diff --git a/checkpoints/Qwen3.5-0.8B/0.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/0.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..b463b72c813f1726642fc3d70cf5f8dac02f7c16 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/0.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94d95085bd210a54f32d41610c014815601aedcfb132a9e7c653dc35caba9ce8 +size 12815506 diff --git a/checkpoints/Qwen3.5-0.8B/0.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/0.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..911762859c4b2260b569ecfc6aa011225d7a68cd --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/0.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3f1130ca15d351290f156c6ca89e3e288176c7f1c7196a782671a6baafdd035 +size 4295788 diff --git a/checkpoints/Qwen3.5-0.8B/0.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/0.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f8e70841820a7515b1ac80dd555b8f39c796ee0 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/0.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17091c36baed035c50807fcf8841f7d0ff6ff0f67a1341617b1096ff8875a6fa +size 4326489 diff --git a/checkpoints/Qwen3.5-0.8B/0.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/0.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b182dbcafc7adecd4e1b8e51fd0670a15984152 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/0.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc045423c6ebc81faaf774ee380b34d827dd2e6b6a56ae01c6861495a28c4f8f +size 7567252 diff --git a/checkpoints/Qwen3.5-0.8B/0.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/0.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..caf5876fb68c092f6ea7dc5e5d30e40d955f19f5 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/0.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6712a1f469d3414ce02bcb81cf5426ab37cadcf4161aaf0550229a18025e97f +size 7490452 diff --git a/checkpoints/Qwen3.5-0.8B/0.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/0.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..397579ce75ebb901ad437bbe28684540214726f4 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/0.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5441cd41912a3510b3820ccd438bf2aec3de13cc167f0cce0151b633b54bc8a0 +size 7490414 diff --git a/checkpoints/Qwen3.5-0.8B/1.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/1.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..94911ace8b8cc6350a10be79bda31a2bf0fd75c4 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/1.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01f4f06cf859dadb409ed043773757b09bcabadc52ec7a71fac6e006e5df7d8b +size 12815506 diff --git a/checkpoints/Qwen3.5-0.8B/1.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/1.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..c0175a0b4a800f3d2c54408024bd5b64ed6d3a32 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/1.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cb2a7956f4be744f3c18562b244f8f1d270b1ab23dd75d2f8ce23febf96c60e +size 4295788 diff --git a/checkpoints/Qwen3.5-0.8B/1.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/1.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9c2be5741ff5c628ec7e661df288a42de6485c33 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/1.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec4b29530d79d19ece75c34730dc6b683f80befd304b5f03437ba216f89b894b +size 4326489 diff --git a/checkpoints/Qwen3.5-0.8B/1.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/1.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4e0420bacdef9890a85fe9515db2a5852e733dcc --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/1.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fa9fcc171514209744b4ab99cbb7fa0d7e96a43e4096063b380864abd354749 +size 7567252 diff --git a/checkpoints/Qwen3.5-0.8B/1.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/1.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..aee1562b3881290216c549dfd801c00d8ad9fb14 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/1.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8be78324a3f34ac08a315b879f12ff3656bebcb4509ad355a06ff33aa94f2d44 +size 7490452 diff --git a/checkpoints/Qwen3.5-0.8B/1.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/1.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f14733de590b6867554ce88396b21483f385af6 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/1.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b0880f713f2b6173f54929a3a3349a2394635a784a868fcb509241edd457e0f +size 7490414 diff --git a/checkpoints/Qwen3.5-0.8B/10.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/10.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..2971974a1a5002b08d43bcd7e0eba9ad71d081cb --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/10.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cab737cc8e22229c5401255cd0735edd8831322d8d34c54980050213dc9492b +size 12815525 diff --git a/checkpoints/Qwen3.5-0.8B/10.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/10.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7bcbebac6ecc77f8b0c2a932a65099ca24d265a --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/10.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9bc8da6459fa70a39bac92037799b46af4ba962fd93625826976a6ccf18ab3e +size 4295807 diff --git a/checkpoints/Qwen3.5-0.8B/10.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/10.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6379c4a8071461aa18c515eaa69dcdd7c5786a3 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/10.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb54bc38ca56ae784b25a4a0f08f5424c97e7a6e32c08a9fab53b80c31a30682 +size 4326508 diff --git a/checkpoints/Qwen3.5-0.8B/10.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/10.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a043cfe98610a05d50f42ac195431222bd5811c --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/10.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9231ce8797f2475521c0eee85fd5132772bdfa978acfcdc33ed30f331ac590aa +size 7567271 diff --git a/checkpoints/Qwen3.5-0.8B/10.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/10.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..974719089545a6d6029c026cf5ad60ac3fc05129 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/10.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:519c221f00e9286e5f347dabb85e4ae82ea2140dd1ec5f10fa1af0abe6fd870e +size 7490471 diff --git a/checkpoints/Qwen3.5-0.8B/10.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/10.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a1e95dd62655fb2b69378f91d6801ac49475fae --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/10.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c271ac733984a224659a2a6d79bfb55aa43cdef4e3a9904f46abf1c066124a7 +size 7490433 diff --git a/checkpoints/Qwen3.5-0.8B/11.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/11.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..db3593530391ef3ea5199761a4c2ff1cd8e8ba58 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/11.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b44e0befba06767e04989c27fd72a123d00cb48263b193c84d6d8416bc28f2c +size 7567271 diff --git a/checkpoints/Qwen3.5-0.8B/11.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/11.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ec78934b1ca4a6655d899c7b6efbb9465b2a00d --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/11.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9f7a6ba5b2951791b112e4353d94dc48d9c4ee1e553cb160ee42cc689876374 +size 7490471 diff --git a/checkpoints/Qwen3.5-0.8B/11.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/11.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0dec8ac12a0d431947f93208889b60da6f9717c6 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/11.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f498d5cc2f1ab7c0901688cd381b4977070d56b6f8a747a24483b11903a4d6c +size 7490433 diff --git a/checkpoints/Qwen3.5-0.8B/11.self_attn.k_proj.pt b/checkpoints/Qwen3.5-0.8B/11.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..01eb0b84c4863f3477a4910b58512f8fae0b0d77 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/11.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38ea51374e9854e47bd29776cb5333a4a1027ebfc0996036c75d18d13b966560 +size 1100768 diff --git a/checkpoints/Qwen3.5-0.8B/11.self_attn.o_proj.pt b/checkpoints/Qwen3.5-0.8B/11.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a518b1f196057fa2535f97c2f3e968f0159b78fb --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/11.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e29c427f2c39f552a2d0ced27cdedfefb0f00ea66da83fd472821f5d2d2bab67 +size 4326368 diff --git a/checkpoints/Qwen3.5-0.8B/11.self_attn.q_proj.pt b/checkpoints/Qwen3.5-0.8B/11.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a79b878888328d2b2d070e4b45ee25e839dd1fbb --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/11.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c802decca4b753cec3fba58f2dd184981ccab95c5401473e78dc77e24bbd174b +size 8555488 diff --git a/checkpoints/Qwen3.5-0.8B/11.self_attn.v_proj.pt b/checkpoints/Qwen3.5-0.8B/11.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..59ccc41fca7d0be604a371badd5e13ea488995f6 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/11.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4e1af37105059e63ed5f8ff4ec9ad5d2b386f5bf4a0bb33d19f770be9fa71a5 +size 1100768 diff --git a/checkpoints/Qwen3.5-0.8B/12.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/12.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..92fa56ede02d0ae181d12766193c1f3c9853a863 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/12.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae34283a5e856b9281323e4d7439b2cc56b205cec709be25deacd4153b690325 +size 12815525 diff --git a/checkpoints/Qwen3.5-0.8B/12.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/12.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..687482024e497f4af23c8790719c356f4587813c --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/12.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1382913ff41304458cce783f89b3e0fdfdcfbcb2ea763e2d3e7a077fc534f28b +size 4295807 diff --git a/checkpoints/Qwen3.5-0.8B/12.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/12.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b24e3f1f2f4eb09e50e3a46c935cf9181b987003 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/12.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed0321a66fb64a6bd5df0e2f8f2aac91702ef34fbf35fe44a1b5e1a41d55a52b +size 4326508 diff --git a/checkpoints/Qwen3.5-0.8B/12.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/12.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ab80bbadf1306891d5c9d278ec2503ff8be8589 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/12.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08ec518bf2a51a8768531c1f675e3c79265016b2776da56dcdc73e2e5633d0c2 +size 7567271 diff --git a/checkpoints/Qwen3.5-0.8B/12.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/12.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d532244a31ea6200baff00107b69ebd5bb5c87b8 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/12.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72f48ded166bd142475cf247a93abb569a65965fffc9f44c557ef3086dfec29e +size 7490471 diff --git a/checkpoints/Qwen3.5-0.8B/12.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/12.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..41e7236f77d07f55f81aa5b91bb9414a996cf757 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/12.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b00649441328fc280e25ca833ba79ae62a4f2b9ead5feaa3d44ae754f47fe443 +size 7490433 diff --git a/checkpoints/Qwen3.5-0.8B/13.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/13.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..250f3b550c40d062468174a1decf2aca443c4080 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/13.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ea24b1a90b174c59a65dd92436327d2abe2ccb3dff5b6bd28d9513443f10ea5 +size 12815525 diff --git a/checkpoints/Qwen3.5-0.8B/13.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/13.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..626932bc0c13e5589a03abe44bf318cb48e15786 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/13.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9361f8de3b8c890df25f56a890295573dd4ba3340a04617d83340843d43222cb +size 4295807 diff --git a/checkpoints/Qwen3.5-0.8B/13.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/13.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c2e736184d0737bcfbdc2adfc3339eb83b874983 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/13.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a78248be3a80cfd65af7a416419d73445a32c0e016eced41ead5e425a852b4aa +size 4326508 diff --git a/checkpoints/Qwen3.5-0.8B/13.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/13.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..08cf0520e7396623a707fa16d9e4eaad7a806ab2 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/13.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55b9fbf54308a6bfb48f081d0779b80af82bd8b98d222655e5d6ff1469d4a6ec +size 7567271 diff --git a/checkpoints/Qwen3.5-0.8B/13.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/13.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4db8678d929871440a7919eb84253d47e1c0147f --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/13.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d278fc04bf3718311f9d4f9d57b402ec7b08a21a99d043eb5b21a204bfa320e +size 7490471 diff --git a/checkpoints/Qwen3.5-0.8B/13.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/13.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a7a3c1e9b1f204925ae34ce4325c33d35edb480d --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/13.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:523f40e40c80f42689e3b4517f91014b8e0ca667c2992f19fb7ec2d7ce5312ed +size 7490433 diff --git a/checkpoints/Qwen3.5-0.8B/14.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/14.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..bd0e15d7fc7b88caf9f643b18949aa2294487ac0 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/14.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe63fdda54c96701435919908e93a3e8873da6ccae1a7167a80f5facaf1628f3 +size 12815525 diff --git a/checkpoints/Qwen3.5-0.8B/14.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/14.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..b58771abced3d4f11f3f910d5f6a8e71b16071d6 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/14.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:436cc65b41441cc0f7b7860e5356baed002a96fece58fb5c33d9cde294cb4b62 +size 4295807 diff --git a/checkpoints/Qwen3.5-0.8B/14.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/14.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4055e9eb131322661b0926d7733452da5265704c --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/14.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed05679c1cccd6341220e1604df17631bd30046b937ccce3460992ff3b68935f +size 4326508 diff --git a/checkpoints/Qwen3.5-0.8B/14.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/14.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..93e6606d1356e8deba70830cb64e08bc02a2b104 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/14.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f852c852cc4b7e0e55217e154135147869ddfaaa80040b68d41184d5fa4c514d +size 7567271 diff --git a/checkpoints/Qwen3.5-0.8B/14.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/14.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..723c59d414da4777339cd162868308ca86dd9322 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/14.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f8f796360d4d4b460bd5ffc2cf045118ab052b5c0e5c3d7b7655d2ff2677801 +size 7490471 diff --git a/checkpoints/Qwen3.5-0.8B/14.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/14.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9fe335c508a84dec0c01819e89a191de18c7f2d8 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/14.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f71f7f283302aeb0815a3492120059bb1e31a8f6ef19cd49c25b96a764d3360 +size 7490433 diff --git a/checkpoints/Qwen3.5-0.8B/15.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/15.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..50664098e1b604ca1aa167a84e1a83dffdc77868 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/15.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f5fd9c244af31ec723933ca65de28ae833fefc122f35b4d036413524b52107f +size 7567271 diff --git a/checkpoints/Qwen3.5-0.8B/15.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/15.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e4ce292f3cade0940113e8d985d31649e42bf4e8 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/15.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:235c2f5556d1a46a3f3d25a884a7392883939cd7d3a8a145387785857f4f9f27 +size 7490471 diff --git a/checkpoints/Qwen3.5-0.8B/15.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/15.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca39307d04ea8a95347636986ae2e0f647ada8fb --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/15.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d640ff242c6f3a2b1dbf98b3cfb12d529419410351f0432f77103c9414ae57d +size 7490433 diff --git a/checkpoints/Qwen3.5-0.8B/15.self_attn.k_proj.pt b/checkpoints/Qwen3.5-0.8B/15.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f2412381a459678677390525bf10b4258ef7e6b0 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/15.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e78c26f9934a353bfb43b6f232a2ecdbb59ab10bbf01d0f9d88f17ff97dc0ef1 +size 1100768 diff --git a/checkpoints/Qwen3.5-0.8B/15.self_attn.o_proj.pt b/checkpoints/Qwen3.5-0.8B/15.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..90e42cdf058688fb3f132a52b1feb0437b40e297 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/15.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c313cc4424825613b672a2cdf25a27239763a0268332b2525bb0660b8acbc00 +size 4326368 diff --git a/checkpoints/Qwen3.5-0.8B/15.self_attn.q_proj.pt b/checkpoints/Qwen3.5-0.8B/15.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a8a866ee9689af9182b456e4758437368be63cb --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/15.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582257b62801245627e754b6d0066f1d76ee3f33bb208ea5e04aaca2fd262b21 +size 8555488 diff --git a/checkpoints/Qwen3.5-0.8B/15.self_attn.v_proj.pt b/checkpoints/Qwen3.5-0.8B/15.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e7fc7beeda2f3397d923604e0b86bc5d31021076 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/15.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8930a0a71698a74b4ee174dd35dbcca35f81ab1a7258268af3635433748150d +size 1100768 diff --git a/checkpoints/Qwen3.5-0.8B/16.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/16.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..2567ed0ca8f12029e2cfd44d59bf3a2cf14c36ca --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/16.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8201eeaf1a7af15c572ce8e1700bc98ff4a078a607745fc0ec0317b6bc95b78 +size 12815525 diff --git a/checkpoints/Qwen3.5-0.8B/16.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/16.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..99a211ce500600433f792279df14aa94236cbfb3 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/16.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:864a88cd3643738835c87bbef29a2bdc4bd4bb7ae8d62009827c9f29555c0303 +size 4295807 diff --git a/checkpoints/Qwen3.5-0.8B/16.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/16.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..721cde8440cff435d7d19ee34edf0b351041c8bb --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/16.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2571a8b47ae8d97af620c943ba9bd06e78d177b3a6d48be3adcb66df137eeb36 +size 4326508 diff --git a/checkpoints/Qwen3.5-0.8B/16.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/16.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8aaed0850efabcaaffcafab55cc80a97fddf066e --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/16.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7e7aac3b5d0c2b8b43b089c595e1a1cd409433bc7e67a455c3fae57b38dfa36 +size 7567271 diff --git a/checkpoints/Qwen3.5-0.8B/16.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/16.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..581e9b90a117c81235f9ca7bb946625f2f76c864 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/16.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea4272dbd99059410a8f146e5c4ba79cf6a55c6565585e27855d4671a908ccf +size 7490471 diff --git a/checkpoints/Qwen3.5-0.8B/16.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/16.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9df525d8593a7642650a9129c34c50b06b37dc55 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/16.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a40a254896815c2d7954d5a06238295dacfb40a03bc80d9ab271555a3206235e +size 7490433 diff --git a/checkpoints/Qwen3.5-0.8B/17.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/17.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d8d2aa9038ad46a239bbf1ea2d86b5b760a536a --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/17.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d07a1697b7f9a7c83c65e9a120e027364318edde2184fe06b371eb8b4b8a478b +size 12815525 diff --git a/checkpoints/Qwen3.5-0.8B/17.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/17.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..b11bb4e7bda1aa5b482f1130f51219a63c2595bd --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/17.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af0871be2b3fe9dbe7f64bb6a9211f724a8267739f1f3ee80ae286449c5b20af +size 4295807 diff --git a/checkpoints/Qwen3.5-0.8B/17.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/17.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..868a0a51b1a224221135cdbb4f1e9e9e0997d083 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/17.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef40c3bef8d7f56e306e822ce2d76a7893f2bb4a6a1245c562e3c92cab2ceddc +size 4326508 diff --git a/checkpoints/Qwen3.5-0.8B/17.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/17.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e7573c11570a528b261d90fc7752070944882f3 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/17.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d2497b3c84cbdfbb3b5a8e949ee345685bb5334fcca34a0cbddf4196c962922 +size 7567271 diff --git a/checkpoints/Qwen3.5-0.8B/17.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/17.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d1cfdb717bd5770cabec3fa29d63454636dd977f --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/17.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:316602077365035845305e8828b929a2569dc61093eee97aea3613cf348a4402 +size 7490471 diff --git a/checkpoints/Qwen3.5-0.8B/17.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/17.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..40da721dd2022348cc817ceb5bbebd0dfa598238 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/17.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5709846689480d81fb32b83b978c064144fc46ca0999a599ba210e10e47b0bd +size 7490433 diff --git a/checkpoints/Qwen3.5-0.8B/18.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/18.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..8c1aecb4d1abdcbfd4383ac684cc98da7859f026 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/18.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e57c66cea7fb35a8427473b631023d67ea7db175b4d17a6a3bebcaacde33d703 +size 12815525 diff --git a/checkpoints/Qwen3.5-0.8B/18.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/18.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..29fb721f76eb3569002a7328085464228fe27c68 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/18.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e20efd7d2541031b4c7bd0f2b1b4edccfe42c3ac6ff32a05c46c68060dfe7d +size 4295807 diff --git a/checkpoints/Qwen3.5-0.8B/18.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/18.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d51cda61c4a9910d1431d8751f3c3bb00b844aaf --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/18.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b7627513799d0d50f4979682c2d42ce408c5bc8bf0b0ad5fce068bde4403682 +size 4326508 diff --git a/checkpoints/Qwen3.5-0.8B/18.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/18.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e843ad5d8cd0d61d2a8f92b4d0f5349475fd559b --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/18.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a91a6660ac652fadb6c03477a8f60b79882ea4157ec17e885b2e0002c08178e +size 7567271 diff --git a/checkpoints/Qwen3.5-0.8B/18.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/18.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..27f93a9ba29e31b2448b792ada2bff6b4a49b9fb --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/18.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d0e4ee3792eb4521b5bb8b698a2dd9ed204a6804937e741e2d20067fa8405f9 +size 7490471 diff --git a/checkpoints/Qwen3.5-0.8B/18.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/18.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..38cdc744f1d783f01cce6918a53a49ed8f0d6fc8 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/18.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bce1291c67811abaea1f613ae2d33d71313f3f64bc2ba014562d9a1d89c5080b +size 7490433 diff --git a/checkpoints/Qwen3.5-0.8B/19.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/19.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..092b55cdc08fe4b187d80e797f6c378f388de2da --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/19.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f60c19f707ef0facf9d4eb1c456ea141babdf2d8c4335c9b7e0d6261ee53db3 +size 7567271 diff --git a/checkpoints/Qwen3.5-0.8B/19.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/19.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f36c0d2e00a3cdb62f98049e7f045bf3d952f6f --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/19.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f86df79745fae0e727705b41f410e4951b0e4e094ead492fe0be6e2fd596fc +size 7490471 diff --git a/checkpoints/Qwen3.5-0.8B/19.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/19.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a7fb468c048c7e77257307bce596eee6c9556ecc --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/19.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4106cfc9f5b00101adef7449c225a08eea5833ac7bdbb489bf0b664ad19fb69 +size 7490433 diff --git a/checkpoints/Qwen3.5-0.8B/19.self_attn.k_proj.pt b/checkpoints/Qwen3.5-0.8B/19.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d91f3327b4390e34efcdd980eea4628085a011ef --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/19.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d4c84ac37e1d1821616a07ccfe773376313f415869586a60bb5fc92b677ad62 +size 1100768 diff --git a/checkpoints/Qwen3.5-0.8B/19.self_attn.o_proj.pt b/checkpoints/Qwen3.5-0.8B/19.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..baa2fc5c678b016b9b85566cd0d932dc2af6b220 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/19.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:066b49c8273b4265f5f5e2529d7701907e417a76daaecb9a908c65d39be0f2ce +size 4326368 diff --git a/checkpoints/Qwen3.5-0.8B/19.self_attn.q_proj.pt b/checkpoints/Qwen3.5-0.8B/19.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5bad98754354631756be17ccda405d026c36fe7b --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/19.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5a5d29b0790a2ca3ae68d387f0d6efc18d95d8d56ed17115733566f253a81af +size 8555488 diff --git a/checkpoints/Qwen3.5-0.8B/19.self_attn.v_proj.pt b/checkpoints/Qwen3.5-0.8B/19.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..be954b08e1214a844e9e35e9a459a6baaaf7cf48 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/19.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f10d0af3cd422c21552b6554d01ddc093d462b0868fb5825124ec1719ffeb44b +size 1100768 diff --git a/checkpoints/Qwen3.5-0.8B/2.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/2.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..3da6622c1007cc579aaa039ed10e2cb34eb77457 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/2.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a65c08e571610549d9d83734dc03979f2b22694adfb9cb78f99e7bbe908a1e0 +size 12815506 diff --git a/checkpoints/Qwen3.5-0.8B/2.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/2.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..51f4feb9ad5eee09432531c4d409a40b80677e09 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/2.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a72a94f329ad2270c595b58c76a944cd66110cc2a9254b7081a08e03ed75f159 +size 4295788 diff --git a/checkpoints/Qwen3.5-0.8B/2.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/2.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f28cce6f28edfb9e96d7651f4ba768a865d3f91 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/2.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f8d6d463e49c5c804eff881a3c71af56434844ee5d4f3fcb60d7a0aa9c6dce +size 4326489 diff --git a/checkpoints/Qwen3.5-0.8B/2.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/2.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae1f2607ce94ba07b1763e763cada5ca1a6330b5 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/2.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1bed089683e7a4d732f5e44f6dc7d08dc2b362c2daf7ed39ce36a75d6fa7008 +size 7567252 diff --git a/checkpoints/Qwen3.5-0.8B/2.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/2.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..75288119c52db803cd5ecd3a533027dd87ef12ad --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/2.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8542acdec3c0895be7ce14621aa2aa90f7f2c8ea186c5277c0afb68b241f276a +size 7490452 diff --git a/checkpoints/Qwen3.5-0.8B/2.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/2.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..832acf71b9c6d71629881538cae720bafaa820a1 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/2.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6c83de166801cbe60a7d98715d587adfdbafe587bcfd8a70de7da40ee83a3d4 +size 7490414 diff --git a/checkpoints/Qwen3.5-0.8B/20.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/20.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..1baa0d81acde677f156f36da319ffbb239a3342b --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/20.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b89f18d02e0e076d8e1fa02ca45794e94420b0b5bc5901c242e0dd4183be1e4b +size 12815525 diff --git a/checkpoints/Qwen3.5-0.8B/20.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/20.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..6675c007ba6e467cb3ccf40e5ff68cf5182b7afb --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/20.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a2770c46adadb0b557774a7ba2dc63bbd34f3373b1ee21e34530fbedd294c37 +size 4295807 diff --git a/checkpoints/Qwen3.5-0.8B/20.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/20.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..50945a1ef216f9d0e95aabb7dc8ff6d1b90cb160 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/20.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4947fc7b1d921db77fe2504aab7cb3cb3fe4d18ebaa575aca4a5185d0f932b77 +size 4326508 diff --git a/checkpoints/Qwen3.5-0.8B/20.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/20.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b4d44049a82773124ae71053d6a0afbb7cacaefe --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/20.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ef221a943e8f64946c31bf741d0fc8889e78788e5e725e36f95380c2c5ecbc4 +size 7567271 diff --git a/checkpoints/Qwen3.5-0.8B/20.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/20.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..58676a03d0742f6be569818a3300f5bd73359a80 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/20.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b35d8a0c9086a15e239e166a38d1afc9ad047610d7ddf7f401097a5be292d3a6 +size 7490471 diff --git a/checkpoints/Qwen3.5-0.8B/20.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/20.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..18a314306b58c778dd75c8921a4ebd667dca2e47 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/20.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e7622b4573342a5c60e2ef31ef9ff9f8d01fe9af0b3740b64168e48d3c637bf +size 7490433 diff --git a/checkpoints/Qwen3.5-0.8B/21.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/21.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..963e1cdf5e9570532833f2bcf1c3e3436a7045f7 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/21.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06f902067c9e9efbeba56b2fa413f6bb129a4a9563bf55c17e38a1cc24c59dca +size 12815525 diff --git a/checkpoints/Qwen3.5-0.8B/21.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/21.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..d998c4793fbb6f3e35edf3d7f8facaf82f8cc96c --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/21.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fea34489c0c970b3be272709b2b627990511ae3cece29357a9980ba491abd0fe +size 4295807 diff --git a/checkpoints/Qwen3.5-0.8B/21.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/21.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..cd4bca9406e1b38a638501563285bef7899b1f6d --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/21.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ac25aa1f3b19ab86edfd5514749148280aa7d27c66ee205948663e4acd68c94 +size 4326508 diff --git a/checkpoints/Qwen3.5-0.8B/21.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/21.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..bbfe5066cbdd99b696dd8de4ebe6e784301cbb79 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/21.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77c84ae7c2a10da9942bc48855e74279fb40e5df87358265a2265d74541c6de9 +size 7567271 diff --git a/checkpoints/Qwen3.5-0.8B/21.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/21.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a8a156f91169e2b4e4602d02dac2fd4b6244691f --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/21.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3ad8931d457e276b6a9d0b705034e1ddd7871f9a9bc9fc07cc9b65066b3fe1e +size 7490471 diff --git a/checkpoints/Qwen3.5-0.8B/21.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/21.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..866618eb23f76521f06fd61bc86d382584ffd1fc --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/21.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83fc5b318de6377aa98becaa70e951dbf0c97d014211e80b3071859772ba10c8 +size 7490433 diff --git a/checkpoints/Qwen3.5-0.8B/22.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/22.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..69de0dd9a4d17cbe7ce575d2b63bbef9a3e03603 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/22.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a8f4c34a6db4dcb3040df212c60c63d6f34843dc77892e71214a2347b6bd64e +size 12815525 diff --git a/checkpoints/Qwen3.5-0.8B/22.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/22.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..3e9a3c933adbd6452e6eb89cfba2d063b35675bd --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/22.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cadda335b0a83935bf1c500c7f8e164a3c04c2c24646e66b0b0c854d54e53cfe +size 4295807 diff --git a/checkpoints/Qwen3.5-0.8B/22.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/22.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7af060e3391773dcac6b681e1857fadbad2cfbf5 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/22.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c99ab99cc8a9c098d65fc690bd02cfd6e97057e934cf67fb764eba65b49c6d03 +size 4326508 diff --git a/checkpoints/Qwen3.5-0.8B/22.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/22.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2ab55fd6dd28d512c4b31814059dfd87b5649ab7 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/22.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aa2dac50d08673d811b560529613f167183b7aa472927e31a8e1ec464091c93 +size 7567271 diff --git a/checkpoints/Qwen3.5-0.8B/22.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/22.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ee9c77696a22dcf2eb80b139dd48030421b840d --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/22.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e99888b29c88142a553012ebef535e2eb1279e8a1463d2eb94f96f3e613cda21 +size 7490471 diff --git a/checkpoints/Qwen3.5-0.8B/22.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/22.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5e006c5b3d7377ba6a249f1bf04949babc806c4b --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/22.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e906cd5cd1e648152ec420434242ac673865e37f53f94fa116192b7d12bab72d +size 7490433 diff --git a/checkpoints/Qwen3.5-0.8B/23.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/23.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7892ef190f8c45bc283e06ccce1a062eb93dd63d --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/23.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26018a264dbed16d40a9996f74c8aa17b5b4adb8d8d244209d7e7316953ffc85 +size 7567271 diff --git a/checkpoints/Qwen3.5-0.8B/23.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/23.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f5654b919954113c903dbe1a9cc2b0e1ca3c0117 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/23.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d422abbe44a5fcd8a8fecbcc655f3fb97863f555724a86aac8988883fe25053 +size 7490471 diff --git a/checkpoints/Qwen3.5-0.8B/23.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/23.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..707ffa8266a57e346e42092e29c044e42b859124 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/23.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55b606e99cce727703ce9f6446d8dbcb9abc4e05963385bb8b67c1ab80caab3f +size 7490433 diff --git a/checkpoints/Qwen3.5-0.8B/23.self_attn.k_proj.pt b/checkpoints/Qwen3.5-0.8B/23.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b4a0c889fb6152560f3037d04645f41c5dae8ec2 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/23.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4b1f1153172c6991893f5a6f58870d22a2449ec7788287c991d5bd4b0c5af65 +size 1100768 diff --git a/checkpoints/Qwen3.5-0.8B/23.self_attn.o_proj.pt b/checkpoints/Qwen3.5-0.8B/23.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba53ea86b976d25cc2db00b75a3269e9fd8e26f4 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/23.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b143cb9af4d14b20bed54c46cd197ef7a44e6c79c1e5b346e62e5c3f440dedc1 +size 4326368 diff --git a/checkpoints/Qwen3.5-0.8B/23.self_attn.q_proj.pt b/checkpoints/Qwen3.5-0.8B/23.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc4871ebbd0c947d11b2cbb4466f09160952b885 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/23.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc7a65e0a996ce05816a7eff83b855645e5fc93c410ecd29d19ab13fd27701b8 +size 8555488 diff --git a/checkpoints/Qwen3.5-0.8B/23.self_attn.v_proj.pt b/checkpoints/Qwen3.5-0.8B/23.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..979b9737694edc8b5452ba88342efc2bc206c0c7 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/23.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e3985567cbee43fce3bbf7d4cb54183be5911a00216e4d854386561c012ee98 +size 1100768 diff --git a/checkpoints/Qwen3.5-0.8B/3.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/3.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d99127f2b4014d1d63113864dfd0d7bb6c7cc0b0 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/3.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3260f9788a0c01ef72e6afae5db47780c3a49af5b5ef5860cd42e256b4a1825 +size 7567252 diff --git a/checkpoints/Qwen3.5-0.8B/3.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/3.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0317a058160622d40e2f189738d7d92e857d513b --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/3.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da5f2f46e1cfbb5fbf08af420c0625d8526a86e6142719f79c062eefaca1a88f +size 7490452 diff --git a/checkpoints/Qwen3.5-0.8B/3.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/3.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..18b754933d425b47ef31a0ea939a61ad0b295d4a --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/3.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4061060a2ee0e2551dd6c0d849fe947c742cd534d748bb93c87e5c17f141a3c5 +size 7490414 diff --git a/checkpoints/Qwen3.5-0.8B/3.self_attn.k_proj.pt b/checkpoints/Qwen3.5-0.8B/3.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..84afba9d021c44ca7bcc9eb72bd4d1d174942ae9 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/3.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a96da90f347d87f8a15358ad13fb6e6380b3003c83121ab1618679e984539d6 +size 1100749 diff --git a/checkpoints/Qwen3.5-0.8B/3.self_attn.o_proj.pt b/checkpoints/Qwen3.5-0.8B/3.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..297ec9a39a50c62b4d814f9115ba43c262d2f039 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/3.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9de9eef1a6fcf8a435836c2fdca49e5dc73ad17b8a44581adb2f31183a670634 +size 4326349 diff --git a/checkpoints/Qwen3.5-0.8B/3.self_attn.q_proj.pt b/checkpoints/Qwen3.5-0.8B/3.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a022a1b7f9a274f699176ccce927e8ac99c636b9 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/3.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ee0c0ccdf41f21c26c41bde0034d78a762e2428c74288768a0ef668ea505108 +size 8555469 diff --git a/checkpoints/Qwen3.5-0.8B/3.self_attn.v_proj.pt b/checkpoints/Qwen3.5-0.8B/3.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8e77d02c33eaca81f60eb0b6efc0d7eef25866ad --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/3.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85240a9f935117cf342f2282cbe8e4c9cc696403d126d403fadd05638355f375 +size 1100749 diff --git a/checkpoints/Qwen3.5-0.8B/4.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/4.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..ffb28cbf5160ec9e8d275a8e54cb55d10f7fd699 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/4.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f238784e32551024b0ee305de3b74cbd3350912cae8c1349daffbf1a5018770 +size 12815506 diff --git a/checkpoints/Qwen3.5-0.8B/4.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/4.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..28586c1f9334ace6558128a03df0a5a335c05562 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/4.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:409c2047795aa84ec2bf7be57aa625da8cd301534e0ea07aa394dff2c707983e +size 4295788 diff --git a/checkpoints/Qwen3.5-0.8B/4.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/4.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..890900023a10b7d3729cc9a92d5f0a87518af2c0 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/4.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c648b5706f8809a087e76a625b40a6e0e97138e9388a0dc7d87f7a60f6c5562b +size 4326489 diff --git a/checkpoints/Qwen3.5-0.8B/4.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/4.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d4cb82f9d92547f2dd3164be2a479112fd9eb34 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/4.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:892c200d27a5bdb5ea755b50679466ba579318438aeb4bc265924056d430f16b +size 7567252 diff --git a/checkpoints/Qwen3.5-0.8B/4.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/4.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e615dab675609957c898aff650438f9fcf7e1f7e --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/4.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19298f250efd94a7fd9bd31271d2b352b1f4e415bd293d96ccc1ac052153ec9c +size 7490452 diff --git a/checkpoints/Qwen3.5-0.8B/4.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/4.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f9e582d6fe264c96e10313f5ce1d3ddebcd7d199 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/4.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4059c623b66fe3863c8259d3c6e9dbfe01203f12d22e1f3ed44c73e17aad047 +size 7490414 diff --git a/checkpoints/Qwen3.5-0.8B/5.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/5.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..0cb8130516a96515079eb58582dd6bb49bc584e9 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/5.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14c3a1c4d784feb3b4d4f38cf458ad1be7692b636947c264ac65d64baa507735 +size 12815506 diff --git a/checkpoints/Qwen3.5-0.8B/5.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/5.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..0c99953e475c1ce5766256d3f561e36b819826fa --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/5.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:167534ef1f61377f44a30d404a35ca9b06e46bd4c4e4e9b5203701160ee4e271 +size 4295788 diff --git a/checkpoints/Qwen3.5-0.8B/5.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/5.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..bee81bf5ae20e2e7f42470b8def8b3021dd3902d --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/5.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69bef550da357405c3326ebde47bed68adf1f88128440a1bfc35b8e8181fe942 +size 4326489 diff --git a/checkpoints/Qwen3.5-0.8B/5.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/5.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4fda673a436e046e3bea4245164d0cefc549ff40 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/5.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b2b88fc45e255ace273d4e34becb152f0b8f73e1636dacde6742ebd0a1841d8 +size 7567252 diff --git a/checkpoints/Qwen3.5-0.8B/5.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/5.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d3edf0a998cfbae78a430ca6161390905e86f10 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/5.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d26838ea7148014267b74625ae8d765c3028cb456c5e534b7b6822c192b832 +size 7490452 diff --git a/checkpoints/Qwen3.5-0.8B/5.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/5.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5ed6a20315dfa99ad0f29225da2841f95e9b6a9f --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/5.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41029214f9b3cc585faea2899c277f10321e6989a137d4c70433c58cda97660c +size 7490414 diff --git a/checkpoints/Qwen3.5-0.8B/6.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/6.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..740761c6cabdfcb3cbece535e6c6798cdc310837 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/6.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b6fb510c99abbe4922e95133e38a83922a40d67ec7aa38fef71059764073f8 +size 12815506 diff --git a/checkpoints/Qwen3.5-0.8B/6.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/6.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..f36ec707acca76abcf5c43b2e9610e37fa337670 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/6.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fc8a4a921f05aef488b1fbabbdba2d1eaf278425a67ac0ee8b2de3f8fe82c45 +size 4295788 diff --git a/checkpoints/Qwen3.5-0.8B/6.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/6.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..357bb0be3c3085f267a4ea2437babfd3f988df1f --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/6.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eef1c86b44c8c857c2e6ce974a9c6b00715c7d2e082767cb49b1af47f4342dae +size 4326489 diff --git a/checkpoints/Qwen3.5-0.8B/6.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/6.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc753387b128ab6adee546624fa256d1b97ac61e --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/6.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b28ff57747d296e2630cb56cf96c033c9647f52b5dcfd80b578332ea982bd088 +size 7567252 diff --git a/checkpoints/Qwen3.5-0.8B/6.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/6.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..46af12fa15886f0c72b67e170d761e8905e8c463 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/6.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7195c423744e9bedb7f690a4e5df04323c4cd4c70635bb8c6149702d3b10f0ab +size 7490452 diff --git a/checkpoints/Qwen3.5-0.8B/6.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/6.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..42c82bd6171d02452e579e45b338bd54eb3f620d --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/6.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:057c8ee179bd5651d68439e0ffa35cb15f142da5fd255aea49fbd84c5e99baa3 +size 7490414 diff --git a/checkpoints/Qwen3.5-0.8B/7.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/7.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a8765c9949afd58ee59987970eefb6b38d84842c --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/7.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d458e6c92d748e6664f706ddd5b022a30d3117492e9dd863d4ef207af5ec204 +size 7567252 diff --git a/checkpoints/Qwen3.5-0.8B/7.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/7.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9749c01405573f7d4c52e63aedc4a5b395123d93 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/7.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7194a2c94b73bfc5c378ed3d1b99d2568858ee4ce9b6fcec4398af1da63bb81a +size 7490452 diff --git a/checkpoints/Qwen3.5-0.8B/7.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/7.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..560b982633d5f4c048f2d07446fd9f6d7564905b --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/7.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15489e18834a680cd7774dd02e37da35e89f2e8e8d87fa8468b20f5556bf8e6e +size 7490414 diff --git a/checkpoints/Qwen3.5-0.8B/7.self_attn.k_proj.pt b/checkpoints/Qwen3.5-0.8B/7.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b75bd52bbfbe4b4dcc04f99d0844b86afd5d283b --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/7.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda0954150875ba8e5d855d9e35b8a022ca28acba3b7c06e4d3d5bd281186e04 +size 1100749 diff --git a/checkpoints/Qwen3.5-0.8B/7.self_attn.o_proj.pt b/checkpoints/Qwen3.5-0.8B/7.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f63de15d60333e4a66706773dd9eaab4d7432a8f --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/7.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:284f18ad4442b3a6285ce18fe6c95151f21c5e70773a8b193e447265ce16307b +size 4326349 diff --git a/checkpoints/Qwen3.5-0.8B/7.self_attn.q_proj.pt b/checkpoints/Qwen3.5-0.8B/7.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6435bb9f7b8194d5b268bfaf55619b4b52727b87 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/7.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b50ee082d096907f9a167ef6f8c8633d10f59019184d85ee6f9b916edc87cea2 +size 8555469 diff --git a/checkpoints/Qwen3.5-0.8B/7.self_attn.v_proj.pt b/checkpoints/Qwen3.5-0.8B/7.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..828bb31e3412bc8dae82e09d76b049269e46abba --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/7.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:857d20825546f3fe1eb36fcee2de24615d7844844b97d2f6f586717a26b67435 +size 1100749 diff --git a/checkpoints/Qwen3.5-0.8B/8.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/8.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca3d1e40ea491cd4bb1698e75d1a69881433ef85 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/8.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f6fc48ca27d0fa243f2ccf184541660e26325ae8624f4a9a5651dead57eb4ed +size 12815506 diff --git a/checkpoints/Qwen3.5-0.8B/8.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/8.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..396e44a62743b4d5a270c1426c04edbfc44dad73 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/8.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:907796c2ec5d86d68b39c7bbd2d9762bc1379c151ac183ec4549abd9e5fc6077 +size 4295788 diff --git a/checkpoints/Qwen3.5-0.8B/8.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/8.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3ebb903814b7879c95a634d3d238a05a907ca389 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/8.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbcd3d13338d1a54577d51cba0113038de09da594dcba4d885c935a99c0ab09e +size 4326489 diff --git a/checkpoints/Qwen3.5-0.8B/8.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/8.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1efdb70c6d3558b5a8b95a6bdd44185b2e1bf55c --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/8.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:494e736995a8cac5d4cd89f4c4fa93b9925615ff924ecef327e6d7202ad7fc60 +size 7567252 diff --git a/checkpoints/Qwen3.5-0.8B/8.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/8.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..89637f4f2c3a70e2b3252e1f1d7d91372fa1c576 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/8.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba5088b97ab13194c3af4b048d4ef000599ca2bd7993e099be436230e966c2f +size 7490452 diff --git a/checkpoints/Qwen3.5-0.8B/8.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/8.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..077d2cc943d62679b9e27ce29eb5dc8d748e30ba --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/8.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afe7319a429ed25fc00b209a16b94c57da055b5f2cac2606b9c6205bca795c27 +size 7490414 diff --git a/checkpoints/Qwen3.5-0.8B/9.linear_attn.in_proj_qkv.pt b/checkpoints/Qwen3.5-0.8B/9.linear_attn.in_proj_qkv.pt new file mode 100644 index 0000000000000000000000000000000000000000..878be7aa7dc1053213d2e99d105df2cb74cecc3a --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/9.linear_attn.in_proj_qkv.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e75378ccca19f8b961053aa75767d34b3d63813646fcf4c3cc7f2440bd9e3b0 +size 12815506 diff --git a/checkpoints/Qwen3.5-0.8B/9.linear_attn.in_proj_z.pt b/checkpoints/Qwen3.5-0.8B/9.linear_attn.in_proj_z.pt new file mode 100644 index 0000000000000000000000000000000000000000..99e8f4c13539df0ab3e263e930a53cdab851db76 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/9.linear_attn.in_proj_z.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7346c5904e42dd77c51db7bc5494ab9f40969197295d116a6d9001405fdf4fbc +size 4295788 diff --git a/checkpoints/Qwen3.5-0.8B/9.linear_attn.out_proj.pt b/checkpoints/Qwen3.5-0.8B/9.linear_attn.out_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..59efaac79d7055abb662b1221c849d13531c34ce --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/9.linear_attn.out_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ccd3c149557fbd81244a910536318f5460bc5f56fbd22b4c6456e21f9c1536a +size 4326489 diff --git a/checkpoints/Qwen3.5-0.8B/9.mlp.down_proj.pt b/checkpoints/Qwen3.5-0.8B/9.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..67a07bf905dc9968d2b9a8baf2daf20aded9f4f9 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/9.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa87fd7af31255330cd2469870cf05e963fec6f8df56defb946e491a6adf880c +size 7567252 diff --git a/checkpoints/Qwen3.5-0.8B/9.mlp.gate_proj.pt b/checkpoints/Qwen3.5-0.8B/9.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec1f8c0243dbb820fd5653dd55a1a6c6938992a9 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/9.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a867d6b5dd4be1e55b5893deaf5cac0c3444e8744f63a47951113f021bc3495 +size 7490452 diff --git a/checkpoints/Qwen3.5-0.8B/9.mlp.up_proj.pt b/checkpoints/Qwen3.5-0.8B/9.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..817e6f86f91956ae451aa048e802b3c0e970ba89 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/9.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c243724fe25fbb7500a4746a40bd2701084d7836703dc6024a4e7e5fbca21ed +size 7490414 diff --git a/checkpoints/Qwen3.5-0.8B/args.json b/checkpoints/Qwen3.5-0.8B/args.json new file mode 100644 index 0000000000000000000000000000000000000000..bb542a5480ac57ea3bc2305cebb5e06afcbfa1d7 --- /dev/null +++ b/checkpoints/Qwen3.5-0.8B/args.json @@ -0,0 +1,49 @@ +{ + "model": "Qwen/Qwen3.5-0.8B", + "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-Qwen3.5-0.8B" +} \ No newline at end of file