diff --git a/checkpoints/Qwen3.5-2B-Base/0.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/0.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f865f93918acd30ec1accf318d5f125da993b15 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/0.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e169979526711f6bce9d07d0134e7b0395902f9bb05d5d6f8e8aeaef67d7f35f +size 25625746 diff --git a/checkpoints/Qwen3.5-2B-Base/0.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/0.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..005f547a104b04c3ddf5fbe30e19fa89373fb6e5 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/0.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef173d17e483b4701baf5ae4dcc7fe9be494e9177e59ad54a5849cb38b59ea94 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/0.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/0.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d0dca00a5785d9f3a5062d39f2a57156c4909418 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/0.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cda01e263374964565326ad915157c753dd089de4575a13f405fe1193b58843c +size 8586329 diff --git a/checkpoints/Qwen3.5-2B-Base/0.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/0.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..63a07966099fd98db297220d9bccf717b9702c7d --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/0.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:991509ce74bc2b577af2bfd18004c0f8ab125a169f4a0bc61b268fc4250f458a +size 25748372 diff --git a/checkpoints/Qwen3.5-2B-Base/0.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/0.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a872a9f03e9aba44a7a48222baa43dd0205aa33f --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/0.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76c3ed94d4b9e9702a6a8653d2b21469605ed10a317049a15de944e73f5ed711 +size 25625492 diff --git a/checkpoints/Qwen3.5-2B-Base/0.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/0.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..de2cb6c3e00a27883e25ad27ad5dd0e0da858127 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/0.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d854634a1644d291566fc0f2ef3cee2c19d9249f50d83b45b7bffdeb7b6cee7e +size 25625454 diff --git a/checkpoints/Qwen3.5-2B-Base/1.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/1.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ddd5373c6009d515c80285ddec4de07a9bf7d4a --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/1.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b672610ae0fd4d118638b91f2d0658a850c462c8a651322568029bb3733b824b +size 25625746 diff --git a/checkpoints/Qwen3.5-2B-Base/1.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/1.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..e01be67561d080c2df84ef0260025e31def1e316 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/1.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8147af6ddb8d82d986c84ce62999065a42b8a5a322be833ec199d584c3cca9f9 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/1.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/1.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dcf2a4aa01b33ead4400960bced808f6bbf722ba --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/1.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8908e351658c5209f7d4d388680ffb7f3b08143691c9757a2e660d726974e342 +size 8586329 diff --git a/checkpoints/Qwen3.5-2B-Base/1.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/1.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b183fdca9149a18924fe8a0c270018920a88c2b --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/1.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbda559ec4ebb7679fa581ed8fbd72dcbe05587d8bb0cc7863a3c99787e27ad5 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B-Base/1.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/1.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..075bfa5a5b8e3574d17faee5c3cdb4b8328d6ce2 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/1.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa5da2416333663c2536ad0ed0d2dd26b601bc1128aaa262d5e06032a901476a +size 25625492 diff --git a/checkpoints/Qwen3.5-2B-Base/1.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/1.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..eee3756cb7e90f63598bec3306b598a562c53d5a --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/1.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a6315c6f566d1be037dc79960837886f3a53c92aec25b87e31d35ced838a567 +size 25625454 diff --git a/checkpoints/Qwen3.5-2B-Base/10.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/10.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..d4f1b1db955601a813d62d9abf6dcaed3b4edc3b --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/10.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ef6d0321deb4927e0208e45224c26435142b22d174b144450f83e9f93aa1912 +size 25625765 diff --git a/checkpoints/Qwen3.5-2B-Base/10.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/10.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ad660aaf2bbb3be6dc514f00dbb2c724592dd28 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/10.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72cad99f75e96bab7437ea875a993de4a84bd3e73c65625ef0a48ef5c2b9dece +size 8586367 diff --git a/checkpoints/Qwen3.5-2B-Base/10.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/10.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8de5bce27e246a46f70bf74c13946ea4c9db59f6 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/10.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:022a84f0295ca89f8666e9082ecac54829105d47613c1d259ad0a2b758df91d9 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/10.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/10.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca10510de763f5ebd0dd1b8e2b3756828cd6d4f5 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/10.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:875b9a48a1011066dff31b058709cfeb87967bc1a027a7c3c674bb24ffc6bae1 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B-Base/10.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/10.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec74804d65456eb7594536f7d9cfb4790e6e1a75 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/10.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06f133c1154b937d4e9844d5720ae6a4d736159a17996443835eb31f8013d8f +size 25625511 diff --git a/checkpoints/Qwen3.5-2B-Base/10.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/10.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d89265a44359dfd52f62247bdcf3b5ab3c07f43 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/10.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e2b1165a7537a95f05a8ba89d5f5f677ba8586173d6e345b3b78a408e9f61b7 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B-Base/11.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/11.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ebcc5354d63ad8f84615f50df9cfad6e0c34c9ce --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/11.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a63cfca80cb90bd159932e0bcac65f8cdd62fdde9bc78bd47dee0ea4c3131337 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B-Base/11.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/11.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2691650992d6a82ca52de8e71952902a5cd77109 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/11.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72444d86c986d68433e4aeba9eaf4a07e04e8834c49fa020a948247114728002 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B-Base/11.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/11.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..cffa5cac65da74851f1b53cce41867a01b490cb5 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/11.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed3788b6bc0101125ec0db67d5cc5df2b4f5559191d34571714ee88461ad49e6 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B-Base/11.self_attn.k_proj.pt b/checkpoints/Qwen3.5-2B-Base/11.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e007deb989fdeab0878132703a6a4a96e80565af --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/11.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7688f5b4f9824ba3614d93969eeb80aa3227b7de3d4221b401f484d53bdd8f64 +size 2196448 diff --git a/checkpoints/Qwen3.5-2B-Base/11.self_attn.o_proj.pt b/checkpoints/Qwen3.5-2B-Base/11.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f362d2d3fb462445e74592996c3ab451bb5971bd --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/11.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0e0a9a001a74902c7fa6debbabf8aebdef26ba7b48ef7fff5330160a60d57d9 +size 8586208 diff --git a/checkpoints/Qwen3.5-2B-Base/11.self_attn.q_proj.pt b/checkpoints/Qwen3.5-2B-Base/11.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..82c10e9e9f5b5a63d8baf2f15eb13195c749a162 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/11.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fe71a27a661de7fa5b8186654aff460680fbd10dedb88e032dee99b951ec1d0 +size 17105888 diff --git a/checkpoints/Qwen3.5-2B-Base/11.self_attn.v_proj.pt b/checkpoints/Qwen3.5-2B-Base/11.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1dc9822dffeb006c80d6c4aa29b7d714d295e732 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/11.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e9df32214ed001836611546a61e2f6d79fc982d4e7c7464c60571455c3bb1db +size 2196448 diff --git a/checkpoints/Qwen3.5-2B-Base/12.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/12.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..3fa0b3f800de44aa22154fff62d37adc7f3b30eb --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/12.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dad98ef98fca7a0b40072724b8e133a2966424cb04cc352a1e7fb17a4667ab37 +size 25625765 diff --git a/checkpoints/Qwen3.5-2B-Base/12.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/12.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..19dbf658de4f4f9429b9ae14e1f4ad64099d1873 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/12.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebe20d3082461cf0437470194c62e535c2984055560b76f34719be96e41cb492 +size 8586367 diff --git a/checkpoints/Qwen3.5-2B-Base/12.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/12.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2643777db9fd7ca0b280308f9d75a01659524807 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/12.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c0210af327a6903b8a03d07111b32a0bedea2c0b25e8d47aaf8dfe80778e98c +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/12.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/12.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..18b4f7539b7661053ac72df446e43c8d0f222a8a --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/12.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ac80165e2ca966e56cb52f36114d2d574806dfc6610a789e0cf76175ce5bb00 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B-Base/12.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/12.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7beea9f15819576055f335d67b700da7256062d6 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/12.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:737065a3d562aec44338fef116317adb083b2dda4d01e33e385afc74b1d28405 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B-Base/12.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/12.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..491c747345ba2cdd723c1b6d3e5c818d24fc5300 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/12.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eb7d9a3fe778d3c6aa712d451ff90928dced06dbbec6fa1b2be3d223603b771 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B-Base/13.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/13.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..7fea0f6a2a83294bc1cfbd0d2fac18997dbea3ba --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/13.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc24baee6e511bc23861a3641e918f294368f53b857ff59d814560e25114655a +size 25625765 diff --git a/checkpoints/Qwen3.5-2B-Base/13.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/13.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d6fbac2f4538188e3501369fb2fd53c8dc4a655 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/13.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14d8d6e14e87932b98edb0c92ff3559acac55ace827f24887b61c0a3804159e0 +size 8586367 diff --git a/checkpoints/Qwen3.5-2B-Base/13.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/13.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a3e7eb0d3d6b04276553cee3032ec5e5e7c83990 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/13.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25ffc2c2a6177e0d75198934b364d497763b1e951bd338f5676ad5eb0312f3c5 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/13.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/13.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dc24740b42941874c31f4829c4603303f4d4b16d --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/13.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80519c523257845fcacf0dfff5e18ae543cfc4ec94e1b062f3adc4e5ea5e49ad +size 25748391 diff --git a/checkpoints/Qwen3.5-2B-Base/13.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/13.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7bdc1c6f1ba5037752ffcfdbd2c151a2e7b813b8 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/13.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7726b51fba0a76c919882280382b2fcc125404bf00453c3944adff78b8bdf15d +size 25625511 diff --git a/checkpoints/Qwen3.5-2B-Base/13.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/13.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e6478570cd82d486a8fdca79c05dd7c4a487cd79 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/13.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e325ab376286190d529776c10f699a757d496a7626e20548ff4a2c5dbfe6dd1 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B-Base/14.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/14.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2b7fcee24a76608c9fdf065746f04adbe9fa9c4 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/14.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3548222ae803b0aca898e3b075fdacbde9fb2f40ab9593a886eeb55b991f0af +size 25625765 diff --git a/checkpoints/Qwen3.5-2B-Base/14.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/14.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..43fa06eed208101a2299ed55ec2bc6040fca9202 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/14.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23cf312f1a5720cc180146d16a262179e39297b765da98d4887e4abb6660f928 +size 8586367 diff --git a/checkpoints/Qwen3.5-2B-Base/14.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/14.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9994de50f4936856c089e03dc905a0ebd9472066 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/14.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f25999568330cee86d4ef5ec39c6e091388cb4d4fe47da4f4f9570b1386d9e4 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/14.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/14.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..140c4124dbe12d34f90611b18345258b4b47d06e --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/14.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2f711942372bde1fbab590750d8f742e3b1ce4f78339c80759ebf6d1e1615f4 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B-Base/14.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/14.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3acf205ceada1ca6ea42eaf51d5fd3d2dbbe2156 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/14.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07f11c43c4d91e10eef6a275a1aa6c70969d2159eb19bcc2f6f28f5577cba1ce +size 25625511 diff --git a/checkpoints/Qwen3.5-2B-Base/14.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/14.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2beac0cc3cdede0c523cb323e684c76c6a8b22d --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/14.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bf47a239222acc3ea469ea20614e8343c4346a2d1510bdbd8f9faaae1e6551b +size 25625473 diff --git a/checkpoints/Qwen3.5-2B-Base/15.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/15.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dcd6eeae8383352b15e66f6337c71bc5fd927692 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/15.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9803b8b0ec89a575d8092203b61a1fe8862a4c2a22ca08a758b60f2d5f5feeb +size 25748391 diff --git a/checkpoints/Qwen3.5-2B-Base/15.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/15.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8157a57bc4f166c42e4e0cad84073d6c553b7377 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/15.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a7761590789447ced6405e7f4ea3b2d0a6267ad09f420ac42c76c322881765c +size 25625511 diff --git a/checkpoints/Qwen3.5-2B-Base/15.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/15.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..aa247bd269d931cb87b95d7facd5293252629360 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/15.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c45abf995f817a98822f3f13b5d9af2d6c335c1f91622269f94b3f2b283861a +size 25625473 diff --git a/checkpoints/Qwen3.5-2B-Base/15.self_attn.k_proj.pt b/checkpoints/Qwen3.5-2B-Base/15.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..16bd11a99755b1e8b428f3c7c865557bb1a0cab6 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/15.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:987327a841e624536fe44fe1848d501e7de3713f715a5c58f927c87f17d6a26f +size 2196448 diff --git a/checkpoints/Qwen3.5-2B-Base/15.self_attn.o_proj.pt b/checkpoints/Qwen3.5-2B-Base/15.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..593320b489f70d436e67337c5c48c49f0627c4f7 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/15.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34d65eb12c5e262e99e9ed8572cc1699ce90213a1a5318499595dc5595296197 +size 8586208 diff --git a/checkpoints/Qwen3.5-2B-Base/15.self_attn.q_proj.pt b/checkpoints/Qwen3.5-2B-Base/15.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6125931a207b6a1aec8f56955aa5734bb7ef437 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/15.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bb0f9d5ebb3225e54f24493409de65a00eb2fcf690035a96ba2249dbed0acca +size 17105888 diff --git a/checkpoints/Qwen3.5-2B-Base/15.self_attn.v_proj.pt b/checkpoints/Qwen3.5-2B-Base/15.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf50133e153b7235f26a7fdfe250ad7e7c5c2838 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/15.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e2ab19a4ff9fe1ac43f36b307056afdbeed1de9581040f2a30ed89483d10676 +size 2196448 diff --git a/checkpoints/Qwen3.5-2B-Base/16.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/16.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..6444d1f0e892114a80ca37633e32fadb7d5da0a6 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/16.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f361df5dbeecb9203a130a3aa9411bd3700f9623ddf48a38155dfca097fd854 +size 25625765 diff --git a/checkpoints/Qwen3.5-2B-Base/16.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/16.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..fbdff04775579dd518d762a6299f73cf3988a52a --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/16.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a30a206ff7d72cf80723d5218bd8194dd5b142c7681dfcc6a4b22b16c5ff78d6 +size 8586367 diff --git a/checkpoints/Qwen3.5-2B-Base/16.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/16.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d7e857aaf211b60d8ec84d3f250ba23c087fe1e7 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/16.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:975d5527a07244550bc71d7e6052dd98e0fa14a46e489ee65618c21ef9df3757 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/16.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/16.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ac19aacd7eea1302c740369ccbef68b67a2afe3 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/16.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e14578fe0f51309b43a69b6d35cd48f00617955376488d68044e3bb5ab4c65c +size 25748391 diff --git a/checkpoints/Qwen3.5-2B-Base/16.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/16.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f2c93a17da3c39476aa03a5d566236cc5fb40d91 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/16.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef3be1e27cf9fc9487215870562404c1d93e8b1dc91432ddc0c223ba802c4eb9 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B-Base/16.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/16.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7601d7311961e1dea0a2d949004f461d5ce686ad --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/16.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:275ba188b105337483af9ea1c37bb143a060f52b70412dc826345abcec86c91e +size 25625473 diff --git a/checkpoints/Qwen3.5-2B-Base/17.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/17.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..6cc5e476350fa68dacf9f500bd186a0b1afad289 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/17.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc051057cb6d14b5beb464396bf4daee839254e60ede22b645e050ab6a1e62a +size 25625765 diff --git a/checkpoints/Qwen3.5-2B-Base/17.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/17.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..1642ed5bf0ded85d3eeb65345a6327f207dcc79f --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/17.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34bad8a36dba567ac9e8f4d9883c7f2ffb4208247b9fc58cc827ac03d858d7a9 +size 8586367 diff --git a/checkpoints/Qwen3.5-2B-Base/17.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/17.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ef1e0fd231e0a47081b2134c31c22955146f4f7 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/17.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d9d52b6b3036fd98b1d66e05508fe220539ea6109b3ea7a323a79eaa1ff786f +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/17.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/17.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d5e8a5b76ffe30dd5efd2506b40e840e700fe82 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/17.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c4a23dbd122f71352aba50964d405ce283a0ef4bb16ab51e857e531aefc6cc5 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B-Base/17.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/17.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e225d9987daddb67cd2c97440eba91d2db305c2 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/17.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbda10151df3948e0d85c8419874e5a622b4bb1f0d9f880f439cefc79696d21b +size 25625511 diff --git a/checkpoints/Qwen3.5-2B-Base/17.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/17.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c36d95854fb999d390312a56d58c364f7250cce1 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/17.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5fe02415f206417ad6ac21954c246c94b62f0411380a482c8882e4cf71d3689 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B-Base/18.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/18.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..ff14f8940c9c4bc94cdb09ed2672863ea8b1ccda --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/18.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb1688825629a2842e02e231538585236e2bcf756ca461269862b8934b3d21bd +size 25625765 diff --git a/checkpoints/Qwen3.5-2B-Base/18.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/18.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a8837508af5745976229d56471ecda4984792f5 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/18.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b952ba38171b1fd58f037193f0e174dc952968265256ab4e7b1874dcc511a1c +size 8586367 diff --git a/checkpoints/Qwen3.5-2B-Base/18.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/18.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3374cbfa9241b605757938358965f87ed98f50ae --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/18.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5302401e9046665223f69716fa457fe495229919350191a3d7e98a5d929f9a84 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/18.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/18.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4b638339d87f014c9f9ee63dd25a6768d5b67dde --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/18.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49ecefbaaf3a9d3c5f1ce6ab2361475d60aaabb69480b6fcf2ebd9c91c5d7ff2 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B-Base/18.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/18.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..056b404729f554c59d504df00528e74c8e07d3fc --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/18.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5f00422af60d82b7ef9fef04be77721a26fddc9d0bf76ffb0018b07cdb53a4d +size 25625511 diff --git a/checkpoints/Qwen3.5-2B-Base/18.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/18.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5d8fba6d8a983a8386ddb7f8dd6f681365fab37f --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/18.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24c7bf36acd02711e4edf5991fcdca6e5f33fe9250bef59966e547d228a0601c +size 25625473 diff --git a/checkpoints/Qwen3.5-2B-Base/19.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/19.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1be1def98f799214292598599110c468e7f1cd19 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/19.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab40341165edd51381310f1e95e3687c420d994bcdb66c986a1cfe7b3e138104 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B-Base/19.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/19.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dedc33925ac942c9797d3890112082c6511dc726 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/19.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da6da8b8053e2acb18abb403f71a18dde4bf07f1dd4488f5cdac4998817dc60c +size 25625511 diff --git a/checkpoints/Qwen3.5-2B-Base/19.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/19.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b40512e53c0099bf1b95f783c53a0af75edd2793 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/19.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:029ab17a3daf48a0adee014e511c1d292988839c191b7c5724276aacd962a005 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B-Base/19.self_attn.k_proj.pt b/checkpoints/Qwen3.5-2B-Base/19.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f6788a7c95bcd83d565f4c100123d5ddb2b687a --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/19.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7d90e3b3163daa7e4ecad8c03d8de3ae9226bdd0f95d10f16a099dee645c627 +size 2196448 diff --git a/checkpoints/Qwen3.5-2B-Base/19.self_attn.o_proj.pt b/checkpoints/Qwen3.5-2B-Base/19.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..132fe3c94b9f1d6d0f02cc395dee6a249102221f --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/19.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e8018dba9e1036f33b1ca59ec1425293ff39540688e94b739d83bc6519f81ce +size 8586208 diff --git a/checkpoints/Qwen3.5-2B-Base/19.self_attn.q_proj.pt b/checkpoints/Qwen3.5-2B-Base/19.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2d51cecd1622e6fde4ae7ba27b3c6137b468438e --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/19.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:682946d5ba27f1326953a20d6daefa6361ec2ebd6261a92c0104d8a47c1fcc76 +size 17105888 diff --git a/checkpoints/Qwen3.5-2B-Base/19.self_attn.v_proj.pt b/checkpoints/Qwen3.5-2B-Base/19.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..60853a1c5b591b5242b9fe8caff0761816e2d2e1 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/19.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:692cd9f93d08698c5b397a21d60ead445e08ea901a76071f83cb9b86caecde27 +size 2196448 diff --git a/checkpoints/Qwen3.5-2B-Base/2.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/2.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..82da69c2c74f99ef37a8abb1d4e84b80cad4690e --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/2.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0514dbad5b5351a9614b7a4b7dadee9bca76d3356ce2accde5b26ab775c4d8de +size 25625746 diff --git a/checkpoints/Qwen3.5-2B-Base/2.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/2.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..f984aa9e0cc82dc7eae61b1f04b2f0e573ba90ed --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/2.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9efbfcaee926d4a9d914fcf47cc4c199b95147b03d72b2823d688f1123e4267b +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/2.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/2.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0d773d719ec4b3a90134c36b06a09bcf38199d46 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/2.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d55e8cfc859b810c7e04fe927ef69bcb7179af0909f45b3bd96517edf8f87003 +size 8586329 diff --git a/checkpoints/Qwen3.5-2B-Base/2.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/2.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a4ca9a91a5182657aa14eb3c9567480d3d9d36c --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/2.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ced13ada0e00a205b124746b5d8fee3e586d06be9f758dffed8ab4961eab7b4 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B-Base/2.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/2.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..36a9ac2ad662cb7ff607fdf12ca148d7d22ee7ae --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/2.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3c6bdb9da40b4ab45be62dc7fc5592ff629266b87f09e7200f4b0fff5b4911d +size 25625492 diff --git a/checkpoints/Qwen3.5-2B-Base/2.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/2.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5cc075bae95098beb1419ac4d6687565e1ef6fcf --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/2.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df5514c07473ea9f2b5838c9247a1ae2dcb671edd7be2927b715f9f6dea660e3 +size 25625454 diff --git a/checkpoints/Qwen3.5-2B-Base/20.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/20.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..739adc14f582bdb15a1746014ffcb38f759d55ed --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/20.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5174cd5bdd392a3d729a1364d0a91db4a7ee896c18ed8584e5fd2a6448e6ecfe +size 25625765 diff --git a/checkpoints/Qwen3.5-2B-Base/20.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/20.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..371ac3b29fd0b2d23a2556b89a581eb830d9d31d --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/20.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab174525880749f30c543cf5ea80ad7eb27678e6352a74ebf99c0075b23848b8 +size 8586367 diff --git a/checkpoints/Qwen3.5-2B-Base/20.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/20.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ec7e227eb28f280330d239392c53ea24862bd30 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/20.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66c088780d6c18e6b210ea9881e17ef07c5990abf1412a13e26208b29b3b4df9 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/20.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/20.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6352d10c2f97f8bc8e5281caae5509a5977797e4 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/20.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50a2b387bff020c21381de2bc30f09deda544ef6fd1425d264775ab7b6478454 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B-Base/20.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/20.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a08f5b00535fe7bc02f7007602c66cd84d76d708 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/20.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd4317c690f6850d3a25c461a78bae2a0229f75f0e9085716f5455526b286e6 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B-Base/20.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/20.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..020d037b9a7d8537102e6842def8d486ca1caedf --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/20.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c7acd09bcb34307ba8df4ed7346246e874ebea7db96f26803a58ff985573f27 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B-Base/21.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/21.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e3ed4490c04420af9ca2769c4b8ac12f787d346 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/21.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ca5029b6d132e120ce7bc4c1f6b300f94be2bee9873d09f67e05fca12a79c68 +size 25625765 diff --git a/checkpoints/Qwen3.5-2B-Base/21.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/21.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..11f6d3b63b460fe03c3b136b552fb1287869ac81 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/21.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c824ebeead103c8187f4b47e53e3283d37ad97593841270a44d5442bf2cf042f +size 8586367 diff --git a/checkpoints/Qwen3.5-2B-Base/21.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/21.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1c9125028c438db07cd0fcbfbbca16d0b92d157a --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/21.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6cb49eed60e9158faf422aeaeeaf53dc69a88facbbeb3ab0152a38d93a2ccf8 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/21.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/21.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c83967478c848184a25b07948fc5e12283f27d0 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/21.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a146de04cc2e08178be914b60892eaa88b28855a2276bd8c88fa04f34a574e +size 25748391 diff --git a/checkpoints/Qwen3.5-2B-Base/21.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/21.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6cae2d08e3b0b5ef29d0dd1ce510bcd662a92aba --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/21.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24302daf2fa5c5adae3527d5795af1e4b8af51a29e4c96c055426367ebb58f04 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B-Base/21.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/21.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..41ce58643a2f013bb71ea4d5d7b7b4b419299bd4 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/21.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbae74d84fa2e8b46f6fe2533360df48c49da5cc9a9fda9f68d4d9720f0ed603 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B-Base/22.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/22.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..4cd9382826ec4f684a7307d7e872730ab3addf52 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/22.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d9061cec7f0c967d6628c606f816b201e7cf64088ee2e97b5a455dac6e9a58f +size 25625765 diff --git a/checkpoints/Qwen3.5-2B-Base/22.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/22.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..3b0d1cfb40a0edab9e2a10006617b5c3a121af1a --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/22.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b4c07c335fa953f106a1665d44e3b3109ed23d9dd0c1b5fadd34d4b32e5f38d +size 8586367 diff --git a/checkpoints/Qwen3.5-2B-Base/22.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/22.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..aeb741d619682fbc110f0b0fe2c03f918eca0d95 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/22.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baabc02253e74e6f356722c2332e879083190324a668c6a3668b55dc42f9022c +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/22.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/22.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..940fa180060e08f3e7ef315371ba4468cc371104 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/22.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6261143a46ed00539c2614ba4516012296daa61997ef6e6fbb12a80b04462408 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B-Base/22.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/22.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b4c43912e955a0bba6ddc62925888af9d9bd072 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/22.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c734e447be91a8fc360f24a7e93d462a65d99dac0c5e5f0b81c220abc7b3c5 +size 25625511 diff --git a/checkpoints/Qwen3.5-2B-Base/22.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/22.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dce5c752c713f5ef5215b309e800af22585f3c1d --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/22.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:319f36cf11d502bd980e20a0b8925e6907d7187aa67c70213278eff938d1d148 +size 25625473 diff --git a/checkpoints/Qwen3.5-2B-Base/23.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/23.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef1e355f738516552d7c88b148c19f9888c2e837 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/23.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c15a3d3e13ca30bd3e168275dac14379bccb2c0c1c60df5d66f615b0ea5db49 +size 25748391 diff --git a/checkpoints/Qwen3.5-2B-Base/23.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/23.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..13418afe0993e5ae9a8cf324d20ddf9f045f5705 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/23.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba82f0e16107274f43b42f5ed1310731fcc70bc9a4ea52fa5b0893b7f3809f2e +size 25625511 diff --git a/checkpoints/Qwen3.5-2B-Base/23.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/23.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d1aebc7ed976d24ed670e43a72f196a7c3fb4213 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/23.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a280d4c5933dc25157e04d945c9f0d96cab84d065b86f74c9a4bd5c55dcfc3e +size 25625473 diff --git a/checkpoints/Qwen3.5-2B-Base/23.self_attn.k_proj.pt b/checkpoints/Qwen3.5-2B-Base/23.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1782bd81309cffe2c454df5d1ffe23b7556e59c8 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/23.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59018cd9bf696938a18b5075314e90caa46c5fdae41fed809c7fc561b9bee65c +size 2196448 diff --git a/checkpoints/Qwen3.5-2B-Base/23.self_attn.o_proj.pt b/checkpoints/Qwen3.5-2B-Base/23.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6d95e4ed4e79aaff1fe665976bdf7a882be621d9 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/23.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0712bf59d64fe4fe3fccb90bf8fb28fc259d873f151d47f10430a97e9eb4e274 +size 8586208 diff --git a/checkpoints/Qwen3.5-2B-Base/23.self_attn.q_proj.pt b/checkpoints/Qwen3.5-2B-Base/23.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a6733a0c619f0a6538079f396094ba94378e7cb --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/23.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeea45750c07dcb186c9bcf0cdfe87ae93f38924af2add15e452bece4aa7c224 +size 17105888 diff --git a/checkpoints/Qwen3.5-2B-Base/23.self_attn.v_proj.pt b/checkpoints/Qwen3.5-2B-Base/23.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7d3c32b091d9964da367b2df143ff99500ac763 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/23.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e9a7098ed03f89f0f0cd1e3e335d8e29cde323bc3fd854dd8a57394337f491c +size 2196448 diff --git a/checkpoints/Qwen3.5-2B-Base/3.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/3.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..df24fdd9a07e6ac3679eabb7a4f800c0ac5c30f3 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/3.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4947adcec662819ae366e6b5593f082ec08d78b0a8fcc5060d68018886ed847e +size 25748372 diff --git a/checkpoints/Qwen3.5-2B-Base/3.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/3.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a175f97ebf1c85782357b1b481c2aeeca0b7529 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/3.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e65383f0900dabced978de44f9afc5e3b9dcd539d9398a095bcb3a7654ee16d +size 25625492 diff --git a/checkpoints/Qwen3.5-2B-Base/3.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/3.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2b81d95e0b55270d229b19b786c51cd0e841a2e --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/3.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88971a3605c2dd5dabbf10e691825c0f80f1825008de3d1fe73b37751e333827 +size 25625454 diff --git a/checkpoints/Qwen3.5-2B-Base/3.self_attn.k_proj.pt b/checkpoints/Qwen3.5-2B-Base/3.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..838300bdcf4ec17410d2f39c3bfcf2ae44ad7ca8 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/3.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1747f87eb8807ac7ed4ff82fc4c1bb36ff2fa7fccc76b002e5c7f34cb6347923 +size 2196429 diff --git a/checkpoints/Qwen3.5-2B-Base/3.self_attn.o_proj.pt b/checkpoints/Qwen3.5-2B-Base/3.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..19bb9f80ad7ceb87ef26314d87b4792d4f0418ec --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/3.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37632a092699337454297e8f215ef5198419c7f9aaf6cfcb7e6c6791e5ae30c7 +size 8586189 diff --git a/checkpoints/Qwen3.5-2B-Base/3.self_attn.q_proj.pt b/checkpoints/Qwen3.5-2B-Base/3.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d150ec965db6090429fcb9e932c4dcfdced4eb8 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/3.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f7db694e303b9c422f513e67513ae861f129a8b9995fe158db3bcbd3c8f0ab5 +size 17105869 diff --git a/checkpoints/Qwen3.5-2B-Base/3.self_attn.v_proj.pt b/checkpoints/Qwen3.5-2B-Base/3.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..896e9bf5e5c44c9314816d8a6a6c75d932a32340 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/3.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b59779f88c543fedc0390637280ccdeb2583388279a82c3d82ea05a62f04fc15 +size 2196429 diff --git a/checkpoints/Qwen3.5-2B-Base/4.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/4.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..ddffb3ab008e036ac0c0a3fb0bb5573cf6ad451f --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/4.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ecd695413691da2907f2a8138b661f10e37c696ce9180df24aec65464a695fa +size 25625746 diff --git a/checkpoints/Qwen3.5-2B-Base/4.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/4.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..1504ef5adb292e3722c85a453855b5a20e8c76b3 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/4.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09a85cdef2f34a8ac06abfd8264e4fba3efa1e1ffc147c41ac755dfdf90c6f52 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/4.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/4.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c2921b7771aea6b4cb35147e69e1fda007533d6 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/4.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77b3d8ba4293edb655cc4e03351780fac3cdabefe56b2ed15e066129a848c74a +size 8586329 diff --git a/checkpoints/Qwen3.5-2B-Base/4.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/4.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8941408a9240ed71775d5e4b48ffff1fb4c35873 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/4.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e16a55fb90a1f772d82e5960854365d8ea628d35ebba12b33c4a53177145294 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B-Base/4.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/4.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..43efb3c4d6477f8cc17549d04ade8858e17213a9 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/4.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c37e792410faff84fccf51897f4b70628d20b2b389703e723f9cee3dd1535018 +size 25625492 diff --git a/checkpoints/Qwen3.5-2B-Base/4.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/4.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..55c5004f4b44693ed5b2f9b025a8618945bbc079 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/4.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39afb845648c830ba81b9ad2af770bb76a10217a3b864e8b18576b2457a103bc +size 25625454 diff --git a/checkpoints/Qwen3.5-2B-Base/5.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/5.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..c0214eea5fcd1d2527f268943d2a63f22f1de41b --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/5.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67a1ef9e565d3d4d74c89b9ee4a4d000eac06715106b8ddf8dab518938d10f4c +size 25625746 diff --git a/checkpoints/Qwen3.5-2B-Base/5.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/5.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..826c22ab9c04b79a12cac4726739cb8ce8f8be46 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/5.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e811627dc8568b9f0a8b0c272f61d42b5b28755204cf7759a7150f5c9ef4b7ff +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/5.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/5.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f5c1bdc23882ae003be98adb6d62c5ff2d93844 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/5.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f80f3cc9096d35e1050fa9e20b36a14d32c33b0dbd89fa6f1f3a57554b1ddb70 +size 8586329 diff --git a/checkpoints/Qwen3.5-2B-Base/5.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/5.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d9e0a7732804a4b8e056a7de4160fdd7e2db171e --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/5.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:807bf9daf21ce9368218ec644dd7b568118cbedfdf1102d7d217a4e3a58a2aaf +size 25748372 diff --git a/checkpoints/Qwen3.5-2B-Base/5.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/5.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..512a4282ff2168e21f9b2467623e415a7ebeaea6 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/5.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59b21cd7720aa352df565def1b580a2a803c5931fd187ad5f0f9d914677a3c52 +size 25625492 diff --git a/checkpoints/Qwen3.5-2B-Base/5.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/5.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..61aaf3be88c6ae43ccd7b4cd54e93fe1a407aa40 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/5.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:085e314e9888b51bd08517b6f6062e3d6f16531de732422ab3e85da7d7abf141 +size 25625454 diff --git a/checkpoints/Qwen3.5-2B-Base/6.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/6.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..1857273d3e882cff0ec8a08e12588d3f43ef2018 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/6.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3590cdf4bfb5bd048b8ac23c41cd60b1ac55ab874799c7eb117c880d37cebea +size 25625746 diff --git a/checkpoints/Qwen3.5-2B-Base/6.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/6.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..c3144167972ae842e290129f2529070b364bd075 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/6.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67a2efcb91a6b52191eb5abed640cf7db5315ccfc3b957b2a653f177584f1d1e +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/6.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/6.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0d8d5aa135e43377e260d513745781186bf9eb43 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/6.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5a2e2e70a2b0ef2061ce258866c4db8d49341d9ec7a65e2a4b3773f25b9693a +size 8586329 diff --git a/checkpoints/Qwen3.5-2B-Base/6.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/6.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fe819e69387d39c79c454260d74ab244bc8ae64a --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/6.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5931a532687d6c6ae6f7ba360de565c03cea13c082d484e6252d8fc3815d6b9 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B-Base/6.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/6.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7406a9538c803010e11c97e42d163172423acc5a --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/6.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b7b9e70a72963275f84ef1bdf966d48586d0434faf0eeec677d2543ea5be4d5 +size 25625492 diff --git a/checkpoints/Qwen3.5-2B-Base/6.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/6.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..73270c05a3a8c4832de14f4d677aa914812b1642 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/6.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20b8c3a285ca0122bc23c68fad4947f68ab8b5c02b09dc32bb220cf398c2f42d +size 25625454 diff --git a/checkpoints/Qwen3.5-2B-Base/7.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/7.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c7e24b86569f90b88ca725ee3287e48612e21c53 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/7.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e04fde2c2cd200fcbae1d3b153d4e67617a4a6c574767dba1d36e88a7f3cafe5 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B-Base/7.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/7.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..83d84b211300702ad3dd27be05d1a8a5991f0664 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/7.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef5e6834ffe33fdb19020f9ee18523f6e7e38719f874468e02a3cc2d8858bca6 +size 25625492 diff --git a/checkpoints/Qwen3.5-2B-Base/7.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/7.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c55917679489e7284270b3e7efbd719879abb96f --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/7.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45b7994af8c501c8497eaf4385e0abedae8409575133591b4c6e8a4c5e22f056 +size 25625454 diff --git a/checkpoints/Qwen3.5-2B-Base/7.self_attn.k_proj.pt b/checkpoints/Qwen3.5-2B-Base/7.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1604d45acbce7f4da24454c5c5bacd4888a9b445 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/7.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9908d03bade3e935ec030a0aed5c950a149192ab07b3e7b09508e58c758c2811 +size 2196429 diff --git a/checkpoints/Qwen3.5-2B-Base/7.self_attn.o_proj.pt b/checkpoints/Qwen3.5-2B-Base/7.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f5de69d1ff32825eb29c7abffc140e7dadba1018 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/7.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa4b9a6f32029a60c16653cc2f2b1f199f7c5fbf51f45cbd94a9318205827e66 +size 8586189 diff --git a/checkpoints/Qwen3.5-2B-Base/7.self_attn.q_proj.pt b/checkpoints/Qwen3.5-2B-Base/7.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3227222c10fac33a11887f2da63a9b3f7c469e47 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/7.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c19ab120c8ad491bdb5b4d5f3d54db1edc12eaf9805f7a44ef29154c09e72b67 +size 17105869 diff --git a/checkpoints/Qwen3.5-2B-Base/7.self_attn.v_proj.pt b/checkpoints/Qwen3.5-2B-Base/7.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..717705a74209edf70ce542ef18d9b25d61225225 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/7.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03904f6f4be62a9dfebc32485d7664b5ffcd38a34784f527fbe8504d69f3f459 +size 2196429 diff --git a/checkpoints/Qwen3.5-2B-Base/8.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/8.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..72104046b10cfa4edb75c46293abd304ee0dc939 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/8.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b15e5ca74e96a8f8e1bd2a32bd2c98c9e8210dee7ee51528c2ec0bf4a7b7d228 +size 25625746 diff --git a/checkpoints/Qwen3.5-2B-Base/8.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/8.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc0e1db8b2253e48d352a4b3f559bf4c203e5c0a --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/8.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7593a089c20c71f681f50fd505d70898b785bc0dc3dd34e2c6f22a544346c867 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/8.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/8.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e3e62de64b9247ad5380c20bd8e877e40ecda031 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/8.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:752658f772933ddc299a586eebbd343535ab0ad9c8afad583ce7e5b5bd62f5f7 +size 8586329 diff --git a/checkpoints/Qwen3.5-2B-Base/8.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/8.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b6c73cd98f77dad51ad44736cfcf9d810d20abf7 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/8.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165c011e854bf6dcd1244a7b88c32b13c4be66c3eba098ca1e300302d4a360c1 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B-Base/8.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/8.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7230e0d68b40a191ea5a738e538246b6092e28f4 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/8.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c44a1e92d679f04f1adfcf6b63595a2401c677e28813564a09ffcbecb3989964 +size 25625492 diff --git a/checkpoints/Qwen3.5-2B-Base/8.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/8.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..af5de2b5770f740f0db3eb1ae38a645e84dc1981 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/8.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b137499dfb80bf0145cb439b2c4b86956af281dd5b9ae29644d7e48048a0163f +size 25625454 diff --git a/checkpoints/Qwen3.5-2B-Base/9.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-2B-Base/9.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..da4029d7fabac4c19d80c6a13f4154f8885ed1f1 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/9.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:235e598178a2dec307be762ff22dc5280dbf687f0be13450ef95833634927d69 +size 25625746 diff --git a/checkpoints/Qwen3.5-2B-Base/9.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-2B-Base/9.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..c170d2b3e24119ff336fa33a98ddf78843a5dfaa --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/9.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6be1ac3019a2ac1cb6390e46bd77ca778c4016864fc4ce29ed515722e44df9c8 +size 8586348 diff --git a/checkpoints/Qwen3.5-2B-Base/9.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-2B-Base/9.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..32e7cb52efaccb0496f41ae7ba9893d9987e5d81 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/9.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50dd31375397c98a766494d950f49aa97f94220ce2dc625edb64b32e71fd8938 +size 8586329 diff --git a/checkpoints/Qwen3.5-2B-Base/9.mlp.down_proj.pt b/checkpoints/Qwen3.5-2B-Base/9.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1bd1e752557954846d331e291aaefe3f78e1c0d0 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/9.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:506f5ebbf99995c5fff1d85751b116abd6790b2aa0964a3f646749794728b204 +size 25748372 diff --git a/checkpoints/Qwen3.5-2B-Base/9.mlp.gate_proj.pt b/checkpoints/Qwen3.5-2B-Base/9.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f34a76dd53e5d0bc94a0add83100f92e446cffe --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/9.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceb4ceeeadcb0af2d14c8974ff4ded9ff781e7e55ae66a8b7632a2e0b70abb03 +size 25625492 diff --git a/checkpoints/Qwen3.5-2B-Base/9.mlp.up_proj.pt b/checkpoints/Qwen3.5-2B-Base/9.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec064cc347b2d386bb54ef51a0bd370aed1dc7b4 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/9.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1f7d9a4fe8d344d4bec73430ffb010aaa55504f3884f81df79c2cbd8c7c2df1 +size 25625454 diff --git a/checkpoints/Qwen3.5-2B-Base/args.json b/checkpoints/Qwen3.5-2B-Base/args.json new file mode 100644 index 0000000000000000000000000000000000000000..8153cacc1d16093c079ed4b0ee8b7bdd2b6842a7 --- /dev/null +++ b/checkpoints/Qwen3.5-2B-Base/args.json @@ -0,0 +1,49 @@ +{ + "model": "Qwen/Qwen3.5-2B-Base", + "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-Base" +} \ No newline at end of file