diff --git a/checkpoints/Qwen3.5-9B-Base/0.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/0.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..73702deb95e3b09467e7e093ff51a51966baeae3 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/0.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:080f0e4c45ccc1674dca612ba5e49486e6089f28f566c2b1d31406e795b9ccab +size 68285586 diff --git a/checkpoints/Qwen3.5-9B-Base/0.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/0.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..7c0e70227a9664c4a3ea84d5340dead94a742eba --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/0.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6efcbf1afeecc039f6ffb9807c9b0f2803cc1910025e34462d5d021081f5f5 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/0.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/0.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d65e712d98497a835be5f6b65d56e0d739169131 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/0.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:472db2956dba06f10ecc43854ef8a352639475a16941976b8300f4da52f9ac03 +size 34206809 diff --git a/checkpoints/Qwen3.5-9B-Base/0.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/0.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa8f0488e944f03964e52a9b1d7ee1a5534b42ab --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/0.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4912324fac83b9ec158b43facacb5eb834dc60a85aa1ec0037db58fbb87efe46 +size 102609812 diff --git a/checkpoints/Qwen3.5-9B-Base/0.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/0.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8933e826aa45ff7e8f46e023fc711a0a7abe6317 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/0.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4f9c036b6770eef15e13169d4c995491d8eb98033096ae7163bf39f32deb8fc +size 102364052 diff --git a/checkpoints/Qwen3.5-9B-Base/0.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/0.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..729dd114d0ba45cb1811915e1d689ea3d039e52f --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/0.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5956787f54425a8adecfad3e7202774ef9b47e8ec76d542126bb7d09d7dc1a7c +size 102364014 diff --git a/checkpoints/Qwen3.5-9B-Base/1.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/1.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..4e0c0e8975b00b93b30ee4c9034dbb0bbc91db55 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/1.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09e0295de967942067eaf95e6f8365917d183db73f703ba8e1aa430a7eaeea65 +size 68285586 diff --git a/checkpoints/Qwen3.5-9B-Base/1.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/1.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8207e2abec7ff18d43a05930a513fb7c87a58fa --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/1.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5adbf95435dbe3d9f6c0a96d55f5e6144f30dcbd9b52d6f501121270454b09 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/1.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/1.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f985a1167ee708871467e588350f30093412c5e7 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/1.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4d7cda63186e2dfff290046e448f17c940fc3230b58d4c81434f7a6b1e755af +size 34206809 diff --git a/checkpoints/Qwen3.5-9B-Base/1.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/1.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4916b99e9064c20f75e70e6c445f0839e3a129ae --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/1.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1508822ff880b5fde371f91d9df0624a972bf37afbf040f4ed1d54935a38dc9 +size 102609812 diff --git a/checkpoints/Qwen3.5-9B-Base/1.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/1.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef56a848b7883d0b315ffe4d48f11e4ad81ac902 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/1.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59c24c1ea9bb61401ec58a56711ec7a63c7af722666f076e33719414107a9520 +size 102364052 diff --git a/checkpoints/Qwen3.5-9B-Base/1.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/1.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6f071668ee69d2a2741b5144650e97d9eeaf15e --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/1.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:030d2c62c38b04508a7653fafa00929649f7d51cf17ecd1e4c1a786138b184d0 +size 102364014 diff --git a/checkpoints/Qwen3.5-9B-Base/10.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/10.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..34c785fd7ade92b0dd660523c22f2af789821efb --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/10.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5884e895bfaf518fd5b2d9fcbbc91499079bd9521cc826f642fb2e1d91996fef +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/10.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/10.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..f05f7fec361a86207ea63cc9d22ddbecd085db4d --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/10.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccb02e2b5afb59606604225ee6de23d8a615382cc3262a7fa606ba7a47d644a8 +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/10.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/10.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2fe8e7de851e676174dca90208e6489b33ede0d4 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/10.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8af223d2cf5922324aea0e3d5f8f3c5ab70c6e9410e49bfce73ba68c513ba099 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/10.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/10.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..37110b5da5b2e131a1f37c0d70bf2156970965fd --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/10.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa474d971e74633c2b15358453780c8721edb2f45530c780cdc6879c7684d314 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/10.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/10.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ed83ec31026cc2b5e84feb122254b8188dcd2273 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/10.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3faed194b22f148e28db205af0c43a986d7927dc5f2ac5f160c306112630de0 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/10.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/10.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..257f0aa957e81aa3dd7ce6bf8ad51fb2a82b22cb --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/10.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48a1330694f78138ca0c2cfcc87bd5af113a870f8f1c22f4361615a7ede215a +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/11.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/11.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..25b6379775d0fdc629350354aaa2f9613611cc7b --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/11.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a487adc427ad4806c6a2be5d38e9808cb39d7abcfa78fe563e0db1633fd38ce +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/11.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/11.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9600c0eed1f28c33e47bc3004d7c58410003144c --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/11.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4de1c4594647775cb4cbdecf5b2d8739ddd95e66ee26c65e9455eb886aff3d8 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/11.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/11.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec8b71f5553c61ed4700fcc813e60336bbb5672a --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/11.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d76d67a1fef4c42cbeb9e22d6e75326aa7cedc7ca273a66b7193f170fb6ce8d +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/11.self_attn.k_proj.pt b/checkpoints/Qwen3.5-9B-Base/11.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1480cb046ac0211f9c0de916babb864bf0aed6ad --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/11.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f255fba52da50616c25451ab65ddc59c367328385b53d8041d3144d5b0ecebd9 +size 8647648 diff --git a/checkpoints/Qwen3.5-9B-Base/11.self_attn.o_proj.pt b/checkpoints/Qwen3.5-9B-Base/11.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8899ad4b4e1103393f09a41fadcc75ecb6597f1a --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/11.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:788e230a764bcffdf66d190ff60552b04666b3c4d2e9a0d5ce07e959afb44062 +size 34206688 diff --git a/checkpoints/Qwen3.5-9B-Base/11.self_attn.q_proj.pt b/checkpoints/Qwen3.5-9B-Base/11.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9795d1b874fab51b7ed1c5abab10790e881bef14 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/11.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a175f309e960a29b11c65a1f167cdccb2a7c72d8cd3def1a83bde4d79452f2b2 +size 68285408 diff --git a/checkpoints/Qwen3.5-9B-Base/11.self_attn.v_proj.pt b/checkpoints/Qwen3.5-9B-Base/11.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f1df33c545c73af16669597f235509915741c09f --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/11.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce945f92bc8f507000c94a2afb64bc72e957a371b905944f1706c3293b468f9f +size 8647648 diff --git a/checkpoints/Qwen3.5-9B-Base/12.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/12.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..a07a5024af83f83b59fa5b7b701fb360a630e0f2 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/12.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eece1e9e4296c19fc7e9bf2b2dd71f6508c11fae40415d233315258dba673ef3 +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/12.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/12.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..4acde365f8b09a512c9a46713f1872746b1c5a09 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/12.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:177fb9bcc96e95f71ca1050c50963f1cf2bbb1f4105f2a4f2fb996d4389c969e +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/12.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/12.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fae9bcea28a4388f567f3bec627d28e19a3d45bf --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/12.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61f8086431f78101d3e81ef4f860d92e6e8e77579c13419656bc23352fd8583 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/12.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/12.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9368bb057c7760a88b64deb4be39e39f5fd7c387 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/12.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:096a26ada9beb0cbe2bf7a6379827cdf4df71d92e87b6823c262ed06deb40fe1 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/12.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/12.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4f23a9e7037f6d7a62d30ed846f0c96cb52856c7 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/12.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f956646638d2fe1d6e64c044b74a16d55cdd4323dba84d247c5e7cdca824d8c1 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/12.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/12.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..56c455f084f16bc1b103b0cf20b5128d241e57ce --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/12.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f9d58a659175ff25e7558cd7d953e2c6212eddb2464624a6867dfbad9c2802d +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/13.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/13.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..ef0f22e92e9bfb6430163800aa2042031780648d --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/13.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96cd3ef2a8db702f1dc155c53c6155c2fe36e77c0a8b4dbf5bdfdefd4c641f33 +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/13.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/13.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..716b6a0fbf6dbe059bea27dff2fd72d22e96b97c --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/13.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7777637a9e8d26223f589865b32eae642ebce982c673a9bb2bc4201ba8d6474 +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/13.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/13.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b8abe5931c62c65ebc8fec525f7ff5805457aec6 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/13.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5e2d6bf93dd4b3ca664f1d012e0f9416f51c6a652ee2b831c78c4e155aabb5d +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/13.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/13.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..71c0c005ae060777bcefb06d45029d81bfd70402 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/13.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:427dcd20bc7f9d7991962847b785909e8390c9b06925597faba48faf1e4397e1 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/13.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/13.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a7999f18ee79b5781feeb38798c8765d3028347 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/13.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:915300df44ef7b06d132dce38326445262513cb01328a4f1fe65e88e7911adeb +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/13.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/13.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ac1174524c2dfbc99da8bc54e7ffdc0d6d09e543 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/13.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9909001d22dd32d421f9c1a134a61b0777831624d9e5616ba5fbd8e6d1a544a +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/14.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/14.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..25e35cfc511dbb84addbaeca3bdbbcce04187eef --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/14.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a03ddb3c681bcebdb9c8344c97220b86d4dbcd4294e33e30a7b6f83977cd6cff +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/14.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/14.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..edfd83aa95bd7c9e3d88b6ae67210d5233dee468 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/14.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4edcf329a63c5559b2a5e66cb26c2cb494ebb049f4dc1e2f5cc995478f54231e +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/14.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/14.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..899f34c51dc84877d98da34a82e20750332c14f2 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/14.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d6aa05be8e74244cf0aef1e3a9c2acf1f43ef09e00c5ad374ca5a5bf8bafea2 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/14.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/14.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0bcf939b04a6c09a39ec475b474924f99768abdc --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/14.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b21c9d16cd52d7a4617e528274612aa4f6dd549074fe385904ebc461d074c1a6 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/14.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/14.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..632286325437de550f9224a49c2d96a2e217c7c6 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/14.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6d12a7af5260ea14a783bd176a5041817fef12e06195274ccb0e3174e7896d1 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/14.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/14.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d0677e30959f81054267c65291ea8ac6d98ee09 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/14.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872e94447dbd3c62e8e556519a777bd0540ad9915cc01e05ad00d22014781777 +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/15.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/15.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a670225024fba41b0809a976709b97081157e618 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/15.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e2172a8626022b66fa14e6c998e5e85df21ce0e13919e8025ed23cad1c5b569 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/15.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/15.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d65f7cd100261fd37d9d29b9b00ec3df4ce01307 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/15.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:856dc14cd8e7a689c6aa169b30570fef8f71591b24856dbb1b250906186ef73e +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/15.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/15.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7b9e505938bc4055749e0970abe80b9f9a20d754 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/15.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cbfac932557e30b419e084641ac467572eefbaf2a5852a08b417f8f2c9c9aeb +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/15.self_attn.k_proj.pt b/checkpoints/Qwen3.5-9B-Base/15.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c68021820ff60682df10169c3b6923e40605253d --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/15.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6be3a82d282c8dae9626f803eefe8caa8c0a767e0215daa54208d0d5c8498abf +size 8647648 diff --git a/checkpoints/Qwen3.5-9B-Base/15.self_attn.o_proj.pt b/checkpoints/Qwen3.5-9B-Base/15.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..176f04223d6aba2e3b31b59323e812df5417d0af --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/15.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0118bc5d743ea80ae4f2ffa6c2b2b838390cdf19735968184f6f1b920019a952 +size 34206688 diff --git a/checkpoints/Qwen3.5-9B-Base/15.self_attn.q_proj.pt b/checkpoints/Qwen3.5-9B-Base/15.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e9e16d9bdbf71f2e4e9ed74e339d73845ae8e1c6 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/15.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a9f6b1f21bdb8caba1bd4936e587971a02cfc2634d741d6d107395b5bb9e1bb +size 68285408 diff --git a/checkpoints/Qwen3.5-9B-Base/15.self_attn.v_proj.pt b/checkpoints/Qwen3.5-9B-Base/15.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..76e5f81f2b29c10bf5de3165b72ec362174a1252 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/15.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63aec7d2c5e1cb930b89efd3154a9f1de1c5879b61bafadcd36c403cd9ee601a +size 8647648 diff --git a/checkpoints/Qwen3.5-9B-Base/16.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/16.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..a4d082d72262f6f551dc9aa499bbfe2902582039 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/16.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a3c2142af6d0019fa4ef9aba15b54639bac436cbe1c851c76a09f748a830b16 +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/16.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/16.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..0447514d1b4ad5857e1b98b83a925e19d858b8b9 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/16.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f97e0dc111d8983d2923b1884b096627fa4b1667fcd5d858d9dd3b78c04544c4 +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/16.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/16.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..29d2ec553c2470567296363fb5e45ce3046ce804 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/16.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:837d79dd8e017a1c5173f988669de29d21cc4b577658a1209755aaf7ce6c393e +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/16.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/16.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8b11c87977d39c2f0e68a5320195d294bd59ce7 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/16.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4012c164c2a68b12a550bd6fbc9744c2203d363474dd9c81933c11a7beebe2f4 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/16.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/16.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..92e382e3191b2b6f9fe007e6fda1fa2d89e5a597 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/16.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e46051eee7408b2b79655ce452e33ece21e72440e18ef0e159dacd437c14e40 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/16.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/16.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd2a72b18b0e877c88cfe048e56142ab6b381591 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/16.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e201c74d789317d5efc8d97cce92a51321c213667c1417831c154a223c06269 +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/17.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/17.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d8c14a36f48f9710d6fa93294c04c1fc5257624 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/17.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8329010d73e90263763368eac4ecd102619107e6d43a8239732e8714523a6180 +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/17.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/17.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb865aa544b82c44b5d80a8d22ff8c1d336403f4 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/17.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2467b2ce67884f0b179166003dfe3da6914fbed20571cfbb7a6c8c56cbe58c83 +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/17.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/17.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..691372ac40c738233ada414c769edb077a0896cb --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/17.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:388df4aa711ae4caf0a242b17c3576361f418bad2e0457447662de29966ab437 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/17.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/17.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..aaa6743d48e6f898b4a2f2644a28c68cee70accb --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/17.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1089ffe470878c2064d25de55e599f9850c5cd34b29ecb73ec3e09fc056e9a97 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/17.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/17.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7c6fbf643f948a42cc8e10018a1989ede11793e4 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/17.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21f1204b0d26b1f7e5842980ff8fa20316fe05b42e9709747943c2fe1351440d +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/17.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/17.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..54ea95a3dd7b6289940cb1e360fd2d77b2c73c1a --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/17.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:317b613bbd345d35afec9deb0258d1712581b5ed90bc9f1125c8acb48bf553ec +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/18.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/18.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..dbe35900791ff600f927b0cdf732ca3be9496463 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/18.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f73c7eb6660bf95e30ad2d3ce27794052a87d28bab6feb4ff6846993daf7188 +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/18.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/18.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..ddafb73f0d3d7d8089f37d8ce52da07d1bfe0ab2 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/18.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2cd12eca28d73e846ff41d157833b5127a0739fd87e930e20ec7fdb5b9dbca9 +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/18.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/18.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..698115a4d6cfe7575bb019e3edda2998ca468dd1 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/18.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5eb2f941c2ee9d0bc6317b9a68c3e153df5ccc5dc59fa9f49fb5e3aab3c29e0 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/18.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/18.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b4bcb6dc804edc01c1f50ac32f4625d3c817a75 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/18.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc1a723f6cd757c25d3c56cbba79b0b5da0df6f184c4fb0e8136d72d8380d904 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/18.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/18.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d7b67d4757a8917982ad4cae779ae960822a1dd --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/18.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:169feac2d9198f845be90bfbe0a1dc0ac88a96d182c4d6603c89901a38a0b016 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/18.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/18.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf06f7bc99f495d4de032bfa6f6568cf6598a728 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/18.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a885cb0b0c3fb7bf0e0178f0b0f23a4177e0e2d331cd31017395c06e6903a9bf +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/19.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/19.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c0f5789b9a16f536a171c053bd0a3b7e15b9b9c --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/19.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3de220cb874c2c8c5ef94dd70482eaff14cd25bca17c5cf10abfd7928c518507 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/19.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/19.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f03f7fa2f17a57c10ff90f22e96932e8e17230b8 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/19.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c676a0ce5dfb10c3df933af796abc4976a57d04aaabaf94bffd2bb9c38cb724 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/19.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/19.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6d8207fa5cb7e6d58cd89755b81abdd4606d4df1 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/19.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:655601560c5c570125d047cf7df484f26bb83305874dd4997136567bf196afdf +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/19.self_attn.k_proj.pt b/checkpoints/Qwen3.5-9B-Base/19.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e3a26264ffaf85e97e9bef982c886c63290f6e4a --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/19.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e2cd1683da03286e4b97e6b1e0f7e919f4f69fbd0578ba47dc0ef071bce3795 +size 8647648 diff --git a/checkpoints/Qwen3.5-9B-Base/19.self_attn.o_proj.pt b/checkpoints/Qwen3.5-9B-Base/19.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d0012eb2259bfa643dbeee5e8ae3b6bcc0f4ee3 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/19.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:669929e42cdaa053e297a67cefcdb63229cdd68baaba2e640c81d0b68d39e1f8 +size 34206688 diff --git a/checkpoints/Qwen3.5-9B-Base/19.self_attn.q_proj.pt b/checkpoints/Qwen3.5-9B-Base/19.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..766b0eefb5b219bed9d979d5914b454b065ea6d7 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/19.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61cddda85acb40cc4ddeb6a5d423f74734a5eb922b71944a36b7ebde3bf5168f +size 68285408 diff --git a/checkpoints/Qwen3.5-9B-Base/19.self_attn.v_proj.pt b/checkpoints/Qwen3.5-9B-Base/19.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..160b879e1e3e6414f0dcdee89014d9171d7ed56b --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/19.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf238fabe7305aabfbdd91b08433ec24ec0bbd901781d37bd0d10717c639c2c1 +size 8647648 diff --git a/checkpoints/Qwen3.5-9B-Base/2.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/2.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa9442f4a6bdb2c5eeb60cd1d7f2d520272044fa --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/2.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b60612715210bfae8e48cc8dc6bab74645ea4e62131600ef47a832475a6877c2 +size 68285586 diff --git a/checkpoints/Qwen3.5-9B-Base/2.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/2.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..d9f3b20402aceee4bc2a18b34cc8a39e52d118a3 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/2.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ece05c49a4e686f938e1df290c93ca6c96ead35a0b52126a504d2cc881730cb +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/2.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/2.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba1ed3d0053d8d5182111f3a16d9ac5fbc88f765 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/2.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3decdcaf088ec2bf2335a11da31588620a74312e6c06b369ad6477102fbe9a60 +size 34206809 diff --git a/checkpoints/Qwen3.5-9B-Base/2.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/2.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6691159a957490cf746c09c162930e8cb953abb6 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/2.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:430606ab79963262fb7f21d50a83b0125dbe410f92447df21bb594d1923228f2 +size 102609812 diff --git a/checkpoints/Qwen3.5-9B-Base/2.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/2.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f03b9c9d45c34909d04588cc5b5470f17a1c71b1 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/2.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90cdf58d216c8e7cd580d12f3e1815b5f2523d4aad90e7fe4d0fa9d6aa5745e0 +size 102364052 diff --git a/checkpoints/Qwen3.5-9B-Base/2.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/2.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..53c24b5891771b8f04fcfdb4f374bd075c1e683b --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/2.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73fd839a5291925723727395ba195d502b172ced096c79fb470ea03c8f3cc1ec +size 102364014 diff --git a/checkpoints/Qwen3.5-9B-Base/20.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/20.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..011af8288a5f06e8255299328c58b5ef388d3b25 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/20.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bebed05200136853610e9de099fdfcd8f0b18f7e320afc804201a3436ebf641 +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/20.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/20.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..fcc5e7d2b05a272db370dbf46546504e8b15745f --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/20.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:355c6205b83f28bc323a7ab018ccb0199bdc3275c3e80c11f72a02480ae589bc +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/20.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/20.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a1545b9debb983d8502ee75006775f07f32732f6 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/20.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c4171c08b13e6fa9d5722f880d5a39160af7ba505799256bfd357201394d294 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/20.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/20.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a60ab82df8a70c5128124c02e2f11b53a75cd8be --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/20.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df137d2fcb738c9a4550e1240564365c064d989b57f409f8797e415083efd771 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/20.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/20.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..89c352258e5aca9de2c3182ca078b0ba857829f6 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/20.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b94339d95f2bf819e7fb9e1b73b9ac5193e8f1784bf2ed836cfe70e7520a54ab +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/20.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/20.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..32e173db02e5cb98191c3eab7d9a74db82065977 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/20.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:463892432a33728c8e3f4ce8028437ae11b4bdd51dd14abf05fe875570fe2f80 +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/21.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/21.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..6c8c6ba72d28c64510440f208b0f0a86b9f19e71 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/21.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b68a10b504ed34c81d313eae2ccbbb929a9ace068a3473003177d47d03e2d113 +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/21.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/21.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..4439ced86b9e356ec747d6208d87799139042e45 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/21.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9679ba24a83c059b4a7f6df5a6dc32336890978268598b360f00ea34073a6e99 +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/21.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/21.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f323720d49ed63ad0786b69ae02d37ef1f472cee --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/21.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a820cafcf55f0ffc1e843ab4f1191a59909804c3b0ae52f3a39d2e9c14ac2bba +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/21.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/21.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dbc5a4dfefb7b52f9016002048c0923b14f828f7 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/21.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a1b883da858cfbd927e2a7aaa8f9ef4e9ecacccb564f34dc6421abb4c5b037a +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/21.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/21.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..302a6e86e5268ea1b8672d2c3148bf37d5c62583 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/21.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:126ab96d73335a6a2dee7fff871a79f05a28fa15be391a4bcaaf26804ffb66b0 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/21.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/21.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c2167418ab011d891282fbc1d40e050e3ecb1b1f --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/21.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1d42e74159916331604f2109b85723b179afc286d63664493f50f1fc8af1eca +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/22.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/22.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c8d030ee3f599782999c9f1237b006723bcb7d4 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/22.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ffe23e9e2e96e8765119ea0bc5d97900510a1df5a24b8180f87e4256dfff7f4 +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/22.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/22.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..c074b9e54bf8ccce6169bc5f23458a702ae11265 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/22.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f8982a4789766d0b8f524a67a4e21b38064fd640ff228de58fcf7336a614b87 +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/22.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/22.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b338cb5aebcf4ff830d1be854bdc0dd57c4fbe3c --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/22.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fdc4c2c43b9dc9eafb97b3f2cd5e5dd2554532bd59d327288da7432a972d64b +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/22.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/22.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a487ae0ecb64bb50188ed48f8c12e96693a5e42 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/22.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c981e72e24d73f64b531bd9ad2f078247cdd14cb2e77d225340426e769fed704 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/22.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/22.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c2037209ffdd21abe343f1db0922a580bcd59433 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/22.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26c852f152aed2418bb31bf80c01f75fdc74beec5af5b81b89176f6a68b85c9c +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/22.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/22.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..eac614c48493777a1b25ff1a3c35d4534c443e83 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/22.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b24b929ca50df55ad5eb425935a974697db80d7dfbce7d043ad954ad12721fc3 +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/23.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/23.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..193a2de61dd57eb852793349f7628725e674716f --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/23.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:211c5c0efa3ab0f3be495456a1f62d6f24ac2b321f38c5bb3c13752905ce4cbc +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/23.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/23.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..99b983ea320f395a1f3698d2c58c691fb581a88c --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/23.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5df8aef580d23718fb2c98c089edea5e6fe4935fafb68c237ed9ca009ea2fe4 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/23.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/23.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e1273d53424da1652613f2a676b00d0ae68cf15 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/23.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86c29711324e9cbf47d91efa28b1b8876b15546034131e0de657c7ac1d979f5e +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/23.self_attn.k_proj.pt b/checkpoints/Qwen3.5-9B-Base/23.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b5e15a0090e2d9dab74175ce4416c945e6333bf9 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/23.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f345391fba311ea9e4e99c7ec028da273b268f3851dab6bcd10a79e2e3371134 +size 8647648 diff --git a/checkpoints/Qwen3.5-9B-Base/23.self_attn.o_proj.pt b/checkpoints/Qwen3.5-9B-Base/23.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..195fc07d7fd48d2e1c326bcfb08887e4944e2f89 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/23.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:642e7da20743b9ad53951b28ca0bc04ab0e574aeb0d49bd0c0384f742be64584 +size 34206688 diff --git a/checkpoints/Qwen3.5-9B-Base/23.self_attn.q_proj.pt b/checkpoints/Qwen3.5-9B-Base/23.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3b3ef3e6a393b01e761013278b69dcfeec1982b1 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/23.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8f1b6fc8bcc5268259eeb42776272a924f06e7cadeaa1d30c49695654d1c684 +size 68285408 diff --git a/checkpoints/Qwen3.5-9B-Base/23.self_attn.v_proj.pt b/checkpoints/Qwen3.5-9B-Base/23.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ca8d61834e1eea1762f5397425926f93a745609 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/23.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22ee5e806dbcb6e98bbee9485af4f1df0cb4b80d8a6dabc98952e07b7ad32ee6 +size 8647648 diff --git a/checkpoints/Qwen3.5-9B-Base/24.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/24.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..c09eb8dedb32559be5515da2ca6c41bc5691ff6f --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/24.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78054880066aea8ca885e290ddef00b579962ed5d4be4563df18788f355b5605 +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/24.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/24.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f6d7e893989408f2c3da98f3e95a41bd939163c --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/24.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32052852005f6c31564bdf16dd6530726009cdc0a9c397629b78d15d56c2822b +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/24.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/24.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5101b3e692f9a8fb190bfeb618e3f51a6a64c360 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/24.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a41eba076e84ad70225a92cb1a4dccc9b77a1715040ba440691a07847784dd7 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/24.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/24.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c452e3549053623e2eda349d93413a2abb2013c --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/24.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a18725ffe1a6f4a8bdf2f071e30fbc933d1df2b45930de13bf06ade1c09a919 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/24.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/24.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c60de770bcc349ed4b84aa388e2683ba7c362f00 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/24.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2ab362f8bbd6477430d44fd6ce87f3d66d05355b76f1ebc89917f3b3d875890 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/24.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/24.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..911b1fa76dcf9170b69448fc45aa469fc55407c1 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/24.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0576a86ebbdae3e9a65c2ae6b2a1df3c02adf007f8fe76bae8e9737ab476cdd +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/25.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/25.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..6577921a2d2ca635fde34e1bec695d8b4c997f0c --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/25.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a544205030c4d2ae454f762f8d2a2a254d7086648c0fb58725d1402f0412a7c8 +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/25.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/25.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7a6bc2b740fb63b5374072b2927f0cb24307b6d --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/25.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3baf06b2b8a54e51f399c6ae45d35489edfb293277faaffc0615b2ffab9b84 +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/25.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/25.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e3c36f58f78d14dbbeda87ba3f4b25ccbdae68c --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/25.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8470f25974b7905c938b51288071325cfb54cea8a7d7148f77a91a769faa3c6a +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/25.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/25.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b952288b528217f7e0ce4796e61dafaf90202e3f --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/25.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b64954890dee4cad1ab1430db28eed3fdeccd3a3b35e69df4c61a1b31d06139d +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/25.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/25.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f1b388ae1099c0bd408b84ee89cd993099b9fdcf --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/25.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4fd225e490c62a5536e313a8920e78214829d613e43c8b6f09897edf9aa7dcf +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/25.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/25.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6f744b88aa85625b44e5670fc17a09a963bcc7fb --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/25.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40d458a4c92987ca243d18a817f3f8e10305f346bbbd6a1a60310c2abdabee0d +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/26.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/26.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..a4b6dd6dfcdf2de4158b4da9d9b66302d74f596e --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/26.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fcc7964e1167b5d36038a961840ea68650bda7f32399db0564131061e9ce50f +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/26.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/26.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..24f6df9ba153f17ca5f626bc2f0722808dfcde3a --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/26.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f13537ea911e988aad56dfd4b835201c24a3b2257a834ae7d5a3abf90e2e0afa +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/26.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/26.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0bf1760cbb64ff5b159af0bb7d4d42cb190a786 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/26.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7225f6c264d5e8ce04654740323168b4bfabec3a21526692794216324680ef +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/26.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/26.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..994756fde81fbb01c6b4d8345c24a0ba92ba9635 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/26.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93d13a2888a7b1b0133a8cd7c3db5fdee025a19d35422cbe053f0fdd1a2eb611 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/26.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/26.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..03185adc05e557a2c30c61ee3762056321b615d1 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/26.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b216f3dc797172a5746ecdd90f9451184520771250f7a50140e02a5bbd60d71 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/26.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/26.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..15ea2cec8b4e67be5fd2274d50b37cdfd23e1900 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/26.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:229445b787fba58b46bd29aaa04a003744aa509c2eefff15ceea4ec7304c4b0b +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/27.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/27.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8098af0d636a984c68b2cd1f476b5438b3c22f88 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/27.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a0d3ea74e338cfddad69d320691b789cd1bb3b0effeeaecf687e688f7da4ccf +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/27.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/27.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c8c9ce75dd9c63f732596e883f896fd6fcbde862 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/27.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9132eef9c82cdbf3f8374b11eb7709313b2de10c59fed9ac8d7dce979772f9e4 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/27.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/27.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..baf12881458c96529611558857b0605032b38aa7 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/27.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:924432bedbf78cba1da074aff1337a4ebed855f3c13ecbe46625f5468c3a5564 +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/27.self_attn.k_proj.pt b/checkpoints/Qwen3.5-9B-Base/27.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..87a33b14204a03b293abeb8656c8c2fc00e7f64b --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/27.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e64aefc40fd19d5ff2c4d22ce1b1d62e26506ba5baa7aa924d689879e66f7485 +size 8647648 diff --git a/checkpoints/Qwen3.5-9B-Base/27.self_attn.o_proj.pt b/checkpoints/Qwen3.5-9B-Base/27.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..522e9406f012f24ae84923798e6a7854b084865d --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/27.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:011a009af21ec8862849296a36ca81ff40b324f690c0c74ed21131a9bce3e069 +size 34206688 diff --git a/checkpoints/Qwen3.5-9B-Base/27.self_attn.q_proj.pt b/checkpoints/Qwen3.5-9B-Base/27.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9a70abbbc230b038ba109529f05e0ba0de55ecde --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/27.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc4ef891de9d67b11feb4b65007b0dc9ebd55868b98071bf288b1fe484560a90 +size 68285408 diff --git a/checkpoints/Qwen3.5-9B-Base/27.self_attn.v_proj.pt b/checkpoints/Qwen3.5-9B-Base/27.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0777f6de1fd2144e02b63676788173a6cbfa9944 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/27.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2fe5b76a66a2c71be5cb2a30ba8d7046e9b36b35dc5b65eccdc5db6a62a9cfc +size 8647648 diff --git a/checkpoints/Qwen3.5-9B-Base/28.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/28.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..254341e7e6751b137f3096215d517335d3a0bcf3 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/28.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f123ad12c6638beece2a3334e5db62c71cdbf37e4688ce4441f8f2a4a38b152 +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/28.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/28.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..08ac7099b65729df10abc3392a166bbfd2d41916 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/28.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c87ffc5fe948279293aa142ae5c37d6cb24d282a0b7d16dee690b3a7e865607 +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/28.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/28.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0897978aa60458c6f18813c0311df6cf3ebce6d1 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/28.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd3d0ff6f9d65b5aa20cfc875b337abd6cb02228e79ca1d0cee697181d9c01d1 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/28.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/28.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..320b8c960d25cfedfec7b69caaa725441cf88926 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/28.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dfb684c29e0955e6173473324577724105f4cceb0a51bfc0742250936042f4a +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/28.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/28.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..63cad4b65f007f7bcee5d4eb62b0dbc48e4a7d7d --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/28.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57411692cb244bde531b6337b45d002ec2426a8f8bd14f98af28ee077e598776 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/28.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/28.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a6e588ae243eee342dead40b32c862d8f4cbb026 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/28.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4c9bcdc4193faa0f7e7cbbea93284021ed8295beace2cbf38eeb4687fbd765a +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/29.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/29.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..099ef4cd684001eda69e1c457700814604df7e4f --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/29.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15b6451cf4eebead68c24a3f29cd5bc5f5b6c20a9706c22ac579c1bab8790b3b +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/29.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/29.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..5c01d1eed59740b74a2c17990eb824a3beecfe3a --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/29.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee9b70c5635dd9b5aebc863c79ce22aa94bd546b2e53f305d7ffbab2eb2f0a9d +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/29.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/29.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d17e30082a1eaa63cab3e6d1ca20ab3f57af3704 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/29.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:205d63d6355419c033f9b1368e6c99382422fb31014b515429455d33290f728b +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/29.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/29.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..db8ae212d217825c05ff9b2a18c56a02abb6f7a6 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/29.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9aef772da61feff12cfbd62466620b0a6ffcb361b5cef2c14e64aab7b9c4358 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/29.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/29.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f2ee9da1d77097fc0a139c3ad9954ef5d90647f3 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/29.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc6a634a997f29eb96239257343fe918b4724f1afd021ebc5553f5c579825dc4 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/29.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/29.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..862606337d623e0b724fbe3e41ee2c1d624371bc --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/29.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22832249f038ca452a04104727a36d83528502e7c2de022efbf0b468762242d2 +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/3.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/3.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f216ecf3d9f73af34193462ba6388490bfc53ef0 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/3.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6992317362841e9f1e6d2e6e7faf42ed211ddcf9b6b78dd149f515fe1d651f44 +size 102609812 diff --git a/checkpoints/Qwen3.5-9B-Base/3.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/3.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c5cbde68824f07b7a691b5433157d178457b397d --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/3.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b7e4725d812f6fac5ed79a3cfd4c55b4ec420c536917bd7b5d3b8ca7d8cc3c6 +size 102364052 diff --git a/checkpoints/Qwen3.5-9B-Base/3.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/3.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..90070ceccd6ac302b7242727e011fd87019f074f --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/3.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:153e7217f7e99d144908d016ae406fb3009c3e41d3c5f2eecba877f108b55dfc +size 102364014 diff --git a/checkpoints/Qwen3.5-9B-Base/3.self_attn.k_proj.pt b/checkpoints/Qwen3.5-9B-Base/3.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0cc277e416aa2f3f8f83a461ba1d764e428c438d --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/3.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ed46679ffd6598dd3d9f76af8282e1df36d00baceaabcb9333bae94d93284a5 +size 8647629 diff --git a/checkpoints/Qwen3.5-9B-Base/3.self_attn.o_proj.pt b/checkpoints/Qwen3.5-9B-Base/3.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b3d08d3dc68746980cb4722755f3b358187ede0 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/3.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ecf167a8a1e94f1dd3d8a8bff95b9d19273612a20526e30302a403668c832ec +size 34206669 diff --git a/checkpoints/Qwen3.5-9B-Base/3.self_attn.q_proj.pt b/checkpoints/Qwen3.5-9B-Base/3.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..59d805ea181175ca4552e02cdbe9fe7f5401b62f --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/3.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d51bd990324b3ab7e38ffb86b461dd5ff0311f4f1194fefeb7fe480555da52d1 +size 68285389 diff --git a/checkpoints/Qwen3.5-9B-Base/3.self_attn.v_proj.pt b/checkpoints/Qwen3.5-9B-Base/3.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4ad7de2791231f0d4b6beab229d656d734da43f2 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/3.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d07f322b039294cd4b2af4c1dc7145f4ab50e683dff144f4cea10cdf3b13987 +size 8647629 diff --git a/checkpoints/Qwen3.5-9B-Base/30.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/30.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..cd580aba1db29ce9c940749f4d386ff998cba921 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/30.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b40c3da02686fcf8e08f4679019b98977be33fa85f4019f51a591383e0be60 +size 68285605 diff --git a/checkpoints/Qwen3.5-9B-Base/30.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/30.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..9bce437bcb4027eb049f87917a2244e5cd54be57 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/30.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14eb3b309574116c10492802000f63a3970aa0bd71fd8a03a58921b3d0990fa1 +size 34206847 diff --git a/checkpoints/Qwen3.5-9B-Base/30.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/30.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d32dfef80395da992577ae77a8f10045615cffd --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/30.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22921abc8ddb03489c26a0e5256f3b979e8a4f3436a0ae16b4d3e4bab565f833 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/30.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/30.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5af7f7c8ace325cf52bf39ccd074647c016bbd52 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/30.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd5d0c2718dfc5fd2765b9096854da220d635cd5d349badf4cf9ff01e4ea4614 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/30.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/30.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6811c456d283b535e8687376cdae622407131c9e --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/30.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f32327151fd78bb9167ee6716624904637ec0d3d94ba260ef58489a7b060f1 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/30.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/30.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c4945e48657ef59c7fa22edaee03bea95a2a696 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/30.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b8b3cc7afd0527c63a85b6a2434e236de8f985d4f90f7ba216b9cbd8886c52a +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/31.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/31.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8cb0840f7449b9a5e668c9147e7a44a71bb12147 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/31.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75577df31318c52f64d43359ffb12444f16f51d9589e86da8f08b9eca4b83429 +size 102609831 diff --git a/checkpoints/Qwen3.5-9B-Base/31.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/31.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..801ff16a2161c586a72d23139e56b0ca32045996 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/31.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34efce46b7bd2457c7ba0e396cc0d039087f6d60b50462922be44c2f7c0f7364 +size 102364071 diff --git a/checkpoints/Qwen3.5-9B-Base/31.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/31.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..58133e181eeb63c8e71de1217853c20a8c60b9fe --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/31.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f7a7c7b71c4c714ea6d8465403c3bcc459296dc2572823c531f8748db616f9a +size 102364033 diff --git a/checkpoints/Qwen3.5-9B-Base/31.self_attn.k_proj.pt b/checkpoints/Qwen3.5-9B-Base/31.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e52686d102c816ba93e55f3b513f8ed8b3ba51e --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/31.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d43211d5befb45ebfd1f90e061dd2ac9d2642542a2c42b8bee162d0da5bcc7 +size 8647648 diff --git a/checkpoints/Qwen3.5-9B-Base/31.self_attn.o_proj.pt b/checkpoints/Qwen3.5-9B-Base/31.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..159b31fa2d46012eb954ba7ee9653f4bf4e5a62d --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/31.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:734d8988312d80bf8055d7232402417f2c3848737dfc87edbe85e989905664f2 +size 34206688 diff --git a/checkpoints/Qwen3.5-9B-Base/31.self_attn.q_proj.pt b/checkpoints/Qwen3.5-9B-Base/31.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9f9358ed943543dc938542f5cee466c305d35561 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/31.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30571f4dc756f7f1219e64bd05ca50d8ce3fb0cae47a7d9c8148c878e60c9251 +size 68285408 diff --git a/checkpoints/Qwen3.5-9B-Base/31.self_attn.v_proj.pt b/checkpoints/Qwen3.5-9B-Base/31.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5c9ae1b77d6576095819af6297d64308f6cd6b30 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/31.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b02c60702cda65103aa1951c0797f8d3eb939c18528440ca787187c6759b06b5 +size 8647648 diff --git a/checkpoints/Qwen3.5-9B-Base/4.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/4.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..e4efd761b6761be547d06147052e03c974a59dd1 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/4.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97961beca3296ac12b08597299400b5cd3cb08a0c09a786a005849efefd57cd0 +size 68285586 diff --git a/checkpoints/Qwen3.5-9B-Base/4.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/4.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e00ca3db4b44fa5c58740c14af112d1394765ed --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/4.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:153b3501ac425aaa81a34d5ff31f67ba3396df40b4f31dc39d1164a650b0b4ae +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/4.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/4.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f5783d6852c9f42c26683d3e8a72e536b4c8b43 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/4.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4df9816a2e1615e8ab99d1c55c5de06f4452700357182e7fddfaad932c91de9 +size 34206809 diff --git a/checkpoints/Qwen3.5-9B-Base/4.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/4.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a260fd302e8ee9dbe1648345a327e0f64faac818 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/4.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf1f231dc294de2a7361c41bc5d022914323f9effb61a58088c50c4bc1a6438b +size 102609812 diff --git a/checkpoints/Qwen3.5-9B-Base/4.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/4.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..af1e58becf97d6de7d27c372310ba23db43f511a --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/4.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b728b88d246b0150e513a0f355ffaa6719ff3aa76370cfd249303afb5e7c1df9 +size 102364052 diff --git a/checkpoints/Qwen3.5-9B-Base/4.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/4.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..89c6ca1a32077260ce8856a2dedea857db989f84 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/4.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc911c5118eb66a256d72c55cf0b4e8a1b76862b37fb76b520819c63718580f1 +size 102364014 diff --git a/checkpoints/Qwen3.5-9B-Base/5.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/5.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..d29763ee5457db2b3f2ed1267ed30ca223129e2f --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/5.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d4e328746139a441804902b34bef3069c49c818a324058c4ec64283d82c824e +size 68285586 diff --git a/checkpoints/Qwen3.5-9B-Base/5.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/5.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..085307bb584e53b923d337c0028f4d2bea91a286 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/5.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c01afd4ae6619b836fda4e7af4d3bd79c2b34ebb6fd63a52be99c481e5b780 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/5.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/5.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3bbd11cf300ae50fc16c33c84a4a70830fb02618 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/5.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b507eb50d98ba005b7e12be6d1f248f9d8c9003ae36b94c69ea185412cc49b76 +size 34206809 diff --git a/checkpoints/Qwen3.5-9B-Base/5.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/5.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8bab96f0d4cb434059956c9e7e0ba86ff98ce968 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/5.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95b77d247213e9a7b80470f217a535f5424c24fc8e01db76d5e4f40c8f597347 +size 102609812 diff --git a/checkpoints/Qwen3.5-9B-Base/5.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/5.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f55e7bf1e911c826836e0c05ffac1e6fe4bb37c --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/5.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59f6dc55ef5275eac059af6403b88f98b1ca5d159d3f4f15b8bb9e24ce95b869 +size 102364052 diff --git a/checkpoints/Qwen3.5-9B-Base/5.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/5.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..00f367ef0dd0856ccea9724e676124e7e98aa0fa --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/5.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12128932865e7d9477649d1c5dbbf5ac56610ece207101060c33f91c7d13f206 +size 102364014 diff --git a/checkpoints/Qwen3.5-9B-Base/6.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/6.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..a52c6c426370016481a1e26a54beaf4c3e84204a --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/6.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad893ec7665232ba62c9c8449d2d92f95311dec3ca403434b487d630f737cd29 +size 68285586 diff --git a/checkpoints/Qwen3.5-9B-Base/6.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/6.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..8df3754a1dade473193a02fb16b4731ee3be99df --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/6.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cfe8c8c3e9c0a33870bc1f6b8554bb9c9cf380c4557545a34798ce46af423a7 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/6.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/6.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2373225a96f9285b884143b215061d4178d08990 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/6.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12e2a7ee8415fe44641fdbae3dec7aad60769611aba083ea5ac1d28558ca182b +size 34206809 diff --git a/checkpoints/Qwen3.5-9B-Base/6.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/6.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..05c78d525e7ee9cc34b8e4d1909d9573f98edabe --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/6.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac25a5909d0a32a04db15080a8ca9cd5f6df71601bd303e93a0525ba75649786 +size 102609812 diff --git a/checkpoints/Qwen3.5-9B-Base/6.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/6.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4fee1649d1ea5b807960a3950cfac093401476e1 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/6.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeeddb651a4c548233ca3dfef7326f7421480a8e4e13af639362cdc11df22720 +size 102364052 diff --git a/checkpoints/Qwen3.5-9B-Base/6.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/6.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ded56ec10bced1ce6d6dd070b72afd12b4c4b16 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/6.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b8d13425d982599b2fb2779ce5439ddbf1d99f47ff89e08afcd0a8246997412 +size 102364014 diff --git a/checkpoints/Qwen3.5-9B-Base/7.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/7.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e397a5c4313315dcde75baa19bcfb2e4c5bdb1d --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/7.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c42dedf416fc0682552f42d8048b2d7401749bd050131ea63102b6d15373e749 +size 102609812 diff --git a/checkpoints/Qwen3.5-9B-Base/7.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/7.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4e2e024dd8d9c21d119fcf2fb132fc1487386d03 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/7.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5fdeb08c311d97b0d4c8a6097e7fe0350cb156a990b5f425fb56a570d2e625f +size 102364052 diff --git a/checkpoints/Qwen3.5-9B-Base/7.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/7.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ab43767758eadfdeb568e58e6aff0af2e0b0cd90 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/7.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95cd63135335de2c513de7830e60d5b4c647296f6083790add4153fa40a21a3f +size 102364014 diff --git a/checkpoints/Qwen3.5-9B-Base/7.self_attn.k_proj.pt b/checkpoints/Qwen3.5-9B-Base/7.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..67609df6dffa9e47dcc9868c9bb450008b34fe44 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/7.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:682137589c00637d7de322ba8e19583bfda4f178b6897d986dd52bd8261f969e +size 8647629 diff --git a/checkpoints/Qwen3.5-9B-Base/7.self_attn.o_proj.pt b/checkpoints/Qwen3.5-9B-Base/7.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d5c12de686f3c0c7a42c6706cbb8ed04c94365e6 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/7.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6239eb1ac62e594f6ce4bbda577edc84ef75787687ee3f47b23a1d3b7b396b3b +size 34206669 diff --git a/checkpoints/Qwen3.5-9B-Base/7.self_attn.q_proj.pt b/checkpoints/Qwen3.5-9B-Base/7.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..eab8d152f72fcce1d992ddeb9b9ee215cee33f90 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/7.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e84bd88916bb3dacc2c0fea6578807fb09c05fe0b420ebfe1aa96a5c0f1bcec +size 68285389 diff --git a/checkpoints/Qwen3.5-9B-Base/7.self_attn.v_proj.pt b/checkpoints/Qwen3.5-9B-Base/7.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d7f3c0f974ca5f25315d7d268dc5040ecfbfae8f --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/7.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bff35f6cfec3edd49d786e886801c0048a9fdbe5ae6066c18ad14d24e0c66a60 +size 8647629 diff --git a/checkpoints/Qwen3.5-9B-Base/8.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/8.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca4f1e993e02df1f1647c433490b16bd1d97321b --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/8.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce67ed9a2f510a355a0ad8708bc626251c0c0ea9af774b2d79de8a2ef45d3735 +size 68285586 diff --git a/checkpoints/Qwen3.5-9B-Base/8.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/8.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..c37174303d38b089043d0ef68ae777cdb0a64c07 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/8.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88287fa3a58d67611dc1f18de2169ae75ab7e39558bba8c003a05846bdf33890 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/8.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/8.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..98ef8fa3b4f3f46843c86a919d31f5af7e657c95 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/8.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e794920fb3cfcc310e1a92e606839bf4fe87bb9e458ed1ac1ce753f3c1339ad4 +size 34206809 diff --git a/checkpoints/Qwen3.5-9B-Base/8.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/8.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..aa368d48ea910c19779491abc0934f95896f0c65 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/8.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f31b540b83374be86925929bae77c0a07f1d4502d33c3946965c8338d68f52fa +size 102609812 diff --git a/checkpoints/Qwen3.5-9B-Base/8.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/8.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a51db45fe988f945f5abcdde79cdc6f26b4bc3cc --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/8.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59e3f9fad23c80b7bc87275b915960f4257f4f8c8ca35358597a2638aa9e8fb2 +size 102364052 diff --git a/checkpoints/Qwen3.5-9B-Base/8.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/8.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1dfcc363b53bb3df6ccf9d7d5968ed43243dc5d8 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/8.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b5f0a3d8ec957ea0e7fb5e89f586defec19169540aa3b18e1b47f811445ea4 +size 102364014 diff --git a/checkpoints/Qwen3.5-9B-Base/9.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-9B-Base/9.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b1fd89dc64481c74a7104c962f4f16a4138cda6 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/9.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7e1e3b3b25eb8b5e09a645d267f45ed9166ff3bf1af64dc22b00f1ae796e321 +size 68285586 diff --git a/checkpoints/Qwen3.5-9B-Base/9.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-9B-Base/9.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e0e8f1d339a8f997686128c35bb9e36bf754b21 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/9.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d0e39fa52dcb61206ae9281795c1998f694c8c0bdcef5c7518e36668823f146 +size 34206828 diff --git a/checkpoints/Qwen3.5-9B-Base/9.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-9B-Base/9.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..562d7b8b3fbe5d1ace1ec66ded92709bd8d1328b --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/9.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:081fe287ee559526eab58d119481b033ec3982c535e23ea163628481c9907b5b +size 34206809 diff --git a/checkpoints/Qwen3.5-9B-Base/9.mlp.down_proj.pt b/checkpoints/Qwen3.5-9B-Base/9.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ccbc587c89c38b2673537285d7783e0cc6b9c797 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/9.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f9f42089422f43f0098703c6f7cc7a8226df214e0d9d580af755f2c8a574d74 +size 102609812 diff --git a/checkpoints/Qwen3.5-9B-Base/9.mlp.gate_proj.pt b/checkpoints/Qwen3.5-9B-Base/9.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4f4d6fa1ed3d2c14410816367c11f5cad6369cb3 --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/9.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fff9dc4c962cb13b58f51230eef525ca92da9e21e0a044339734c0f2eb2db297 +size 102364052 diff --git a/checkpoints/Qwen3.5-9B-Base/9.mlp.up_proj.pt b/checkpoints/Qwen3.5-9B-Base/9.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..759420d419156743bd6d8c33c3eba557a39a5e3b --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/9.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c27f0033830e111b93cc3b724d035cb24a4437bced5c513f7b3e12e5705e44 +size 102364014 diff --git a/checkpoints/Qwen3.5-9B-Base/args.json b/checkpoints/Qwen3.5-9B-Base/args.json new file mode 100644 index 0000000000000000000000000000000000000000..0fc9a0de4c0e5e2793028bb4b757ef8e47faa0cb --- /dev/null +++ b/checkpoints/Qwen3.5-9B-Base/args.json @@ -0,0 +1,49 @@ +{ + "model": "Qwen/Qwen3.5-9B-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-Qwen3.5-9B-Base" +} \ No newline at end of file