13.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/13.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..7555e21cb49c2d6f862bf59af2333852bd2f3fb3 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/13.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:703ed9381017dc9211f6ce14454c5de8ad2c17d26d000fda44ae50da7cb000c3 +size 8586367 diff --git a/checkpoints/Qwen3.5-2B/13.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/13.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e132830cda386fa6c917b7608eb7b197e7f15047 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/13.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0d43e05528924fd52cc7b9bef18130e75f5243e14f9336e53c2237eb6a7f8ee +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/13.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/13.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ffb2dec94cf63579d03e667e924e72b34cdc0f2 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/13.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:370a41dfa25c4f493facee9c64bb2bb9ee96797db634b51031cc0c6ae1f874d4 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B/13.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/13.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8551e3b0ccf90557198abefaea4a7e6b1f9a3f8 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/13.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43682ea2e8937fbf499b0c5a2abbfb2a4daf9cb634dde84675ac1a212e5de881 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B/13.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/13.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..596d91f34e480e2c344e87178e619f62669e47da --- /dev/null +++ b/checkpoints/Qwen3.5-2B/13.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1474a2b08e3d7d1c0897c27bb438b2a0af664a8987ceec5438d27920b83813c +size 25625473 diff --git a/checkpoints/Qwen3.5-2B/14.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/14.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..bcdc24ed3aa58c688f26348564b529baf461cbee --- /dev/null +++ b/checkpoints/Qwen3.5-2B/14.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ea07ae695847300c444fb12a30cd9489b1b5767f8719e54c080e91ed04c8242 +size 25625765 diff --git a/checkpoints/Qwen3.5-2B/14.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/14.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..0db698382af1241edf294fa759b42787f7a396bc --- /dev/null +++ b/checkpoints/Qwen3.5-2B/14.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb6f742bc064db37e0a41025ca2ada1459c4f9031cd405a8b16818b055f3f4d3 +size 8586367 diff --git a/checkpoints/Qwen3.5-2B/14.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/14.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b6d64729cab27cbe4c4ee4e59bc0dce205b0b0c --- /dev/null +++ b/checkpoints/Qwen3.5-2B/14.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f735e0164b17c7b64828f4ecc7e29f4295ed41d23f77c21ff0399f07a0b6bfa4 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/14.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/14.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c86a2d58f321cb994a6d0402cbf0a484d4cdba49 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/14.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bb8f8081c109c3159a777a76c67caf39e2d9b45bf4493323ba22eed20a7e095 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B/14.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/14.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..cec5df406ffc832b803b394aeef4b9ee3f95906e --- /dev/null +++ b/checkpoints/Qwen3.5-2B/14.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff9eeb9df774509320d867fbf47029de0977cb901eb8bb6f732eb4b1e10160c1 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B/14.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/14.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..27b7ae469cd510219b24ac88a6b8b1dc287df115 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/14.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2961fb1547f3b34268c42163fd7660a0e95d9cd64b5eab4e1cc5cc37d71a1a59 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B/15.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/15.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8104fea0e54900ff199e250bc5c5f0c108aeb221 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/15.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b707bead634264daf2830c02a34225995266e594d92e61854e1d2a9681f0aa70 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B/15.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/15.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..21216e158e3e5f40ade0948c937249915fc7ba97 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/15.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be6baa2022ea7d107a814a5c3a4395b5aa3393ce7ef59cd6ed6b7bcb00f04503 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B/15.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/15.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..98e3b344e20212b1df065dbbe233ca778b696541 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/15.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b3b1ee302f40d5874aa401fd18e68bb5a3118afef24a83c3200093eaf1ccae9 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B/15.self_attn.k_proj.pt b/checkpoints/Qwen3.5-2B/15.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..889b10939eb7fbc8e9a66dc4cfc4fe1c08c6df0f --- /dev/null +++ b/checkpoints/Qwen3.5-2B/15.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a697e9c281652f08d006a514c879dd709a3fef08c61b703391cf07d1df6f3ae +size 2196448 diff --git a/checkpoints/Qwen3.5-2B/15.self_attn.o_proj.pt b/checkpoints/Qwen3.5-2B/15.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a3d54a364cfec663834f27fa81a2affca80ba89 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/15.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e1c84c52f7525bf9132ef9d91d579a4220d3b3d1ace1370aaa0be0834d453a3 +size 8586208 diff --git a/checkpoints/Qwen3.5-2B/15.self_attn.q_proj.pt b/checkpoints/Qwen3.5-2B/15.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f2ef234282835f33ac9f0f2255917a16fe9010e1 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/15.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79a1feba81a70fccf1953d5702fc842894d193b6740540ecf7eaba6540c90fab +size 17105888 diff --git a/checkpoints/Qwen3.5-2B/15.self_attn.v_proj.pt b/checkpoints/Qwen3.5-2B/15.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..938cac4685e922b763f87d64f5db9b7b7cce350b --- /dev/null +++ b/checkpoints/Qwen3.5-2B/15.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9898566dee2ceddf0acbce7511f183e5c6ee89a1665661cbb48e4e0c816486b7 +size 2196448 diff --git a/checkpoints/Qwen3.5-2B/16.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/16.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc0d3ff19bcaed8d82ac7fea29e55dd332339d50 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/16.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2f4f959eb7aa3998361ae92d202ca03e02327cecf628a4fd5fca6311ebe5916 +size 25625765 diff --git a/checkpoints/Qwen3.5-2B/16.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/16.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6d4cd45b8af8088eddc55be3fa38abb9c33ab44 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/16.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:557aab0e565ef2067dbefe5d94f9d715a7e8847029f6e26f851f846d0e84178c +size 8586367 diff --git a/checkpoints/Qwen3.5-2B/16.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/16.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c485bc545f8868d1d3fee23a7285011c83d4792 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/16.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8782eddf4b1c3d8b11417f02d68bb78e224e0992d4b87121415dbf5a98fbeec9 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/16.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/16.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e75a61c4f97cb61007e9d467b5a4cfe285835eea --- /dev/null +++ b/checkpoints/Qwen3.5-2B/16.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7acc513033c3bb8017cd5b6bda0c33c21d0747e35e7c799c3abd156ebba61975 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B/16.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/16.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..981c822c2925390129fd3b1680efa22761bea87b --- /dev/null +++ b/checkpoints/Qwen3.5-2B/16.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b034ebb814d89d7bca19a65d239212f3f9f13dcd556d9600a01948680af5ae0 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B/16.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/16.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf3daa01ec1613640bcf3937c5b2bb05378b70f3 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/16.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3529f9c1fcad110bcbca0cad2b095596684c5f8fcd861ace13e912121ac93dc7 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B/17.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/17.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..70c4881e65447b9b312060b1daea623ad7507c54 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/17.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:337c0f9d42b11f8b48d6f5d554bbea76296e7dbc3df495da0d0c45e13a1d2c79 +size 25625765 diff --git a/checkpoints/Qwen3.5-2B/17.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/17.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..a7cf3453d5e23cb822ba5c18844fc298e21d8070 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/17.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9282d349258713a9cb7091438728b4477235821eea5fc1121091ef77fdcf8afb +size 8586367 diff --git a/checkpoints/Qwen3.5-2B/17.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/17.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..66418cf41d6c5c63d286ba7ee5a55d4f53dfb8b0 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/17.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb3e97f969f50f5460535418f9dc21c4fe500651bb78dfc67d891b234780070c +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/17.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/17.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..13e88206f3dfe9b25a09478a4161995b924b2f1a --- /dev/null +++ b/checkpoints/Qwen3.5-2B/17.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d4255541c61aeea268f5be232a180b3cdb8d7803858b7a0f25434b9d87d929b +size 25748391 diff --git a/checkpoints/Qwen3.5-2B/17.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/17.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..686d5956af10b2c1c441839df8da0259fe143c54 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/17.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a45792a7039b796eeefd0085647f74cbb93e73d83f7d1fec43b3eb8198627ca5 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B/17.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/17.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7058bb136f8df0b661ccec54217ca18bfa0d7522 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/17.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5e06494d2780b3de559289e28864a99b915362e88bbf302adeaf29db8ccf722 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B/18.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/18.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..834f30aee4ea08c3e08c0a2f53dec28d881a6d2a --- /dev/null +++ b/checkpoints/Qwen3.5-2B/18.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64cb7aefab4b6b5a49ec833f5bfb085201a3962589c5039d5369b8548d915475 +size 25625765 diff --git a/checkpoints/Qwen3.5-2B/18.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/18.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..66fcdfd88959d0ac4f6c46868e503a4ceff313e1 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/18.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fded6bd29942f1107482167239a3ae5f9fe36c8b31f93db729ae2ba12451c129 +size 8586367 diff --git a/checkpoints/Qwen3.5-2B/18.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/18.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9ea411d38cbf05ab898430309a7fa2cb0d2b0b64 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/18.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eae949bcf45b6defb63b4ca701d0447cea15c3cd2c1cc62a4dca9fc5dc605ba +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/18.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/18.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4090cc676039e8eb206f173d2afb1055aefc58f2 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/18.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb87bd2fc7cdee4d636e53fc89740c29b35883d15043fabd7b415ffb5103f733 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B/18.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/18.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..cfe7c2f9391a662e5ebc0f9876ca08834c0f61e5 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/18.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e85af250cda2f11c0891eb25e59e57373ff0a61e576fc771fcdc9660c9a1680a +size 25625511 diff --git a/checkpoints/Qwen3.5-2B/18.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/18.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a097114c9d0f5e42760d7953b090097a900753f --- /dev/null +++ b/checkpoints/Qwen3.5-2B/18.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5a407a75a452452c33a2994e25b24477614bca2fa37c3978e231cc0234368fa +size 25625473 diff --git a/checkpoints/Qwen3.5-2B/19.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/19.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c9e309fe48292794ac71a94882c52c3f7230871 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/19.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c739bbaa0d1b4da5e34d7acfa6654209246a2ed6969bc654e99c1fecf6c31c59 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B/19.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/19.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a03a3d3c16893eb6b9160617dd6af880fc43f613 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/19.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aab8f380d2d331d1806cd970a22e3550b22dd17875351a932d3375ccde47cac +size 25625511 diff --git a/checkpoints/Qwen3.5-2B/19.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/19.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..da52ec198428b28693d1efbb0a1c912064e362a9 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/19.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de210c60e6b72634fa77321b2554b7549d4dc76b6b0f6eb97d039dfa3bc00e3e +size 25625473 diff --git a/checkpoints/Qwen3.5-2B/19.self_attn.k_proj.pt b/checkpoints/Qwen3.5-2B/19.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..84c7fcf103cfda8159d30ee3afe39ac006e26c39 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/19.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cd6f99ec518a0882a4781248968415356e929b1fe863adc8361f33873434fd9 +size 2196448 diff --git a/checkpoints/Qwen3.5-2B/19.self_attn.o_proj.pt b/checkpoints/Qwen3.5-2B/19.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc40d67f54534dc600292734ceeca000970f94aa --- /dev/null +++ b/checkpoints/Qwen3.5-2B/19.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7b8a3c33f2971f7735b5c9cbe993d9d288f52831f3633731f6c1816a3fb6822 +size 8586208 diff --git a/checkpoints/Qwen3.5-2B/19.self_attn.q_proj.pt b/checkpoints/Qwen3.5-2B/19.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..104961446ce78d5c85110ee2b83d7513a97540df --- /dev/null +++ b/checkpoints/Qwen3.5-2B/19.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4cc4006ee67ceac91d37f620cb1f890ce3f9acbd0d065b37677cd914d53f28a +size 17105888 diff --git a/checkpoints/Qwen3.5-2B/19.self_attn.v_proj.pt b/checkpoints/Qwen3.5-2B/19.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e9f9f34f48023dc74610a9cd402ef60ea0bc514e --- /dev/null +++ b/checkpoints/Qwen3.5-2B/19.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:612f9c3cb8a6082344b77536d9e2ab541ba684655e3cb84be2d836a02d0090a4 +size 2196448 diff --git a/checkpoints/Qwen3.5-2B/2.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/2.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..2160c9273a48d792459d310284e2f68c04b01602 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/2.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d12c324518274bef5d1009ff7b613f23f1abed597cda4b2c7b0032db6a827f +size 25625746 diff --git a/checkpoints/Qwen3.5-2B/2.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/2.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b2c94eac03907e9dfff12671f47c714b2584353 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/2.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84af034d210384ba0a38a7046c5350712cafa3bf503835ae1c022caf6be94b6f +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/2.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/2.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6c3a862e4bd95630d1d58d2a482ad412d28d335e --- /dev/null +++ b/checkpoints/Qwen3.5-2B/2.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee91f6fc1d085c0da6f5e8f863003804f484c5eb4836b7e82f9d2c84446853d8 +size 8586329 diff --git a/checkpoints/Qwen3.5-2B/2.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/2.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..12bd62e7de868bcbd36fe021a8290e0498172d58 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/2.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f3660076841a718de68e9fa84e8a0f34fde1dc228fb69f24e4bbf25efad8232 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B/2.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/2.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8034e2d00d625424a960a80bab1296951273fed --- /dev/null +++ b/checkpoints/Qwen3.5-2B/2.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d9ad417f2fda177237de6017321b81a763ae2a4409c0263eb66d83b663afc21 +size 25625492 diff --git a/checkpoints/Qwen3.5-2B/2.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/2.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..912e8cd716d4c6eb9067880b6475a18c7e1c941b --- /dev/null +++ b/checkpoints/Qwen3.5-2B/2.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb6a4ddd0b26b0e9f878da6ca8b1a5f8f48ee3743b8c7761dec21b2b15e2391e +size 25625454 diff --git a/checkpoints/Qwen3.5-2B/20.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/20.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..58ef29ca5fca53587f8a1c5540232c55ab854bee --- /dev/null +++ b/checkpoints/Qwen3.5-2B/20.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476ebae3d79e78ddae6ad5e28acb4d1b4ca51fb382fe35e2efe7c59e24a0e7f9 +size 25625765 diff --git a/checkpoints/Qwen3.5-2B/20.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/20.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d32daa2bd84e3b042903cbd3cecc61eb6f00c58 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/20.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285627f19eb2abf6491b510026417fac649bb8930d7a8d1f70fb88ecd0516e74 +size 8586367 diff --git a/checkpoints/Qwen3.5-2B/20.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/20.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3af010d3acbbb3a63e72b865975eb1d0e6415fd9 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/20.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac436ec4b756a0c4823ea047d4d72cdc9f1274ade3ddb2b094c0d4aaaf223eff +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/20.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/20.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6db10727b420e307e4912f643c76b6a78da97c3c --- /dev/null +++ b/checkpoints/Qwen3.5-2B/20.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:942d9843af52d460e58b8c9179f7cd1f989a0f0b9520e1b174ee9f6d3b6af9dd +size 25748391 diff --git a/checkpoints/Qwen3.5-2B/20.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/20.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9722217a6360d6b08483a90d57298f4a6437ba2a --- /dev/null +++ b/checkpoints/Qwen3.5-2B/20.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69e03f37e208df308545c1665340bd165c421fa733cff5ae4ee7310fc4062de1 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B/20.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/20.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c752caed789b7040c9ed6786e44092b6c583427 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/20.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d80d78ae17fa84501db5982e7ae8588992bd48809801a35980712fb972e8dd2 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B/21.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/21.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..5646794533a24d37e0fa6e4f0bb2471286a264de --- /dev/null +++ b/checkpoints/Qwen3.5-2B/21.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3afd4341ffe1cc71334d987eac9f0f2eb2ecba4481a47efb80b3e4a93f77511b +size 25625765 diff --git a/checkpoints/Qwen3.5-2B/21.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/21.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..553065cda7571406166f091d3319e31f2a6c3570 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/21.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1aa003f34b3c7d4bab3144b60f01d81dd1f16fea002d77eb1a0f06d4e36d1d3 +size 8586367 diff --git a/checkpoints/Qwen3.5-2B/21.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/21.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d621f912c9e974fb8cb7623e6331a3ac3309b2c --- /dev/null +++ b/checkpoints/Qwen3.5-2B/21.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4805b5dc484d6537a0e6822d58ddc60208ef599aa852ecdcf0b4c34598441389 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/21.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/21.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..900fd4e1d7b380a8fa91f6a494477e3252b09497 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/21.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ab1ad18f86bb475a02d58fb78a66ede5eb4bd268bccaaec6bb5ac267a22d2c3 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B/21.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/21.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..615e0e174097564af507ab1f916401b9fbbd78a5 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/21.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03f4fd71888c0863dae3e157f6f0ff283a024c35ca81ab62b7c4682774d80b6e +size 25625511 diff --git a/checkpoints/Qwen3.5-2B/21.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/21.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..10491490e0f876f0af7adb35f28ec134478e0d46 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/21.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef265837402cdb331f6427c1b56c469aa29eaf0f34021fb911913319546e5bbb +size 25625473 diff --git a/checkpoints/Qwen3.5-2B/22.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/22.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..8a3f1b4c7e81b815ef2a1cfa3ea0581d7ece3b5c --- /dev/null +++ b/checkpoints/Qwen3.5-2B/22.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9057fefd0315b86d0329c9ebb3b87b7216b2959b31139965070ed01789dc467 +size 25625765 diff --git a/checkpoints/Qwen3.5-2B/22.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/22.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..6eb640b06d605c3ee666b78a051d294a43df5f8a --- /dev/null +++ b/checkpoints/Qwen3.5-2B/22.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5563eee3c6e8e3885a002a542bc6759ab638215f3685929771401bde5dbeae95 +size 8586367 diff --git a/checkpoints/Qwen3.5-2B/22.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/22.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..82b9bf0a39e06a7432889555b03cef2507c5e8f9 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/22.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb96e84dfa75ce61c73633989c77acd657e5eda6b71d46aa9a5e5c4f5e75c7bf +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/22.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/22.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8aa77a8cbfb3299f52ab9028ebd1b6c3c4c7d9fb --- /dev/null +++ b/checkpoints/Qwen3.5-2B/22.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f5998692d6fff8fb48485245b590e521d6617fdde0b64bc6cdb3b97c0a6221b +size 25748391 diff --git a/checkpoints/Qwen3.5-2B/22.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/22.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c3f76ab80e43e9b8aa128865036afedeeb7f3ed6 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/22.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:997dd2e40f336c39f25de038ee665378402f7214c7a4a5e923a6367189115c46 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B/22.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/22.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e02cfc64bb0aba2e1f7f803bf2baab1a66f02b3c --- /dev/null +++ b/checkpoints/Qwen3.5-2B/22.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d809f2f1d30c6b81c4bb0f7c02431bcbe429c423ec82c80694dd484877c1bf +size 25625473 diff --git a/checkpoints/Qwen3.5-2B/23.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/23.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d121b5236ab1bbc85a9cf95ea5d4b8b3881fb79 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/23.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:083c48413d2ffc82aba26ef98f9b49bb643f2fe431dbe8158018a7b78bfb2ce4 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B/23.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/23.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9617a94976dcf2abb86ea074022e967e77bde226 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/23.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f94093cc5c1ee5041e21f84b330d933050864461293c9de0a8ba7c07accf5d1 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B/23.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/23.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d4af975efb2177bbb79baaf1577ffa6fb805bb78 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/23.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efc067f5575f95934ae357299ad7a467359cd83d5a85f47e2ba66c3f2ed41a74 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B/23.self_attn.k_proj.pt b/checkpoints/Qwen3.5-2B/23.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d99d04fddab01b8e1cb3c779a34af3a6e5b9ed5 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/23.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fc222f51dd7ccba3bb3dfade71044ba59be0d90b7fa710950b8f2a59e518cfe +size 2196448 diff --git a/checkpoints/Qwen3.5-2B/23.self_attn.o_proj.pt b/checkpoints/Qwen3.5-2B/23.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e96631031b2b05843239e7a39dfb41ea1bfa79e5 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/23.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efbb1425c88032738e27395250073aa047c2afc7d50f5b03e9c77b6f394debb1 +size 8586208 diff --git a/checkpoints/Qwen3.5-2B/23.self_attn.q_proj.pt b/checkpoints/Qwen3.5-2B/23.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..98d174f6f6106599b2206721c017c8e618c7cbdb --- /dev/null +++ b/checkpoints/Qwen3.5-2B/23.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e23b1ef35eb82e6747ed82eba9c7e21227a704e2d441ea10ad5544b398745954 +size 17105888 diff --git a/checkpoints/Qwen3.5-2B/23.self_attn.v_proj.pt b/checkpoints/Qwen3.5-2B/23.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c32989eaf1e8ce003f8b88ce54067b820ff4635 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/23.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e46631e098d8ba9fc96e09750168b4ce9f9f1c6de6336b3e87d3ee2c44d45dff +size 2196448 diff --git a/checkpoints/Qwen3.5-2B/3.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/3.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f5edcd1901083a2be39cf7be502a6437786fbe8f --- /dev/null +++ b/checkpoints/Qwen3.5-2B/3.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f436175e8e89796def39751c1081944ea34226b055406e35624c85d6fa5f9b7 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B/3.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/3.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..54943e4322e4621fe8835f1948b4d951ff12842e --- /dev/null +++ b/checkpoints/Qwen3.5-2B/3.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61d0a510fcd2d2522dd80b5faec8d1f07499793ff4afbd89f1f3e2744f862f36 +size 25625492 diff --git a/checkpoints/Qwen3.5-2B/3.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/3.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f3e689aec0e30762d365750f2edd11ab769db110 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/3.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02d9695b2b4acbf83e2362433a8db04036bd2b34d82468a8fb14b1da88edde32 +size 25625454 diff --git a/checkpoints/Qwen3.5-2B/3.self_attn.k_proj.pt b/checkpoints/Qwen3.5-2B/3.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ce2402f00c50a7fe84b93fc6eaa15eab179336fe --- /dev/null +++ b/checkpoints/Qwen3.5-2B/3.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2d829942501c6bd7b7fe9e3b334cdcef02d4de942c1e7e73d7b34a9a1e238ac +size 2196429 diff --git a/checkpoints/Qwen3.5-2B/3.self_attn.o_proj.pt b/checkpoints/Qwen3.5-2B/3.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..85a006cabc56303589f76e1c695b88c7d3f2bbb9 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/3.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48d9e4b705c8c728963cfa2239fdbdc5ae9c82d3848ebc1aea54f442ed063d80 +size 8586189 diff --git a/checkpoints/Qwen3.5-2B/3.self_attn.q_proj.pt b/checkpoints/Qwen3.5-2B/3.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..81d6452acc511dca2efe315de8930a282817b718 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/3.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a271953b10e088b31b59b0b7ba56e3e705be76489e3c8d38509139f556635186 +size 17105869 diff --git a/checkpoints/Qwen3.5-2B/3.self_attn.v_proj.pt b/checkpoints/Qwen3.5-2B/3.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d52d2fa91f2d21b43aacff3333a2581cbb54785b --- /dev/null +++ b/checkpoints/Qwen3.5-2B/3.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:245253fec89077ef96a62d8916d7bf8539d06de8edb0f26e869767ecf8bed9a8 +size 2196429 diff --git a/checkpoints/Qwen3.5-2B/4.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/4.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..f41b9ef522f83325ddf44ed86679eba9b28ca606 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/4.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89847fbabd12a3119407df71a148d5aeb4535e227d5e9e5a60a67e296ed8085e +size 25625746 diff --git a/checkpoints/Qwen3.5-2B/4.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/4.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..b6fb1c50a33fc96e04aa3d833ed8b40bfde8f696 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/4.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c279a10ead3bebaa064e5dd7f4024fdeef4855799dfd752f8daa73a4b78ca893 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/4.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/4.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4856521ec84cd690342382507eb458ab7ce60925 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/4.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a573602c4f04eeeddfb1653e157559745cc051478a792df1ab0f63fb0e26114e +size 8586329 diff --git a/checkpoints/Qwen3.5-2B/4.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/4.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..acf21c102d78c8155dd310b8bbbc28605f5bcc92 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/4.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf226f741d82d18d2b03807ec3146ea60f9180f62805829d19a302321e66a715 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B/4.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/4.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..07b7285caab922e1b408c03c905f0d6084f28d1d --- /dev/null +++ b/checkpoints/Qwen3.5-2B/4.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9531af5206eec505badf5c6b39425f877ca6b172626d7e6940075f7debdc7066 +size 25625492 diff --git a/checkpoints/Qwen3.5-2B/4.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/4.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dc0a387e0e60f62a26fd8e381fdb39f721010af0 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/4.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef4d1cc22eee33ffeb46970689b19da3ea5978d253b3ef6e2059e860f24aff5b +size 25625454 diff --git a/checkpoints/Qwen3.5-2B/5.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/5.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..06996f1c86e12c7f7f057e92b7d5bf6fa7d7d4b9 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/5.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61d36a3c009396a3ceb48a25d9aa469076410018dac359b136c029d709bb67d9 +size 25625746 diff --git a/checkpoints/Qwen3.5-2B/5.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/5.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..a30bbab141ef5a73ed414f03a8de26de76a571a0 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/5.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41f9151ebc69325b01080e130da6d5c0cab025a2d27c9836f6717bc7a90a03ee +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/5.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/5.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d64e2595f7382ab8be70b703b5b2891bc9665b73 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/5.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a87e35b4d9207923df9e8e9ab32d591608cfc2ebd8f2ed04513df235dc761340 +size 8586329 diff --git a/checkpoints/Qwen3.5-2B/5.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/5.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a9def2793b2cbffe8e941f7e8a44342ceef7c4e8 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/5.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90c94bef7046f6e3902065d6d283d95f49ec2c7fceb854d9f09e9f054ff02b08 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B/5.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/5.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c14fed8f4519233758352d10fa6cae466c7f396f --- /dev/null +++ b/checkpoints/Qwen3.5-2B/5.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01c9e3128672c641c094068e6039b1c70255624e58ab7c9a618599b0ca085d5f +size 25625492 diff --git a/checkpoints/Qwen3.5-2B/5.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/5.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..aacd6d9bd0d3ad69075793abd93b6a027a76ec03 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/5.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eb81412ee4453fdda899c8f347f8faf3cfa87a9e635bfc4206cb0d8e2b12cd9 +size 25625454 diff --git a/checkpoints/Qwen3.5-2B/6.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/6.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..a0264a2a05208de26e9f9c16b5b90594e4481fb1 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/6.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0093e32b36e58b75c6e25d41b79d8c56f9094c675fe8d4aea398c82af836c2da +size 25625746 diff --git a/checkpoints/Qwen3.5-2B/6.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/6.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..262d018709738257a568dd2643d71cb03cbcbb88 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/6.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:560dcce9adca9353f581166a9f09d5c3afeb6ec8d0aa51c85f869d212dfe489c +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/6.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/6.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6c59f1e28ad8ce143ae9a9eff4963e67c764c525 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/6.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc1ed6ef72156b48cd160126788ef15da3378ba8fd6f5661c1537deab2dc680d +size 8586329 diff --git a/checkpoints/Qwen3.5-2B/6.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/6.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1a86296276542515ceb3dbfed8c61dd13c8360dd --- /dev/null +++ b/checkpoints/Qwen3.5-2B/6.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9ad0c13379db2d0d77719767cd9609b6347ad6c58d9b5a14b97c2f1e0b6da21 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B/6.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/6.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..56b28a02ce58fff7a8476291e4809f7bf6ad08ee --- /dev/null +++ b/checkpoints/Qwen3.5-2B/6.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86f9263dc358336a10f470993c185c4bd3a108819e7ab43c075ed3f5d9cbd27e +size 25625492 diff --git a/checkpoints/Qwen3.5-2B/6.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/6.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4cc3e2725058db6c22f8e21f532616617c6e2aba --- /dev/null +++ b/checkpoints/Qwen3.5-2B/6.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dae379946ad71aaa03aeddec1224eac5274f48dbc634bd8e47d230c7596b57c5 +size 25625454 diff --git a/checkpoints/Qwen3.5-2B/7.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/7.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1fc104cd4ab152c663d365cfcfacf99182f9fe4f --- /dev/null +++ b/checkpoints/Qwen3.5-2B/7.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23474c7832aae458e500ecbc084bf9e0825b9c8ab92a839d639658b67397422d +size 25748372 diff --git a/checkpoints/Qwen3.5-2B/7.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/7.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..634f30e26086fef17b6772b6d9acb37208e68d02 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/7.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59da3a866aca9e3a5368167f24771b9dbc33896b59add3391bde0b33060b91c6 +size 25625492 diff --git a/checkpoints/Qwen3.5-2B/7.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/7.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..82d289f3c01adabfea6553cffb01cfde248c675c --- /dev/null +++ b/checkpoints/Qwen3.5-2B/7.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59bc7497ef92686fc69f9e707318e6726cd5a68d6197638c0c5105e2ac8ba27c +size 25625454 diff --git a/checkpoints/Qwen3.5-2B/7.self_attn.k_proj.pt b/checkpoints/Qwen3.5-2B/7.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f79b8e50caf01533ba7dc076e771a4fff4d0f10a --- /dev/null +++ b/checkpoints/Qwen3.5-2B/7.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e91948c8975e51e3fcb6d88955a83a64a87c9628e9dfab9735b0071096751ffc +size 2196429 diff --git a/checkpoints/Qwen3.5-2B/7.self_attn.o_proj.pt b/checkpoints/Qwen3.5-2B/7.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..969adb81c361af7e6e9824d5f58a6ebac95c00a6 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/7.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1abe74fb4cfada24fc450e3caccb8071e648183a0e8d3009ef8b96e7ee63b560 +size 8586189 diff --git a/checkpoints/Qwen3.5-2B/7.self_attn.q_proj.pt b/checkpoints/Qwen3.5-2B/7.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2614f00a9329a459644bad7b35f3e07d182c014 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/7.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e950dbf70bf45a8ff0fd8fcdf710f557898e0d698a2fe48f36e6b2b0759e359 +size 17105869 diff --git a/checkpoints/Qwen3.5-2B/7.self_attn.v_proj.pt b/checkpoints/Qwen3.5-2B/7.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4661ef8e7f3ebdf717de34e4d7ada543aa7e81bd --- /dev/null +++ b/checkpoints/Qwen3.5-2B/7.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd878df1c7973855a38cfe1c7050806568f11420597b9a99ce0c34a5f72216f1 +size 2196429 diff --git a/checkpoints/Qwen3.5-2B/8.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/8.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..54f6bedbc856b9738ae6b585645aa33eaeebe340 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/8.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad7a141842d3daad5260435c2b6cd6d3119ad0311d3a393f5036e1fe98bb58be +size 25625746 diff --git a/checkpoints/Qwen3.5-2B/8.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/8.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..9570ea50c7d90c9f87e59acf0eb0ea463a67c818 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/8.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:279c9cdcd8376a799bc7b4d12191bb16459beee52cc03c0c55bbbd211467a099 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/8.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/8.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f3cfca0bdacc1d79bd8c6b0895cb9305f0bfa17a --- /dev/null +++ b/checkpoints/Qwen3.5-2B/8.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:205c6686ee2479eaf95466a2631d5ff601ef65952dbc770fd3f6105f76d7bf45 +size 8586329 diff --git a/checkpoints/Qwen3.5-2B/8.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/8.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8d3439a098717006ec1b130b92c97797bf92a420 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/8.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20a17a821eada96cb33a82711ed69b41ec3626da1c725a05f11a3f823a14c086 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B/8.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/8.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a5df50547e13b2dc513a8cae05cf07c3ca90950 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/8.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53b25a2e29a302d9d40c6307882dc955556096ca02b78d22ec51184f0fc76eb5 +size 25625492 diff --git a/checkpoints/Qwen3.5-2B/8.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/8.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..be3ba8c65df8cb1a2891ef09c200b5dd23c7d6fc --- /dev/null +++ b/checkpoints/Qwen3.5-2B/8.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0f9ad69f47dda7b6310a47fdcedafbfca01e408fe59125b3aba86923c3dccb5 +size 25625454 diff --git a/checkpoints/Qwen3.5-2B/9.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B/9.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a936714c125ca965378ac37c6a8bec50da99331 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/9.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0175a968571b9475287df916ff0714e713b1e71768232018fa8d6af1c62805fe +size 25625746 diff --git a/checkpoints/Qwen3.5-2B/9.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B/9.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..baa89a3c505340aa1958c54346b5e947832fbdd8 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/9.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4689a61c700966f76ee72016304ec4b0c6039b550d6d8c1e8ad0ba83da0742be +size 8586348 diff --git a/checkpoints/Qwen3.5-2B/9.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B/9.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd41fec3461be74354e14352f126710b4ef9fb7e --- /dev/null +++ b/checkpoints/Qwen3.5-2B/9.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3126d2c760ff84e6cc4fc4dcf079358b5603b6e2458a5148041c95dd4b651bd6 +size 8586329 diff --git a/checkpoints/Qwen3.5-2B/9.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B/9.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..22bd4ef2194db2e871127a06c3767142b0240a43 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/9.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7787bbb71e50fbebd187c4e8b1436db1365b5a5558abca468fbb64b00c42e6f9 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B/9.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B/9.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f667dc081fd6c4080b2daef0c220e9c9faf0d00f --- /dev/null +++ b/checkpoints/Qwen3.5-2B/9.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98db75489f34a63fd0d20d3019597f3b0a36b7b06be6eb234c9216986de832a0 +size 25625492 diff --git a/checkpoints/Qwen3.5-2B/9.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B/9.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6d2361faa68463791c6a3335e23ab42b4b9f7ada --- /dev/null +++ b/checkpoints/Qwen3.5-2B/9.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7879597f894f4648df66386acaf237e94a2bcbf7ce72591fae1328abd06046b3 +size 25625454 diff --git a/checkpoints/Qwen3.5-2B/args.json b/checkpoints/Qwen3.5-2B/args.json new file mode 100644 index 0000000000000000000000000000000000000000..3e10fdd97bef248751aece9db5902b7201442563 --- /dev/null +++ b/checkpoints/Qwen3.5-2B/args.json @@ -0,0 +1,49 @@ +{ + "model": "Qwen/Qwen3.5-2B", + "params": [ + "channel_scales:0.05,angles:0.05", + "weight:1e-5,quantizer:1e-6" + ], + "epochs": [ + 10, + 10 + ], + "weight_decay": 0.01, + "betas": [ + 0.9, + 0.95 + ], + "eps": 1e-10, + "loss": "smooth_l1", + "group_size": 128, + "n_bit": 4, + "num_rotations": 8, + "skipped_modules": [ + "mlp.gate", + "mlp.shared_expert_gate", + "linear_attn.in_proj_a", + "linear_attn.in_proj_b" + ], + "unfuse_mlp_experts": false, + "moe_mlp_key": "mlp", + "datasets": [ + "wikitext2", + "c4", + "redpajama" + ], + "val_dataset": "pileval", + "train_size": 2048, + "validation_size": 64, + "batch_size": 16, + "val_batch_size": null, + "seqlen": 2048, + "cache_shards": 1, + "output_dir": "./output", + "resume": true, + "checkpointing": false, + "seed": 0, + "use_wandb": true, + "wandb_project": "paroquant", + "wandb_entity": "liang2kl-ucsd", + "wandb_run_name": "calibration-Qwen-Qwen3.5-2B" +} \ No newline at end of file