diff --git a/checkpoints/Qwen3.5-4B/0.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/0.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..adb356a83c9cf3f7e8f1da880eadc9b768e41a10 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/0.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d43c3019066e61b1beb6b5d36c4dd52aa45f3d47a44927e9cc0c45c1bc657a51 +size 42680466 diff --git a/checkpoints/Qwen3.5-4B/0.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/0.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..cf5d7005ce08e511ce566d52f48ce3575b55c28d --- /dev/null +++ b/checkpoints/Qwen3.5-4B/0.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd2af5f86336e346d636f4e84f109472a85197a31c554f69e93292bc7028945 +size 21381228 diff --git a/checkpoints/Qwen3.5-4B/0.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/0.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..20febce94c33a3939632251b5525e6e9030d4b02 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/0.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f930a8a17e247631d26a84c38328efb33f94b5f749779281ec9e7b52e66cc49 +size 21427289 diff --git a/checkpoints/Qwen3.5-4B/0.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/0.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..53d17d3d1238201c2fe94050d1f8c00554eaad03 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/0.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b463b9db8aa5ac355ead385c60be04a263c8bdb972d8368b296eadaa12a246 +size 48204692 diff --git a/checkpoints/Qwen3.5-4B/0.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/0.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0006467f2296f50ecc11748c2c96ca5d889c04b --- /dev/null +++ b/checkpoints/Qwen3.5-4B/0.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:965b0f4459abc89ccc7a3b681e69df5f72cb6458b06a838e060c78e025da6f7d +size 48005012 diff --git a/checkpoints/Qwen3.5-4B/0.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/0.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..12b3ad9ecf7e0b1e1741296da0c1d57a4e6e92ad --- /dev/null +++ b/checkpoints/Qwen3.5-4B/0.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cef12c2abb8e65c9f0eb75901ebd3b09d24fd093006ecdd0f3545028ea95827 +size 48004974 diff --git a/checkpoints/Qwen3.5-4B/1.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/1.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..f78fa83954a3f6aa50da837ff162d4879a5e94e9 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/1.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67a903bd811d1b6d6b745b1a48d4523f57c9bb2d8da6eb26c4170741ced41f4c +size 42680466 diff --git a/checkpoints/Qwen3.5-4B/1.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/1.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..cf12b29253cf373c99a46c4cc0f4d85ed29744ba --- /dev/null +++ b/checkpoints/Qwen3.5-4B/1.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70790dbe4e588d852d8af82787d20b9790ef5522f7b7fa05e7cd19b6572c37fe +size 21381228 diff --git a/checkpoints/Qwen3.5-4B/1.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/1.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..613e2f4aafd0f0f1481c9f4f22c373f8c6663bca --- /dev/null +++ b/checkpoints/Qwen3.5-4B/1.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc3ece354c655eebeca213020419ae573b6f40dfb9922d9e3ecaa5edf9248a3 +size 21427289 diff --git a/checkpoints/Qwen3.5-4B/1.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/1.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c7572647fa801d3e71b6d4efffa825df3808d958 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/1.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd13c301af376e72b31e23d98de9fbcf474bb946eeec745dc1967e3c5ea4f255 +size 48204692 diff --git a/checkpoints/Qwen3.5-4B/1.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/1.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..520ad1529fc08646cd00985d8ba2518ce6426bc4 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/1.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:696d08a820651b17d86cca0724a506f977f86edb6b149ddfaf2cef10382ef9e2 +size 48005012 diff --git a/checkpoints/Qwen3.5-4B/1.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/1.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec266705dd5e5f97225d7aeb0fc9d742f9d34f8e --- /dev/null +++ b/checkpoints/Qwen3.5-4B/1.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dd81af871aa7d70711ea1605328c78c799a8edcf8e1ff13f86d451b49a262a3 +size 48004974 diff --git a/checkpoints/Qwen3.5-4B/10.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/10.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..44aac70232d5ab78e670ac1843609676d7b9ff68 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/10.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5cd7867c81014cc62690c71918743f436c4bb481784e4787a83114bc8ecda2c +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/10.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/10.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec3a95433bfcf6446aa54627d70a04fe488908da --- /dev/null +++ b/checkpoints/Qwen3.5-4B/10.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1517861766832aef758964285e71539954dbebb4472fe8d5ae186f711235aaa +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/10.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/10.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6e84e1e089d06d8bdefaf35ba9b194a417dd4f1e --- /dev/null +++ b/checkpoints/Qwen3.5-4B/10.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e3ef67f28f0dd8f98bb747eaf89738539ed21903e8ce35c83704f6251700d3c +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/10.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/10.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f4a309b2e10dacd1e39aa94ba4cecb35ac08e295 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/10.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82622dcae23a53dab155945796aebb096d7a4e1121a6637902577a041828fbe9 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/10.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/10.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6b48423ca7722f7ce94b292666525ed10c0893c4 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/10.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c9c24d80db93f1dda18cd68b9f575eaa83d3078b6cc20d6b4ce8cef3419e448 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/10.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/10.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a7c850de04a40c57360b59f6a58b9a775860633a --- /dev/null +++ b/checkpoints/Qwen3.5-4B/10.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9324379b309a7a71c1a1598a746e922a5836f9cf46635779540201f7d7b48cf0 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/11.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/11.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a09909584df3cb2ff4f405fb4151a0233c06685 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/11.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:975941a3aca372753a34f3549302c4bf56cecf42952d2b0bea984fb497321fa3 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/11.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/11.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..77c3d33e51b1991a2e278071ef92a066a1d10f7b --- /dev/null +++ b/checkpoints/Qwen3.5-4B/11.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3c85ff8dd419aa090716ce45a2c112e9e8b2aa01a9e76bcd0882156bcc4a850 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/11.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/11.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ac2399f17e7b5d23fb604261d8226cff7da5a1e6 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/11.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d7a09bd2d9fd2400e7aebdf0e665e86e69166fcfc6b83ee605f7d17c7710acb +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/11.self_attn.k_proj.pt b/checkpoints/Qwen3.5-4B/11.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fbdc49cf4d652e749d3e1f301e921a057a22fd42 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/11.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8309cc0ad489e5d4de048d54bc2fe8ea263657e7390c422b6099c26b386f8802 +size 5406688 diff --git a/checkpoints/Qwen3.5-4B/11.self_attn.o_proj.pt b/checkpoints/Qwen3.5-4B/11.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..35b8b984dea24213b98ba26a9f2a2ff429f334dd --- /dev/null +++ b/checkpoints/Qwen3.5-4B/11.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe0ca69ff80176aceb28b4e69c0f8f845748a7d28d91aa6f3f170b2722419713 +size 21427168 diff --git a/checkpoints/Qwen3.5-4B/11.self_attn.q_proj.pt b/checkpoints/Qwen3.5-4B/11.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ee5cd442b90f85f28375c62ac6dda883414b6e50 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/11.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4df81378f62c76f02d9149ecee768926388e8df0b6567792b9b02ebc0ec28f7 +size 42680288 diff --git a/checkpoints/Qwen3.5-4B/11.self_attn.v_proj.pt b/checkpoints/Qwen3.5-4B/11.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..511ba447abad006459107a856a16408bfa57b4fa --- /dev/null +++ b/checkpoints/Qwen3.5-4B/11.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31872b5555fc8466314ec77ce95972ab81260ea5bb0ef1b189e3cf48f9dcb54a +size 5406688 diff --git a/checkpoints/Qwen3.5-4B/12.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/12.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a6b77803d1f0acda80cddf7c7d56598bc642e00 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/12.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49c6277186e472bccc2ef76c3af3eb200e439b8d083bf50bbcf5614aaacae6ca +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/12.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/12.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..39563a182486dd4e54387d6bb86bff2dddb054a0 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/12.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:372bdbc3a719f7d7efe7f17ad573865ed25bea6eac41c789f1b05a75cfe9f930 +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/12.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/12.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..27fb07a05f51007cff6634a1b6cd062213b9f9d2 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/12.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd1d2e89fb96d0b40d946f982df9abf21296f03c262ebafc6663ca71448fdae5 +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/12.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/12.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ad52873e347ed65ea5ff45f4d76fb6e68127c10f --- /dev/null +++ b/checkpoints/Qwen3.5-4B/12.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:374e4d509d5b690d4a01021a584f5927924082c4ffa309e6524d352112445d20 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/12.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/12.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6cfc91873542f16fe06472d7c8795b9681183bfb --- /dev/null +++ b/checkpoints/Qwen3.5-4B/12.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:106d3d5c969f940b743579d8d1845e5dc816bac48303a1bc9ce87569dcef3574 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/12.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/12.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ccfdfaa29fa1899cc7360678e3ba757687b5dd3 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/12.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c5e06f8d2882a651d47f685242eba116ccfaaf632d7779a4ccf0914938db21c +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/13.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/13.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ff786a7273823cf59a0cc84ade7e16ed6e65415 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/13.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbf621090b81377543c3af23375d159bb4ff111c881c2f2b2481167c948a112d +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/13.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/13.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..4282a367f1b5e7c52ad530a2651e4035ec60b882 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/13.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41dd4419f530d1581cd2238cd1a0ef26da4dc5c7b9691c5d2479921b5862c0fb +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/13.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/13.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d4d324c13cdc791597c73dd18c65f2f1293d3301 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/13.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eb6bf28fa6ef9094941a4dbfb80242234e84c55c643608b30b6cb874d04f605 +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/13.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/13.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..73356c8bf79f331c86a5d855270058b45f697f71 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/13.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef629926cd320490b5137fd66063010be08be5151304d47d83ab6c019e0e7eeb +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/13.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/13.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c5d2dd3fee7bada64bbeda7f460f139c0cd9697f --- /dev/null +++ b/checkpoints/Qwen3.5-4B/13.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b4889926d71820b1339d03662a033bdc7e6db9663b9d6236670986e662178d0 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/13.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/13.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..284dcfbcb3e23a56b2c505ce0459d8d1358b3e5d --- /dev/null +++ b/checkpoints/Qwen3.5-4B/13.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e49863dc5b410e06f4d2623962af7a0eaa11f6016029c46594fe2fdb50565bbe +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/14.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/14.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..8361b99300a4b797a5fb015f304ba60ddb6b2126 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/14.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33ab59fb36ae7ed94a40dec2274bdd725e12cbcbb3fc869bae785bec3ad77469 +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/14.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/14.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..ecb59570eba3f9113a2ad3a6ee3a700562c86f42 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/14.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e7d5cffec2b28ca81eaf8d2bbd29304575b9436c4fe8d9b2a45ad1ef093a2a6 +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/14.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/14.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..11089ca69683ab571099c840aa8a898c70327e73 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/14.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f225616341e9b95e686e2426959ffd3414c5df04accd0fc884f1e84c60bfa183 +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/14.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/14.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a0bb2df50ae7a699fc81b46a4ca8e5961256ff59 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/14.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e0edc1a939f4a5ebd0a963fe2dd7fe43c1fd0e68b0afa24faaf0ed86c501aa9 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/14.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/14.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3975a3f1cd93888e1e592b99d2a3d262f884981c --- /dev/null +++ b/checkpoints/Qwen3.5-4B/14.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aab5be75dbfb4b8e173bcb63a3035b8eea8b1648d228105d9513dc073efa1aa8 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/14.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/14.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..07b320158c1f30c28dd61693d6654388be275108 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/14.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be4c9b1fb5630d8bba83a1342ce28c07f95889f27b4cc7e25cf2b551696a2ed6 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/15.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/15.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d381604909f2c27838ece599efb8ae73a324bdd2 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/15.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:051c173ddd2c14ec4664fff2150e5c6bb61f8866263d8d640ab50613a057d21a +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/15.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/15.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d51afdb279106e3c9f3653a35c46798f7ee7da6b --- /dev/null +++ b/checkpoints/Qwen3.5-4B/15.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d43358954b4bd3f4428afbc4bda266a27ead8813f5c7ababa05d97ac9ad852ee +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/15.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/15.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b725f5b333b2e7f9a826264db18a1d9a7895c123 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/15.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d70238845964c79b69834d89f630b4cd64050c98d407306a652be3937243d609 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/15.self_attn.k_proj.pt b/checkpoints/Qwen3.5-4B/15.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8575ef7a2e46abd6f4a4056e5469eef2c3919cd2 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/15.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ea9d5f7482bb148730617689dc47d1c74573109b8b66fccc23006b142ac9ec6 +size 5406688 diff --git a/checkpoints/Qwen3.5-4B/15.self_attn.o_proj.pt b/checkpoints/Qwen3.5-4B/15.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b9536f1a027cbd6e5e8130d7dea631173768c6c5 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/15.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d8039e2c18090eb53ebbda4586fa39e9d01d89ae12ab189a5eb103913df5790 +size 21427168 diff --git a/checkpoints/Qwen3.5-4B/15.self_attn.q_proj.pt b/checkpoints/Qwen3.5-4B/15.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c7e03e6e5e1c34112385f4419a28ec43fb869223 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/15.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8922fc68a490f6181568f0bd4718a663a46d1b090b4d4ee99aef9c702d36738 +size 42680288 diff --git a/checkpoints/Qwen3.5-4B/15.self_attn.v_proj.pt b/checkpoints/Qwen3.5-4B/15.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e08111f7a94c5f04b1068931bafdd14b23e7d53 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/15.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41085bfa11bd56da3fedecb8ecb755834a73cefd0ea1f8445b7f6fae2f00bdd6 +size 5406688 diff --git a/checkpoints/Qwen3.5-4B/16.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/16.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..4964aafe10928aa5d4f8abb2bf776182ef97b731 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/16.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bec2f4c7c03a676cc996870c976ab3615ae8dc2db2eeee613f5255b2a063816 +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/16.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/16.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..f8e3e856f9cb95fd4b51fb4976eef022b302ed98 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/16.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3f4f3beebdb500f6944666bc5d129210aa53d44774c182d03bdac5b147666d9 +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/16.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/16.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..cfff65fe0bec010e46d855e3dd499881d8ace96a --- /dev/null +++ b/checkpoints/Qwen3.5-4B/16.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b070ced549b26ac5282371b9c9ea7005dc9a463e71c97becfd93a2a2696f51f +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/16.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/16.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0edabafdfa7c55aa93850a5f53e9fa6d2adcc27f --- /dev/null +++ b/checkpoints/Qwen3.5-4B/16.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94dc1eb3c5159d745aef05fcf424febc2a2947dd1f707884e054e29d96d38b23 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/16.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/16.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8ffe10fcf87432f9516c49ef8763ad81a7d6cc8 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/16.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a05b0b2b6b261e1733bf18765a4a6f8bbe316e260d0ae4a7c91c7b971a5ded6 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/16.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/16.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..922998617ed2f6507faff2334dc8220e77a8bb34 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/16.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef3d4c200980f123845f2a16a8c8fedc0611c40ca03edbf20713a97bf2d3f00 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/17.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/17.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..3bab2900616ed606787f087c5ed944e65fe951b2 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/17.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7385ff2fec165c264da1a89cf3bb45b5ec60c131c593cb63c4172d7068997142 +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/17.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/17.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..5667ffab8b9708c7796b545b8d6003e7353cea0b --- /dev/null +++ b/checkpoints/Qwen3.5-4B/17.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e4857983902137635edf530a01ce98f6b3db32ae3ba26e0dcb68bc9c2273160 +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/17.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/17.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..011772f5e64a6a4e82a663a124a4bd3d24192ca1 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/17.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13f855ee7238baf3a4fc4967517ce1340f9a1eca7d97b446a5338c153e2c703e +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/17.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/17.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d6d4167208e32878547a0f09d7fe610709d0f0d --- /dev/null +++ b/checkpoints/Qwen3.5-4B/17.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58de165d5ad1c11f5e172fe735998ca62ee700e7c03618242b56a9120de2c32d +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/17.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/17.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..70ac840808ae4c3ef2db5fe797ee2f1fbbbe3975 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/17.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21a2cdea62ed4439d346545d6ee8a62f92df5b5b6d05254d729afdcafdfb42f5 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/17.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/17.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7e15cc2dac48a3b6c55b9da70d74c69f85c0fc50 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/17.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e44e484bb0003dd5ab2622160f93033f9bb092b51de0b537e16e96ea911b2cc +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/18.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/18.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..d73d43db56692f9f00790ba7b633d982fcbb1215 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/18.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d56b2ac0c36982238c17ada6eff589feea0dc634ecf6ff1f01b9539d56eb7590 +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/18.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/18.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..a156c2960c15a8593abd01f4092bb2d5b9dedd7e --- /dev/null +++ b/checkpoints/Qwen3.5-4B/18.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c20573abde01d3021a995158d1ea6cf5c6e07246ce9596bf2c168179f7ff358b +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/18.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/18.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..aff1898b774622377b5235c596c65846ac1f3862 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/18.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7466677cf71fd0091061fdfb9d8ea14cccaee681a7543e8e8edb566d4ba8de7b +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/18.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/18.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f0a7133b3d7d086e8927b0c775d191fdb62a0c1 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/18.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03154bacd8388a6c286daf05ceaaf68ee35def1fcbf5deafcb6da8e5b4f96852 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/18.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/18.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3afbf6184b2a578a0f2415cd0586b3bc3019d772 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/18.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:175f3906348fd59bea5b1431e0eb05dea73e93b6279268e8187b464d3cb8a9a2 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/18.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/18.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f74684d1d3ac68d356da2a2d00275b85b8289667 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/18.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e3c5d1a18e9883544e57869b20073c6c2ac0c8f2fec01d941e000b4c47c37ff +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/19.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/19.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..47b4ad6662364773ff32367f7292aa58f0d616c1 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/19.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80814e483238ad7f5ac03d6e43121d7e3c75efb0e76e292991cd4e4570fa5048 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/19.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/19.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb577cf09588cd5dc0baa06603eced2a7abee268 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/19.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:310a249f47286ec5bbaa38967a1d030b1648cfcc9f9ad882d28a51a61f4b3d1b +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/19.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/19.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c51d8e365f25293bb731234a77fe4d300d503074 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/19.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc3c158bf7d00431883b6acfba9770c35da475ec352c768a6d403baa0c52b6f8 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/19.self_attn.k_proj.pt b/checkpoints/Qwen3.5-4B/19.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..05cef97124680cedc37aee3330dc4ab9316e4d1e --- /dev/null +++ b/checkpoints/Qwen3.5-4B/19.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dce3ed5e1bf3d6a10a38abcb200d98a77189b2a22ed76341d5bfbb9cd0f6b5c5 +size 5406688 diff --git a/checkpoints/Qwen3.5-4B/19.self_attn.o_proj.pt b/checkpoints/Qwen3.5-4B/19.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d179c376732963a479f2b14315b3bf94bb955885 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/19.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4819e9e3544b146dcdfed4e06b80a1ad6bd31794604497db33f66b51a5fe4f81 +size 21427168 diff --git a/checkpoints/Qwen3.5-4B/19.self_attn.q_proj.pt b/checkpoints/Qwen3.5-4B/19.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..78bbe96695c4a4f52f59dbfddd5c81d469b95386 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/19.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb13e030e45c322e7eb4b4104b63c69f7af1736a5014b507b8b9d6cdcc0ae81e +size 42680288 diff --git a/checkpoints/Qwen3.5-4B/19.self_attn.v_proj.pt b/checkpoints/Qwen3.5-4B/19.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d4b85382bd6ac9873a6e64911cd3b44c482e3af2 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/19.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11e9a94dcfbfb36235910f197317f510131d0695995e8b34eb261acc6618c602 +size 5406688 diff --git a/checkpoints/Qwen3.5-4B/2.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/2.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..f823c8ac9cc104a2a6771d23851e578b37752f76 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/2.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e88c62ff5c3969864039d7140f16dc77bb39727e91beef49bc40149b5cac5d42 +size 42680466 diff --git a/checkpoints/Qwen3.5-4B/2.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/2.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..a700714f8b004fc2511bf950aa4712cb0825437f --- /dev/null +++ b/checkpoints/Qwen3.5-4B/2.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:197f41f15922b54e55ff7ff09dcfb806d567fd89c8b64320c6d14ec52baf41ff +size 21381228 diff --git a/checkpoints/Qwen3.5-4B/2.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/2.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3c35e964bc9a2318e8d4065048e4190f3fd8f8f5 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/2.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bb7a11ebcfe496779297bae627f5f94c2bca07dad260de60c41b69211f66459 +size 21427289 diff --git a/checkpoints/Qwen3.5-4B/2.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/2.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..115af2fb206f623df882375f291c4eb7d1de9433 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/2.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8808176c8553e070fc91dc27a53bee9d29cf320f05c46b8a5833aee8827896fe +size 48204692 diff --git a/checkpoints/Qwen3.5-4B/2.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/2.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8b4927b5cf3f6a3ecf47a2405b6ec10522a55126 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/2.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:805640933f8fb825c4c98c7a2f1b56ede2afdb27b0b2f1d19e3f16d572d2c8af +size 48005012 diff --git a/checkpoints/Qwen3.5-4B/2.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/2.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b5a242eecec3d44530f51e3862c648cad294252 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/2.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e4a4e1df0db6d88ed14e1872b32628210be9f9b6c88be59034c5432c22f848c +size 48004974 diff --git a/checkpoints/Qwen3.5-4B/20.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/20.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..555806b4fafd84992f80283b6d30bf452a66f388 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/20.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d51409c541719c681edf9c9a517becd7e38d46e65aca0c41b335d779f1a3368 +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/20.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/20.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..fafb13ee32b91582a737391c98f37ca137278ca5 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/20.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efca3a372ba14ff15193778cbd82ad7a6c231fe19988c0677e49b341172179f4 +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/20.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/20.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..06e80ce1d8db4234452a35c1804d46cc25fd39d1 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/20.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd9010543e559984405611c60f7a958000e5f3c5eaa8ec295933ab75f7b0ef72 +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/20.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/20.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b31362071ae33ab59bec7843f3551823665dfc71 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/20.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2806fa060a531629bcf45a3dffacaf82da242fb6e2228247f71ea9a84d69d72b +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/20.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/20.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ee25882e0b4838f81996b5543d421ab9eb83f53f --- /dev/null +++ b/checkpoints/Qwen3.5-4B/20.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abe9baf36b08e42d564372861184d050978d7b837c73844ecc6b2ee2589255f8 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/20.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/20.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e583b93bba632d5db484e423007c23a62dd479c --- /dev/null +++ b/checkpoints/Qwen3.5-4B/20.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5937dcd634490e194265fdeeaa4fc120f7d8b618ebc760d08915c600f4dd7859 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/21.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/21.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..8fa1139c1d152d24b6d157b0decbd8ea3f1ffd19 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/21.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7900d8bc21686a58fbede84f5ae96c3ace7995e07b39507ecdc1410722a2c81 +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/21.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/21.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..09606e39a25f5ebbc294257acd7199ea577d4301 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/21.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7111ea0a2423fe838d0d146ec1c3c3d6a1c89cc840f9e1f973eb01d5fe5339b +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/21.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/21.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d88601dccc6f7bb90244a5dbe90f54d9a9654d4 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/21.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f86ec4280e4bd6d2a9e298cfbd9b588ada4ce5aa8bfa825cb26ca395bfd9e74 +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/21.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/21.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a7099c32b6194937c38045af78f81442670c82bc --- /dev/null +++ b/checkpoints/Qwen3.5-4B/21.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e64bbeab843d04ee99629ce579d500b026b75713ac1febef60f8e3f282c67fa4 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/21.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/21.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a85a602fe94086a5b7a8956764f1b6c5354da692 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/21.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be7ccbc8630d362b48414749d889642a6e1a952f086b5f7c3d95073d6c03d40c +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/21.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/21.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9f4d54466232aab3b8ee0b2c799e241bf4444262 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/21.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bea60f2de899def7d7d5e3b8852c6f123aa7bda36947a7905a3ca4bbc7ed91b6 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/22.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/22.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b2a47f4bbc181610468854dd0ec1026ac20a81e --- /dev/null +++ b/checkpoints/Qwen3.5-4B/22.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1349c32a9a567dc15d1b430552fdb79a965ff596f2f3dc97b32318e94efa06b +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/22.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/22.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..b32043706aa4beae2c8fc4b9b05416c496d9846d --- /dev/null +++ b/checkpoints/Qwen3.5-4B/22.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c47915150096da556d75b726547d83b81d02176ef07c5a5b177e29fd987dd14 +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/22.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/22.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b883e2d9112344632990841e6720aca016f1ac95 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/22.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cc3bd40f34f468b1c7d56b002b054932cec5646d36e913966f4f16fcfa09898 +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/22.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/22.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b57d4f93e38e8ad3e4d83c66a7a9d93d275e0ea5 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/22.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af770e7dd659caf79bf2dabfbf44e84d04887b48c00b19a3713c9ffee2002664 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/22.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/22.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9015d532deb3c083b3542e91b1232d37f2a236ad --- /dev/null +++ b/checkpoints/Qwen3.5-4B/22.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a2d29fd98fc17c15d9ab8f7c31b4cca3dece7b1b2bf86becc8d7d34afc59251 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/22.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/22.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2809872622c108f876acdd56c9d28adfbebf40b6 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/22.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:663aed31778a3890f553ebaf1affd69bf423e13282431f9943346bc8da55a480 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/23.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/23.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..95584d3a2990e215f3695fc69fe36552a904ce21 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/23.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80afac29ce61d5056c1bff58bdee0282ac2b39a3ecba51f1446965fd1300c91a +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/23.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/23.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fdf9925c69a323f78c267f365142484425974797 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/23.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec4f54f8ff8f738fc1fccc9fc54e0b775aff44c7c0843255a14d04a063691042 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/23.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/23.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..819112e91b7f99ea41e50d4e069ea8a71b878aec --- /dev/null +++ b/checkpoints/Qwen3.5-4B/23.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8bdb9f8f65baa92a95464d1b8f514f1997a553505ac43351f7e3da92178c963 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/23.self_attn.k_proj.pt b/checkpoints/Qwen3.5-4B/23.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6de4571899d5c31c476dea685a8e3ded733bbc57 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/23.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:414f3f7de512482321fb42131b57de5e18de21f8d137dd8a7f7d7fd9410cf0f1 +size 5406688 diff --git a/checkpoints/Qwen3.5-4B/23.self_attn.o_proj.pt b/checkpoints/Qwen3.5-4B/23.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1c2c775a137d486b067a03662a44ca4773962a37 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/23.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbeb2576d4e5bc698007496ffb0f5b98dfa0a64ab1274ee1dc203ac0b6450f84 +size 21427168 diff --git a/checkpoints/Qwen3.5-4B/23.self_attn.q_proj.pt b/checkpoints/Qwen3.5-4B/23.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..533a935ce80a2c51df9cbe41bb644dd18fa2d6c2 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/23.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1db27ec8192e758f7596c24278c811c2ed8e0415ed597436077cd80c01f6649 +size 42680288 diff --git a/checkpoints/Qwen3.5-4B/23.self_attn.v_proj.pt b/checkpoints/Qwen3.5-4B/23.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b6289f54976f2dbb313ea52ba623de81d3b1beb2 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/23.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1dd3237c7db2de2b77d2b270fc8d9de61120e7dde4ba1db993b9a4b4e359421 +size 5406688 diff --git a/checkpoints/Qwen3.5-4B/24.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/24.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..e8e2d32c751b9015115a990eeb7408e3038a40d0 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/24.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8f74a15486cd0cf8e4b5260f711a37a7f5cf47d0506590e765a7cf6f94b54fd +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/24.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/24.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2f4f9ea3b430fa5c822ef6bf9ecf1d9cb3d70e8 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/24.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aebb5692920f32e2d7fe32ca77cf4e2ff9898316882c884e1699d495a3224b0 +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/24.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/24.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a8db15d28b3265765e00aa5734fab3247cbfb5a6 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/24.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae1fd52a23de39237f3c97220094609ae95965d5bf399c840e3d6bd614b8eac +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/24.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/24.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6dd730c48de9ac6af628b7c0158ce7f041f0e77d --- /dev/null +++ b/checkpoints/Qwen3.5-4B/24.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb4432c89cb81c55797209e5236f21a22fb4ab4c958a1055447974c94064abcb +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/24.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/24.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d5ff2c6c6615c5a945c422c67b151c877b5996d --- /dev/null +++ b/checkpoints/Qwen3.5-4B/24.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:374009df43a5ac9594d647d21d005adfe0906ffff208ebfae53c87e2d5983acb +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/24.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/24.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ac3b0496cc5adf5da5cf5c38cb4c0280c1680ee --- /dev/null +++ b/checkpoints/Qwen3.5-4B/24.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:459490c57fc7051a6108d59d35d76b95bc6888451a49e7b97cd8ae073de86ab1 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/25.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/25.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..2eef46637e1303e5125c20155bf09922bb4daf27 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/25.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb02cd4738356ffb493714bcfbbfd305f3f90a01540bd0fd48a189f3636862a +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/25.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/25.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..6079c58b4079ca55bee4fa5409d93e42134bfbaf --- /dev/null +++ b/checkpoints/Qwen3.5-4B/25.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d99b58c309333622ee700434872640e14de7ce636b6b2e33233c8d9461cec54 +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/25.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/25.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..22d7b152b1717a0a62b0c264a1d4ce85e0b76d3f --- /dev/null +++ b/checkpoints/Qwen3.5-4B/25.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aacb8620196dbf2313b40455a435930e81cb8e93f3226038598d3a927d37f0f8 +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/25.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/25.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e91fbe852eb759396941d558298fa915ccb02947 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/25.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67208c319f3941de08e0ce19544d3fdc7314375f22b907cfb8139684f801cd70 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/25.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/25.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c480c1f17d7f1148d8c37047d69ca4f69b3c4198 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/25.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88f5a59c4bd9c9b35d5512fedd7352c3b3b0a1c83012afefba9cb96e1c5db8ca +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/25.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/25.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a5da9d54213540c72b6605ae6371cfd6e313f370 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/25.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c41a87012a092888e6a5dc2a9afa8fa4c1de2a0859a1e30ef69bcc0b375fbb4 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/26.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/26.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..3b989d6aa8e56b1a37afd08bb862e55a9c2c570d --- /dev/null +++ b/checkpoints/Qwen3.5-4B/26.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b59b8977e82c097b4957531d83502dc08e4de379265f62f850677d07a4ea028 +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/26.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/26.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..9468e44c93fbc0c3285d707bdf91335f9a6823cf --- /dev/null +++ b/checkpoints/Qwen3.5-4B/26.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b0ea3f64f88b544f3063f946fa93c3b9c51e3c0d2de64595dc3b63861b86dea +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/26.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/26.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..74b20aa043c5ffa8237ec6bf757e97167de035c0 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/26.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e97c432d804726ac8c983db76692eb3a22220effd8f5e6f76608645b41e387f +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/26.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/26.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1c144cb8018808194377e206b63a59b9ce73b607 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/26.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b282563dd693a302ae587f2ec7a697744ab045e6fbf015962439046d9a0d8a8 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/26.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/26.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c1dfca9c860ad999acb4411c445351baed65b41 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/26.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1f3c57c8b744d0e0523a962e7bf5f2a7a95c682ceca4ee404a766e5113ba5a1 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/26.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/26.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f51444777acf183bf59efa27f309100d4d094ea --- /dev/null +++ b/checkpoints/Qwen3.5-4B/26.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3a515920b3e669cfecfb7ab5244bef5adf34905da445701a4ab9ac1770ddc1e +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/27.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/27.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0bead4179cc3b3f11eb5dc08690c701995c09de2 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/27.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4df2971e253f9aa0d37a17cc510ab8e2fc55a5e635e173e55af6702ada894b77 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/27.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/27.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1fbbbb861582cdbd6e4826be4f5900019e6cadca --- /dev/null +++ b/checkpoints/Qwen3.5-4B/27.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85248e468ee94e00129309ca4b69e8065b3f65afc12125a3a3fefc50c8e95405 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/27.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/27.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f72175e7e01e84555613e98beca280127ed435f9 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/27.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ec5c1763015f9eef01c4db2a0d32485d195dc6745b89271f55eeec20b137475 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/27.self_attn.k_proj.pt b/checkpoints/Qwen3.5-4B/27.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dfe4d44e53dca6e0a6b5ecc7bd883dc5e5b3f563 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/27.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3133d0aca9b120b8513df7af034f10c223548034c00b38c1190cc0266360640d +size 5406688 diff --git a/checkpoints/Qwen3.5-4B/27.self_attn.o_proj.pt b/checkpoints/Qwen3.5-4B/27.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..645ed6b876069be2bc5986ac360932fb9963784b --- /dev/null +++ b/checkpoints/Qwen3.5-4B/27.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c4e9205e6a97172dacf570a25bb12e438f7011a01844f82cf9309d7454790ac +size 21427168 diff --git a/checkpoints/Qwen3.5-4B/27.self_attn.q_proj.pt b/checkpoints/Qwen3.5-4B/27.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..06ca8979abcfcc598627a9687fb02093be3589f1 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/27.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1a4c5bf694395d901019a81ec0657757f493a74c4334dbf731dc8d5dca36de3 +size 42680288 diff --git a/checkpoints/Qwen3.5-4B/27.self_attn.v_proj.pt b/checkpoints/Qwen3.5-4B/27.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f771a446281cc2ec13827b08eafa65454393a6b3 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/27.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebc0feeb08e5f2bc95c19ac38142deed8148c5fa6f055eccb5344a7564bd3de2 +size 5406688 diff --git a/checkpoints/Qwen3.5-4B/28.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/28.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a80b30945fa45fa7ec11cb135e6ae698e0737db --- /dev/null +++ b/checkpoints/Qwen3.5-4B/28.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fce1b925ae4c04105a26e3963f40b1cfbfeb39e01008b5cc9443d70e39fe1769 +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/28.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/28.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..ff7986a0e7c757480aaf6b39216b9490264ad33f --- /dev/null +++ b/checkpoints/Qwen3.5-4B/28.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2583877ff7e08e03846b7b6dedf5b33354ecf8e59f74e9a4ec869b0ac7c209fe +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/28.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/28.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..12a792a6f9eefd7feeae89f4cfd3573bbde237d3 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/28.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aac16a832efddf602c6b107ef5e0f431246b2bafbceac174657466209e83a80a +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/28.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/28.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a816eae864bba39d07fedaba1d9081d5b17aae8a --- /dev/null +++ b/checkpoints/Qwen3.5-4B/28.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ed0d213d6559b805e96cb0bbd56acd64a3d586773fa2c74d3a32208494aff79 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/28.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/28.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4534dc904653486b6f14188c7434eb6f797f3244 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/28.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:308b88d7d51c490aa732b287c064fac3d097466c9e1afe6d45235151a9a5cf35 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/28.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/28.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dbe3beca0269629c51421fd3c550a18fa06f3228 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/28.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce9a05ef3f9ea3e7f5279dd2d3d1d4f164a8904649c61b1ac318db24478ada6 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/29.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/29.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..607596ab772bcdd8a95bfa657ea15a43f12bcb2e --- /dev/null +++ b/checkpoints/Qwen3.5-4B/29.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:289290fc1b0fa57ede4aebdc025a92a91cf31112d1de88326b4b42a4d3888c63 +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/29.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/29.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a370f2b62e21806ca29112823d60b0bc84f88cb --- /dev/null +++ b/checkpoints/Qwen3.5-4B/29.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:508e8c63fae79c2474ffd40cf75238ea403a62a6982654fd9f27f95a7b454590 +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/29.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/29.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..47cb7ea8dad57f4a0925351bfbf9b2dfa8867ed3 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/29.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b843ba7d769216ff24576dc5fc74a10c47c388b9815eafe0a176f2e0cadbc9 +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/29.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/29.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..cc519d9b3af01c430831acf899e38d13d1293f43 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/29.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d5f39b9cb0a0135c6e8051e78a514f9a54abb0c58d3279fee33f9b6b0653ea3 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/29.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/29.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e980a4033a8829510114dbb8bf76f45cb26e956f --- /dev/null +++ b/checkpoints/Qwen3.5-4B/29.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:257fdf1b0d265fce6f64ca3ccd6ddade21b0a1a56e37ade78f2ca374d36d4b35 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/29.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/29.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..83de11e44519509efc55c73b3b09e03fac23d50b --- /dev/null +++ b/checkpoints/Qwen3.5-4B/29.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6477776ecf872c85e6bd34712267d94f0c390bdad68094ce39fb790894d2d51 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/3.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/3.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..47e0e37ec7db8dec6f3b18dcd9044af6b3aeb74f --- /dev/null +++ b/checkpoints/Qwen3.5-4B/3.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f33e918c2980602ea20a6a34c1c3d919c9b4bf0cf497734e9c74a67e2db5c6fc +size 48204692 diff --git a/checkpoints/Qwen3.5-4B/3.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/3.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4121751184a0878f9ea37c114d10d919217f2079 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/3.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:960866650b6a86b0186ab8c3810d62f2d023fb26b295c3f1bf9a8bf4701b7eed +size 48005012 diff --git a/checkpoints/Qwen3.5-4B/3.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/3.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d725fc3306bec604ac82af109ffe1634de54d742 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/3.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80139cb079afc9be979f2dc5138ab24de66e5a6f8486a5fa4bd51ec66ed56433 +size 48004974 diff --git a/checkpoints/Qwen3.5-4B/3.self_attn.k_proj.pt b/checkpoints/Qwen3.5-4B/3.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c5c4dfc0b327024e499b054c220d3c0dda6fa21 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/3.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a4420e6ae90f98cfb501001e6564dcb847d9ce5a3cb7066121f82dbc7eae59e +size 5406669 diff --git a/checkpoints/Qwen3.5-4B/3.self_attn.o_proj.pt b/checkpoints/Qwen3.5-4B/3.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..73c82f743d611fabb7ebb4ac73c20070d592dbfb --- /dev/null +++ b/checkpoints/Qwen3.5-4B/3.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0ac21e497947705cbf820f6f0e91ee83ae826922f1074618fc8cdc48d560acf +size 21427149 diff --git a/checkpoints/Qwen3.5-4B/3.self_attn.q_proj.pt b/checkpoints/Qwen3.5-4B/3.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..351f5e89e7b3105304e7ad211dbf67e7ce94c8d1 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/3.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:688d69160a5a8ad7c037b2afe6991b54b1b265e1ee2eac25ac993cb5c84b6370 +size 42680269 diff --git a/checkpoints/Qwen3.5-4B/3.self_attn.v_proj.pt b/checkpoints/Qwen3.5-4B/3.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3a748ae51ebf9f532b1791c72f1124d4f2526b5f --- /dev/null +++ b/checkpoints/Qwen3.5-4B/3.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6021940c2719ee81f7c6ff0ae4e394169dd32493627732d89e01a357e5de8a38 +size 5406669 diff --git a/checkpoints/Qwen3.5-4B/30.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/30.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..b753284c745121ab1161f9cf665fea14f6be6ddd --- /dev/null +++ b/checkpoints/Qwen3.5-4B/30.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94431683f16a911e46ddd49b942005b195f2a856ab45a9bef6543d94fe627206 +size 42680485 diff --git a/checkpoints/Qwen3.5-4B/30.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/30.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..bfff947ad79d8d8decb398fabd1178d4384c8b23 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/30.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94a3de67ac854520a9e73675562708aaca8fab256e58858183535ba46638aa7e +size 21381247 diff --git a/checkpoints/Qwen3.5-4B/30.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/30.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..85cdd31100aeef0be86f29d7175ecfb0dc5bde26 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/30.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e08a922da74c7f9ba2939da787c8396ac852a64990c682ba5d5c86ab8ee93f85 +size 21427308 diff --git a/checkpoints/Qwen3.5-4B/30.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/30.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9e125e90ba9abb491e2e4b66a16689a74af7026d --- /dev/null +++ b/checkpoints/Qwen3.5-4B/30.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38738032f905f4717e503c20addfa132596a8fb5a75806b298d1d8126d375226 +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/30.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/30.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6cfa94225223421e3549e7c1248a37d7e6795282 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/30.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8972ec679ba958416be294484356ffbc0f56918a84d56b6d3886a51fef80cbaa +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/30.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/30.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ee9be1809325d905c8ae46522f16575ea68f7e3d --- /dev/null +++ b/checkpoints/Qwen3.5-4B/30.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e23214b46e601682a7208c4b5c2a029c29847ada97cc9c322b7ed8b2677b4b +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/31.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/31.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c14f7734a7e26ab40a20fd1fc7f008494956b4ae --- /dev/null +++ b/checkpoints/Qwen3.5-4B/31.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b78274306b3aed06b0cb6248ffa50d1a6591c7d4a364c89047a360e620f41bd +size 48204711 diff --git a/checkpoints/Qwen3.5-4B/31.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/31.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ed3e2ee62c1bb11262476110d10c2e07b372a2c --- /dev/null +++ b/checkpoints/Qwen3.5-4B/31.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:668282a6c4e2f774ad3ac853d49685e5206cfe47f057799d453df08fc88ad623 +size 48005031 diff --git a/checkpoints/Qwen3.5-4B/31.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/31.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d0a807a4952ed3e1c074e9fea417893a1debddc --- /dev/null +++ b/checkpoints/Qwen3.5-4B/31.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b179390bc1c29a35ff8d41c04b63c8b1b52caee9160d8fa51d218801cfebef6 +size 48004993 diff --git a/checkpoints/Qwen3.5-4B/31.self_attn.k_proj.pt b/checkpoints/Qwen3.5-4B/31.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..69f3525b2d4b0542f032b1e45d1ff52c0de83293 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/31.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b4dac323dd69165a552a60752ab83afc819d7d5103dea8392aac91ce2fd9f35 +size 5406688 diff --git a/checkpoints/Qwen3.5-4B/31.self_attn.o_proj.pt b/checkpoints/Qwen3.5-4B/31.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae4b65ab448483568cbb22cca6b33c793f1e5ef4 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/31.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b8f6fa7117f45d4793751a0d13e0a8a37116a5b2c8acaee35344bf7f24107d +size 21427168 diff --git a/checkpoints/Qwen3.5-4B/31.self_attn.q_proj.pt b/checkpoints/Qwen3.5-4B/31.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b9ba6842d441b2536d64c9a06dd5d0187cf3004c --- /dev/null +++ b/checkpoints/Qwen3.5-4B/31.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ac374022606798164cf462f0c0409835e5abb36ea82d939b0fb1bf9b96d8957 +size 42680288 diff --git a/checkpoints/Qwen3.5-4B/31.self_attn.v_proj.pt b/checkpoints/Qwen3.5-4B/31.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f333f2449ff7513279bcc774ead52829f0c85b8f --- /dev/null +++ b/checkpoints/Qwen3.5-4B/31.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4da85ebe620f6bab252d776b6c37094c0ed1dcd62c5769eb789bb9f7adb1c131 +size 5406688 diff --git a/checkpoints/Qwen3.5-4B/4.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/4.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b960ca6df4af66b2da9b86fbd9350c60dbffad8 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/4.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:208b4ae8f2a373b20eeb18d25048db75f6c8472686e26bc0110b9beeacc44cfc +size 42680466 diff --git a/checkpoints/Qwen3.5-4B/4.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/4.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..d950626712605eee3d31ac56a0a06b7dda540df5 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/4.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15fc15915269ecc10b83ff79302c8cc8537b56d416b0dd1c0359653ec6ad6519 +size 21381228 diff --git a/checkpoints/Qwen3.5-4B/4.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/4.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6c016f696623afa60c9c439fb29c83c52fea649d --- /dev/null +++ b/checkpoints/Qwen3.5-4B/4.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:506051cb3b3adfb6d26d5ec0f2ea22a8d4012bd1c61ee148ec52c97f50de748b +size 21427289 diff --git a/checkpoints/Qwen3.5-4B/4.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/4.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..41145f64413740b7147d5492ce51acfc81feedc2 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/4.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4663df006f3998776c4e78402fd27c4fd8ec7dc4af0e253f9a28ab133b10486 +size 48204692 diff --git a/checkpoints/Qwen3.5-4B/4.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/4.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ef15f43af1030272647f675ad89bf0c7dd4963f --- /dev/null +++ b/checkpoints/Qwen3.5-4B/4.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b9d68c40783da65557e2f5f4f8187660103a964b29b4d2da087898e61379b73 +size 48005012 diff --git a/checkpoints/Qwen3.5-4B/4.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/4.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..18d93b4f5829352c4454464188a9bde35487c28a --- /dev/null +++ b/checkpoints/Qwen3.5-4B/4.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4430797c8221c644eb56f63ac18003fbdd74869fd2e799ec4f65dfe0f19537a +size 48004974 diff --git a/checkpoints/Qwen3.5-4B/5.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/5.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..4e3ecf437c661168878d538b655d4d946d3160e5 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/5.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:633e7fbd0be03883dc14155b633f46810e3dc9e7db26f4e3523a9c9a16473d18 +size 42680466 diff --git a/checkpoints/Qwen3.5-4B/5.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/5.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..8edffeec4be08918a2d72e8dbc3e76143b1a5fdf --- /dev/null +++ b/checkpoints/Qwen3.5-4B/5.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fdd1574b39c2ea8cf69d3b795a98ab5dcb57aa91f3f3b684c3ded1eebeb8f1b +size 21381228 diff --git a/checkpoints/Qwen3.5-4B/5.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/5.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..bdf5dc02ed06ee727b3fff49cb31d273e71c4827 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/5.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51898e1c12d27e61fd31de421405f085e60c68116db3970ba3a6745b3e3d03e4 +size 21427289 diff --git a/checkpoints/Qwen3.5-4B/5.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/5.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..826ba30ae77dcdbd02c5c085e94d0fc8ab029ea3 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/5.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7ca486244389b68f9a9548de9d17ce7b264ad13a4cc030211cb85696964dfc8 +size 48204692 diff --git a/checkpoints/Qwen3.5-4B/5.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/5.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e9ae5aea9593b60775af34f57333b079c6ab6646 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/5.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:750695975cdfe0ae39fafebeb046ddfd312ceae69cee588c88ca03044747f69b +size 48005012 diff --git a/checkpoints/Qwen3.5-4B/5.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/5.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..17457ee409b24a2d15e99895c2c71a5f213ac059 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/5.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93a5197bb3399c6c98878777a7abb0bfd858fd8f67b9916a9b97fbb13ea7927f +size 48004974 diff --git a/checkpoints/Qwen3.5-4B/6.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/6.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a17aa2a918c441ff6e3cd78d7bfef4bf5a2528a --- /dev/null +++ b/checkpoints/Qwen3.5-4B/6.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55a1c9ed26ac5be1c79cee0701c334982c1bebfac98459397d40c4ed9417637b +size 42680466 diff --git a/checkpoints/Qwen3.5-4B/6.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/6.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..389fbe69c3c254cb83acf3592e0c49002abe297e --- /dev/null +++ b/checkpoints/Qwen3.5-4B/6.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab08e80027c87a4b2beec1412f7f81a7f52839e2ad067560a9b9f379fe7f167b +size 21381228 diff --git a/checkpoints/Qwen3.5-4B/6.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/6.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba53c700e9e07a46674b025659e1065398c033a1 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/6.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9285ef051e7bad48e11a52c7a57b2ab6b6fab320591b2af74c73bd9833720a7 +size 21427289 diff --git a/checkpoints/Qwen3.5-4B/6.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/6.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a5bd8aea4f878e737843e6c70c68a4259d3dd766 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/6.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9847a14d821e445d6549d64fe91d430d9674486a03b9f72df4b1eddcbf84fd89 +size 48204692 diff --git a/checkpoints/Qwen3.5-4B/6.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/6.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a2ba5cd1c759293f06eb7501fb1446ca280ba1a --- /dev/null +++ b/checkpoints/Qwen3.5-4B/6.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c843451dbb3e3f75d6378f658013f9cedcbb7d84df49aeed24dcaa3e247b257 +size 48005012 diff --git a/checkpoints/Qwen3.5-4B/6.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/6.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0dbe174ebf81beb82ac173c6ca4d5d462476948f --- /dev/null +++ b/checkpoints/Qwen3.5-4B/6.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:930a931d06e169509723e3468e2489f107a400e53cc8a08fb7e90db4f5d830e9 +size 48004974 diff --git a/checkpoints/Qwen3.5-4B/7.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/7.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a95ccc526f24f4ef8be0cc7a72bb86a3d3b43b00 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/7.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:427119e2dae8bc164d92b3eb690a45604475f9669f73182d9bef4c5482794d57 +size 48204692 diff --git a/checkpoints/Qwen3.5-4B/7.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/7.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c8be65162e7f9b697dae587aeca8d447e2a1064 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/7.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ace362c313e6e5e750c17cd61d09448c7c791851f9c5cb700e589bdf7ebc19be +size 48005012 diff --git a/checkpoints/Qwen3.5-4B/7.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/7.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ddd49bb3f668632f72be2e958c433e1ebed65cb2 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/7.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8348cae6bb7f417a696ab25f0f1f9de83d77d669edd1a15796b53ea95dbd2556 +size 48004974 diff --git a/checkpoints/Qwen3.5-4B/7.self_attn.k_proj.pt b/checkpoints/Qwen3.5-4B/7.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..aebce46e0d207a5fd3850310f7d20d30449dc293 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/7.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c8834564e08b0e9b3876a02707b28db4308b83e85c44202b5507b4bb79b1f51 +size 5406669 diff --git a/checkpoints/Qwen3.5-4B/7.self_attn.o_proj.pt b/checkpoints/Qwen3.5-4B/7.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8eca86e8a6dc34ab4163792582722fe271b66470 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/7.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d8d0d2b20b1a816e70ca74268a3e2fd762277742604c607878ba7af70bf69a +size 21427149 diff --git a/checkpoints/Qwen3.5-4B/7.self_attn.q_proj.pt b/checkpoints/Qwen3.5-4B/7.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..50f6fb524a8e8bc286dced73641f2ea97c9ec0dc --- /dev/null +++ b/checkpoints/Qwen3.5-4B/7.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e366eacc47b7308287a6d97ccda5ad45d49ae6e4bddda936bdbc2bcd43c629 +size 42680269 diff --git a/checkpoints/Qwen3.5-4B/7.self_attn.v_proj.pt b/checkpoints/Qwen3.5-4B/7.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f65141cca1d97ecb5a8d60a3b241c7ea82fa1913 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/7.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a3ec05e052436ee0423cf66d52dbbe5d5137b684d762239e54abffa1f7aef0 +size 5406669 diff --git a/checkpoints/Qwen3.5-4B/8.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/8.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a8b5be1a73b49c29716f3cc7f4283fb1609ee04 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/8.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebb26a857ffe8c0b3ad63629cad05b0991c5b578a5aa9bdc8d97a3ea336f23c3 +size 42680466 diff --git a/checkpoints/Qwen3.5-4B/8.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/8.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..91e393b262e157e6ee4b41d4c714a2841d5f19da --- /dev/null +++ b/checkpoints/Qwen3.5-4B/8.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a065c7df1c938ddd1f340be451fc3fb63ab913378059d009a62079716a480f6e +size 21381228 diff --git a/checkpoints/Qwen3.5-4B/8.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/8.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..aae8028194a5814747482cd77a039cae97a92461 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/8.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a232cd2ecddd91518f111e8b34336287b153c97bc02bd08461b5c6fa44b03bd +size 21427289 diff --git a/checkpoints/Qwen3.5-4B/8.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/8.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..349b3ff1f3d2a68c322975b6380af5173f5a763f --- /dev/null +++ b/checkpoints/Qwen3.5-4B/8.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa83ae73a3a840f5824b304af57da2dcd7a1ecf7c3801dc210f4e13c2ba9287c +size 48204692 diff --git a/checkpoints/Qwen3.5-4B/8.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/8.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3b34fafb8d1719f939e4efdb1fe57d7655a33a6a --- /dev/null +++ b/checkpoints/Qwen3.5-4B/8.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42f898bb68d4746d0cd9f91b200d26da17a79769ee53a0f4e725f54242b74e56 +size 48005012 diff --git a/checkpoints/Qwen3.5-4B/8.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/8.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..991ec4033f4948288c8ce0ec4db82e56b0998d36 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/8.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24a6d17818e6aad3172e123eeccf8e181429641079635944544b0583b57e9f94 +size 48004974 diff --git a/checkpoints/Qwen3.5-4B/9.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-4B/9.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..693bce3582067a4b53ac24cb3bf7711dcad4fb08 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/9.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af4fd9d654c606935fd3c053c1967fd214257e4058caf6352d62de7e0ed1aa1 +size 42680466 diff --git a/checkpoints/Qwen3.5-4B/9.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-4B/9.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b9301c62f35f0412735b148e256d1c98513677a --- /dev/null +++ b/checkpoints/Qwen3.5-4B/9.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e345186817e3033ec294f6b8b4d1a28ec6e5f581b4319928985182aabb750278 +size 21381228 diff --git a/checkpoints/Qwen3.5-4B/9.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-4B/9.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a3bbee51489fef633bbff38f20a1a8a88c65b3d0 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/9.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad532fd4f89a24e1b961fbd3ed39b4c06455b2bcf796402bcf08288aec19eff7 +size 21427289 diff --git a/checkpoints/Qwen3.5-4B/9.mlp.down_proj.pt b/checkpoints/Qwen3.5-4B/9.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..706123fb6409cfb35953b7d36549dee0e17353b8 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/9.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:062d67928bde43be2b625ca73eb4f54700f99e7878ec640318bc7a20e68d9201 +size 48204692 diff --git a/checkpoints/Qwen3.5-4B/9.mlp.gate_proj.pt b/checkpoints/Qwen3.5-4B/9.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8456cba59217debdcd434b1ed27436a755e984c8 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/9.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db469725231a90dc01d7e6ae6f9441e3e61f91c718e2558d7666a3b32de589fa +size 48005012 diff --git a/checkpoints/Qwen3.5-4B/9.mlp.up_proj.pt b/checkpoints/Qwen3.5-4B/9.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..32e75bf1de39e7af15d85e12b8532ccbef8cf521 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/9.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43c586d9733e0c8ed8242c5d0f0e8f970e199e3a02fc3e0df21851a045f74a76 +size 48004974 diff --git a/checkpoints/Qwen3.5-4B/args.json b/checkpoints/Qwen3.5-4B/args.json new file mode 100644 index 0000000000000000000000000000000000000000..f91428a7b83e32ad0d8cbf699764bd71c21163f5 --- /dev/null +++ b/checkpoints/Qwen3.5-4B/args.json @@ -0,0 +1,49 @@ +{ + "model": "Qwen/Qwen3.5-4B", + "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-Qwen3.5-4B" +} \ No newline at end of file