Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,160 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text
+model.embed_tokens.weight filter=lfs diff=lfs merge=lfs -text
+onnx__MatMul_16859 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14776 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14781 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14786 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14829 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14843 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14852 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14857 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14873 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14878 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14883 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14924 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14938 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14947 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14952 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14968 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14973 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_14978 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15019 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15033 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15042 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15047 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15063 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15068 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15073 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15114 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15128 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15137 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15142 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15158 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15163 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15168 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15209 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15223 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15232 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15237 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15253 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15258 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15263 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15304 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15318 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15327 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15332 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15348 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15353 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15358 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15399 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15413 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15422 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15427 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15443 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15448 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15453 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15494 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15508 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15517 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15522 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15538 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15543 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15548 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15589 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15603 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15612 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15617 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15633 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15638 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15643 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15684 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15698 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15707 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15712 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15728 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15733 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15738 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15779 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15793 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15802 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15807 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15823 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15828 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15833 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15874 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15888 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15897 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15902 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15918 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15923 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15928 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15969 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15983 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15992 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_15997 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16013 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16018 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16023 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16064 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16078 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16087 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16092 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16108 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16113 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16118 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16159 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16173 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16182 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16187 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16203 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16208 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16213 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16254 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16268 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16277 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16282 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16298 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16303 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16308 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16349 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16363 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16372 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16377 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16393 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16398 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16403 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16444 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16458 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16467 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16472 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16488 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16493 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16498 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16539 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16553 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16562 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16567 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16583 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16588 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16593 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16634 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16648 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16657 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16662 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16678 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16683 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16688 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16729 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16743 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16752 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16757 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16773 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16778 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16783 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16824 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16838 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16847 filter=lfs diff=lfs merge=lfs -text
+onnx__Round_16852 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,3 @@
 ---
-license: apache-2.0
+license: cc-by-nc-4.0
 ---

act_dict.json

@@ -0,0 +1,2290 @@
+{
+    "model.layers.0.input_layernorm": {
+        "input": [
+            -0.22867023944854736,
+            1.1115107536315918
+        ],
+        "output": [
+            -2.1261632442474365,
+            3.831766366958618
+        ]
+    },
+    "model.layers.0.mlp.act_fn": {
+        "input2": [
+            2.046371889719012e-07,
+            0.7579811811447144
+        ],
+        "output": [
+            -0.2726189196109772,
+            1.9698854684829712
+        ]
+    },
+    "model.layers.0.mlp.w1": {
+        "output": [
+            -1.3973281383514404,
+            1.1478052139282227
+        ]
+    },
+    "model.layers.0.mlp.w2": {
+        "input": [
+            -0.19404251873493195,
+            0.20824076235294342
+        ],
+        "output": [
+            -0.6336596012115479,
+            0.544675350189209
+        ]
+    },
+    "model.layers.0.mlp.w3": {
+        "output": [
+            -0.6615440845489502,
+            0.7680639028549194
+        ]
+    },
+    "model.layers.0.post_attention_layernorm": {
+        "input": [
+            -0.5048871040344238,
+            0.5236737728118896
+        ],
+        "output": [
+            -0.925523042678833,
+            0.7021209001541138
+        ]
+    },
+    "model.layers.0.self_attn.k_proj": {
+        "output": [
+            -16.452835083007812,
+            6.599212646484375
+        ]
+    },
+    "model.layers.0.self_attn.o_proj": {
+        "output": [
+            -0.5184494256973267,
+            0.46981656551361084
+        ]
+    },
+    "model.layers.0.self_attn.pv_bmm": {
+        "input": [
+            -5.756418258728857e-11,
+            4.316623210906982
+        ],
+        "input2": [
+            -0.23561592400074005,
+            0.33119601011276245
+        ],
+        "output": [
+            -0.21975915133953094,
+            0.3089066743850708
+        ]
+    },
+    "model.layers.0.self_attn.q_proj": {
+        "output": [
+            -9.491658210754395,
+            14.472428321838379
+        ]
+    },
+    "model.layers.0.self_attn.qk_bmm": {
+        "input": [
+            -15.129252433776855,
+            15.248381614685059
+        ],
+        "input2": [
+            -16.292478561401367,
+            16.165193557739258
+        ],
+        "output": [
+            -350.88092041015625,
+            296.008544921875
+        ]
+    },
+    "model.layers.0.self_attn.v_proj": {
+        "output": [
+            -0.23130042850971222,
+            0.3251298666000366
+        ]
+    },
+    "model.layers.1.input_layernorm": {
+        "input": [
+            -0.6882500052452087,
+            0.5670577883720398
+        ],
+        "output": [
+            -1.9846813678741455,
+            1.2388458251953125
+        ]
+    },
+    "model.layers.1.mlp.act_fn": {
+        "input2": [
+            0.0,
+            0.7920277714729309
+        ],
+        "output": [
+            -0.2325526624917984,
+            1.414695143699646
+        ]
+    },
+    "model.layers.1.mlp.w1": {
+        "output": [
+            -1.9397541284561157,
+            1.1908618211746216
+        ]
+    },
+    "model.layers.1.mlp.w2": {
+        "input": [
+            -0.19818152487277985,
+            0.3571622967720032
+        ],
+        "output": [
+            -0.4769497513771057,
+            0.557122528553009
+        ]
+    },
+    "model.layers.1.mlp.w3": {
+        "output": [
+            -0.8463128209114075,
+            0.9521018862724304
+        ]
+    },
+    "model.layers.1.post_attention_layernorm": {
+        "input": [
+            -0.4584429860115051,
+            0.3836226463317871
+        ],
+        "output": [
+            -0.4750775098800659,
+            0.45680534839630127
+        ]
+    },
+    "model.layers.1.self_attn.k_proj": {
+        "output": [
+            -10.099939346313477,
+            9.865056991577148
+        ]
+    },
+    "model.layers.1.self_attn.o_proj": {
+        "output": [
+            -0.19676999747753143,
+            0.458579957485199
+        ]
+    },
+    "model.layers.1.self_attn.pv_bmm": {
+        "input": [
+            -2.383558073137948e-10,
+            3.8818066120147705
+        ],
+        "input2": [
+            -0.5660212635993958,
+            0.6268333792686462
+        ],
+        "output": [
+            -0.2186438888311386,
+            0.2836461067199707
+        ]
+    },
+    "model.layers.1.self_attn.q_proj": {
+        "output": [
+            -6.189110279083252,
+            6.045177936553955
+        ]
+    },
+    "model.layers.1.self_attn.qk_bmm": {
+        "input": [
+            -6.714675426483154,
+            6.662216663360596
+        ],
+        "input2": [
+            -9.725031852722168,
+            9.801608085632324
+        ],
+        "output": [
+            -283.8371887207031,
+            185.15756225585938
+        ]
+    },
+    "model.layers.1.self_attn.v_proj": {
+        "output": [
+            -0.556850016117096,
+            0.6166768670082092
+        ]
+    },
+    "model.layers.10.input_layernorm": {
+        "input": [
+            -99.1098861694336,
+            11.07666015625
+        ],
+        "output": [
+            -1.4399017095565796,
+            1.4974979162216187
+        ]
+    },
+    "model.layers.10.mlp.act_fn": {
+        "input2": [
+            3.426980811127578e-06,
+            0.9152793288230896
+        ],
+        "output": [
+            -0.2603260576725006,
+            4.84480619430542
+        ]
+    },
+    "model.layers.10.mlp.w1": {
+        "output": [
+            -3.465219497680664,
+            2.4651899337768555
+        ]
+    },
+    "model.layers.10.mlp.w2": {
+        "input": [
+            -0.282131165266037,
+            0.384011834859848
+        ],
+        "output": [
+            -1.5551173686981201,
+            1.1471128463745117
+        ]
+    },
+    "model.layers.10.mlp.w3": {
+        "output": [
+            -0.7345466017723083,
+            0.6632845997810364
+        ]
+    },
+    "model.layers.10.post_attention_layernorm": {
+        "input": [
+            -44.71582794189453,
+            4.991600036621094
+        ],
+        "output": [
+            -0.597541868686676,
+            0.8133209347724915
+        ]
+    },
+    "model.layers.10.self_attn.k_proj": {
+        "output": [
+            -18.501943588256836,
+            14.959020614624023
+        ]
+    },
+    "model.layers.10.self_attn.o_proj": {
+        "output": [
+            -1.499884009361267,
+            0.9227837324142456
+        ]
+    },
+    "model.layers.10.self_attn.pv_bmm": {
+        "input": [
+            0.0,
+            10.06771469116211
+        ],
+        "input2": [
+            -0.9095252752304077,
+            1.0232160091400146
+        ],
+        "output": [
+            -0.5237104892730713,
+            0.6686661243438721
+        ]
+    },
+    "model.layers.10.self_attn.q_proj": {
+        "output": [
+            -9.523984909057617,
+            10.38270378112793
+        ]
+    },
+    "model.layers.10.self_attn.qk_bmm": {
+        "input": [
+            -10.853270530700684,
+            9.348071098327637
+        ],
+        "input2": [
+            -18.354463577270508,
+            17.64851951599121
+        ],
+        "output": [
+            -338.5840148925781,
+            253.34640502929688
+        ]
+    },
+    "model.layers.10.self_attn.v_proj": {
+        "output": [
+            -0.9095847010612488,
+            1.023282766342163
+        ]
+    },
+    "model.layers.11.input_layernorm": {
+        "input": [
+            -101.14524841308594,
+            11.28887939453125
+        ],
+        "output": [
+            -1.5151044130325317,
+            1.873944878578186
+        ]
+    },
+    "model.layers.11.mlp.act_fn": {
+        "input2": [
+            3.2362688671128126e-06,
+            0.9267445206642151
+        ],
+        "output": [
+            -0.2646248936653137,
+            4.923959732055664
+        ]
+    },
+    "model.layers.11.mlp.w1": {
+        "output": [
+            -3.655752658843994,
+            2.5590267181396484
+        ]
+    },
+    "model.layers.11.mlp.w2": {
+        "input": [
+            -0.3750685453414917,
+            0.3230517506599426
+        ],
+        "output": [
+            -1.2398120164871216,
+            0.937217116355896
+        ]
+    },
+    "model.layers.11.mlp.w3": {
+        "output": [
+            -0.6163890361785889,
+            0.6410446166992188
+        ]
+    },
+    "model.layers.11.post_attention_layernorm": {
+        "input": [
+            -77.12692260742188,
+            8.598007202148438
+        ],
+        "output": [
+            -0.8170561790466309,
+            0.9191882610321045
+        ]
+    },
+    "model.layers.11.self_attn.k_proj": {
+        "output": [
+            -22.057157516479492,
+            19.91728401184082
+        ]
+    },
+    "model.layers.11.self_attn.o_proj": {
+        "output": [
+            -1.0617130994796753,
+            1.217335820198059
+        ]
+    },
+    "model.layers.11.self_attn.pv_bmm": {
+        "input": [
+            0.0,
+            20.30547332763672
+        ],
+        "input2": [
+            -1.1099920272827148,
+            1.2887194156646729
+        ],
+        "output": [
+            -0.921210527420044,
+            0.7567086219787598
+        ]
+    },
+    "model.layers.11.self_attn.q_proj": {
+        "output": [
+            -11.205497741699219,
+            10.441486358642578
+        ]
+    },
+    "model.layers.11.self_attn.qk_bmm": {
+        "input": [
+            -10.428231239318848,
+            10.510344505310059
+        ],
+        "input2": [
+            -22.121395111083984,
+            19.97528839111328
+        ],
+        "output": [
+            -381.7677917480469,
+            238.34701538085938
+        ]
+    },
+    "model.layers.11.self_attn.v_proj": {
+        "output": [
+            -1.1099989414215088,
+            1.2887275218963623
+        ]
+    },
+    "model.layers.12.input_layernorm": {
+        "input": [
+            -99.4482650756836,
+            11.078857421875
+        ],
+        "output": [
+            -1.569658875465393,
+            1.8513926267623901
+        ]
+    },
+    "model.layers.12.mlp.act_fn": {
+        "input2": [
+            2.2228719842587452e-07,
+            0.9314825534820557
+        ],
+        "output": [
+            -0.2631029188632965,
+            6.441186904907227
+        ]
+    },
+    "model.layers.12.mlp.w1": {
+        "output": [
+            -3.6479241847991943,
+            3.3462159633636475
+        ]
+    },
+    "model.layers.12.mlp.w2": {
+        "input": [
+            -0.4353678822517395,
+            0.3869936466217041
+        ],
+        "output": [
+            -1.3589602708816528,
+            1.455013632774353
+        ]
+    },
+    "model.layers.12.mlp.w3": {
+        "output": [
+            -0.8044908046722412,
+            0.5105422735214233
+        ]
+    },
+    "model.layers.12.post_attention_layernorm": {
+        "input": [
+            -62.470062255859375,
+            6.949943542480469
+        ],
+        "output": [
+            -1.0635490417480469,
+            1.0388154983520508
+        ]
+    },
+    "model.layers.12.self_attn.k_proj": {
+        "output": [
+            -21.62252426147461,
+            17.76136016845703
+        ]
+    },
+    "model.layers.12.self_attn.o_proj": {
+        "output": [
+            -0.8174425363540649,
+            0.9816339015960693
+        ]
+    },
+    "model.layers.12.self_attn.pv_bmm": {
+        "input": [
+            0.0,
+            6.8579325675964355
+        ],
+        "input2": [
+            -1.3389040231704712,
+            1.4144874811172485
+        ],
+        "output": [
+            -0.7504150867462158,
+            0.6463429927825928
+        ]
+    },
+    "model.layers.12.self_attn.q_proj": {
+        "output": [
+            -7.999295234680176,
+            9.738272666931152
+        ]
+    },
+    "model.layers.12.self_attn.qk_bmm": {
+        "input": [
+            -7.916897296905518,
+            9.486627578735352
+        ],
+        "input2": [
+            -21.433029174804688,
+            17.886558532714844
+        ],
+        "output": [
+            -259.88922119140625,
+            216.72589111328125
+        ]
+    },
+    "model.layers.12.self_attn.v_proj": {
+        "output": [
+            -1.3148822784423828,
+            1.3891096115112305
+        ]
+    },
+    "model.layers.13.input_layernorm": {
+        "input": [
+            -86.26165771484375,
+            9.588691711425781
+        ],
+        "output": [
+            -1.649336576461792,
+            1.9763603210449219
+        ]
+    },
+    "model.layers.13.mlp.act_fn": {
+        "input2": [
+            2.544876906540594e-06,
+            0.9145498871803284
+        ],
+        "output": [
+            -0.2592918276786804,
+            7.993622779846191
+        ]
+    },
+    "model.layers.13.mlp.w1": {
+        "output": [
+            -5.687346458435059,
+            5.135588645935059
+        ]
+    },
+    "model.layers.13.mlp.w2": {
+        "input": [
+            -0.5235582590103149,
+            0.4653850793838501
+        ],
+        "output": [
+            -1.4153391122817993,
+            1.788828730583191
+        ]
+    },
+    "model.layers.13.mlp.w3": {
+        "output": [
+            -0.7486878633499146,
+            1.123031735420227
+        ]
+    },
+    "model.layers.13.post_attention_layernorm": {
+        "input": [
+            -63.23237609863281,
+            7.0157012939453125
+        ],
+        "output": [
+            -0.8964369297027588,
+            1.1264958381652832
+        ]
+    },
+    "model.layers.13.self_attn.k_proj": {
+        "output": [
+            -18.75926971435547,
+            22.478782653808594
+        ]
+    },
+    "model.layers.13.self_attn.o_proj": {
+        "output": [
+            -0.9660946130752563,
+            1.3633023500442505
+        ]
+    },
+    "model.layers.13.self_attn.pv_bmm": {
+        "input": [
+            0.0,
+            14.002142906188965
+        ],
+        "input2": [
+            -1.2294055223464966,
+            1.3193620443344116
+        ],
+        "output": [
+            -0.8531197309494019,
+            0.7348039150238037
+        ]
+    },
+    "model.layers.13.self_attn.q_proj": {
+        "output": [
+            -8.40859603881836,
+            10.566553115844727
+        ]
+    },
+    "model.layers.13.self_attn.qk_bmm": {
+        "input": [
+            -9.85166072845459,
+            9.03686237335205
+        ],
+        "input2": [
+            -18.746200561523438,
+            22.11090087890625
+        ],
+        "output": [
+            -304.88323974609375,
+            275.91217041015625
+        ]
+    },
+    "model.layers.13.self_attn.v_proj": {
+        "output": [
+            -1.229308843612671,
+            1.319258451461792
+        ]
+    },
+    "model.layers.14.input_layernorm": {
+        "input": [
+            -92.7020492553711,
+            10.2801513671875
+        ],
+        "output": [
+            -1.568450927734375,
+            2.1694462299346924
+        ]
+    },
+    "model.layers.14.mlp.act_fn": {
+        "input2": [
+            6.2880517361918464e-06,
+            0.9631829261779785
+        ],
+        "output": [
+            -0.2625121474266052,
+            6.425864219665527
+        ]
+    },
+    "model.layers.14.mlp.w1": {
+        "output": [
+            -3.615870475769043,
+            3.3168134689331055
+        ]
+    },
+    "model.layers.14.mlp.w2": {
+        "input": [
+            -0.854144811630249,
+            0.49869322776794434
+        ],
+        "output": [
+            -2.835049867630005,
+            2.239513635635376
+        ]
+    },
+    "model.layers.14.mlp.w3": {
+        "output": [
+            -1.0184581279754639,
+            1.0759518146514893
+        ]
+    },
+    "model.layers.14.post_attention_layernorm": {
+        "input": [
+            -62.98443603515625,
+            6.968025207519531
+        ],
+        "output": [
+            -0.8999509811401367,
+            1.0614806413650513
+        ]
+    },
+    "model.layers.14.self_attn.k_proj": {
+        "output": [
+            -15.748926162719727,
+            20.759946823120117
+        ]
+    },
+    "model.layers.14.self_attn.o_proj": {
+        "output": [
+            -1.1212328672409058,
+            1.5860103368759155
+        ]
+    },
+    "model.layers.14.self_attn.pv_bmm": {
+        "input": [
+            0.0,
+            25.853843688964844
+        ],
+        "input2": [
+            -1.298612117767334,
+            1.2684118747711182
+        ],
+        "output": [
+            -0.9813904166221619,
+            1.0367913246154785
+        ]
+    },
+    "model.layers.14.self_attn.q_proj": {
+        "output": [
+            -7.34971284866333,
+            11.581365585327148
+        ]
+    },
+    "model.layers.14.self_attn.qk_bmm": {
+        "input": [
+            -12.523106575012207,
+            10.125065803527832
+        ],
+        "input2": [
+            -21.095430374145508,
+            20.93062400817871
+        ],
+        "output": [
+            -370.3804626464844,
+            339.1870422363281
+        ]
+    },
+    "model.layers.14.self_attn.v_proj": {
+        "output": [
+            -1.2987051010131836,
+            1.2685027122497559
+        ]
+    },
+    "model.layers.15.input_layernorm": {
+        "input": [
+            -96.00485229492188,
+            10.613883972167969
+        ],
+        "output": [
+            -1.5501868724822998,
+            1.7997932434082031
+        ]
+    },
+    "model.layers.15.mlp.act_fn": {
+        "input2": [
+            1.4850113529973896e-06,
+            0.9971228241920471
+        ],
+        "output": [
+            -0.2568572461605072,
+            9.069701194763184
+        ]
+    },
+    "model.layers.15.mlp.w1": {
+        "output": [
+            -4.972715377807617,
+            5.011870384216309
+        ]
+    },
+    "model.layers.15.mlp.w2": {
+        "input": [
+            -0.5734550952911377,
+            0.7439417839050293
+        ],
+        "output": [
+            -2.318004608154297,
+            2.227762222290039
+        ]
+    },
+    "model.layers.15.mlp.w3": {
+        "output": [
+            -0.6860116124153137,
+            0.545910656452179
+        ]
+    },
+    "model.layers.15.post_attention_layernorm": {
+        "input": [
+            -49.25102996826172,
+            5.433860778808594
+        ],
+        "output": [
+            -0.9355494976043701,
+            0.9282405376434326
+        ]
+    },
+    "model.layers.15.self_attn.k_proj": {
+        "output": [
+            -18.496917724609375,
+            17.78549575805664
+        ]
+    },
+    "model.layers.15.self_attn.o_proj": {
+        "output": [
+            -1.700047492980957,
+            1.5626873970031738
+        ]
+    },
+    "model.layers.15.self_attn.pv_bmm": {
+        "input": [
+            0.0,
+            17.365955352783203
+        ],
+        "input2": [
+            -1.4967215061187744,
+            1.2101151943206787
+        ],
+        "output": [
+            -1.2445505857467651,
+            0.9747527837753296
+        ]
+    },
+    "model.layers.15.self_attn.q_proj": {
+        "output": [
+            -12.66657829284668,
+            15.178054809570312
+        ]
+    },
+    "model.layers.15.self_attn.qk_bmm": {
+        "input": [
+            -13.573946952819824,
+            13.897137641906738
+        ],
+        "input2": [
+            -21.92919921875,
+            17.450702667236328
+        ],
+        "output": [
+            -510.9229431152344,
+            232.58938598632812
+        ]
+    },
+    "model.layers.15.self_attn.v_proj": {
+        "output": [
+            -1.496742606163025,
+            1.2101324796676636
+        ]
+    },
+    "model.layers.16.input_layernorm": {
+        "input": [
+            -100.52581787109375,
+            11.0853271484375
+        ],
+        "output": [
+            -1.5624299049377441,
+            1.8722219467163086
+        ]
+    },
+    "model.layers.16.mlp.act_fn": {
+        "input2": [
+            1.0168923836317845e-06,
+            0.9851000905036926
+        ],
+        "output": [
+            -0.2558925151824951,
+            10.573112487792969
+        ]
+    },
+    "model.layers.16.mlp.w1": {
+        "output": [
+            -4.58713960647583,
+            6.344828128814697
+        ]
+    },
+    "model.layers.16.mlp.w2": {
+        "input": [
+            -0.9895568490028381,
+            0.8258172869682312
+        ],
+        "output": [
+            -2.62292742729187,
+            3.516347646713257
+        ]
+    },
+    "model.layers.16.mlp.w3": {
+        "output": [
+            -0.651694118976593,
+            0.710453450679779
+        ]
+    },
+    "model.layers.16.post_attention_layernorm": {
+        "input": [
+            -62.668067932128906,
+            6.895301818847656
+        ],
+        "output": [
+            -0.9683569073677063,
+            1.0723953247070312
+        ]
+    },
+    "model.layers.16.self_attn.k_proj": {
+        "output": [
+            -19.975080490112305,
+            19.20680809020996
+        ]
+    },
+    "model.layers.16.self_attn.o_proj": {
+        "output": [
+            -1.0730109214782715,
+            0.9763514995574951
+        ]
+    },
+    "model.layers.16.self_attn.pv_bmm": {
+        "input": [
+            0.0,
+            10.039031028747559
+        ],
+        "input2": [
+            -1.5520944595336914,
+            1.1964061260223389
+        ],
+        "output": [
+            -1.0620307922363281,
+            0.9147418737411499
+        ]
+    },
+    "model.layers.16.self_attn.q_proj": {
+        "output": [
+            -9.887508392333984,
+            10.283008575439453
+        ]
+    },
+    "model.layers.16.self_attn.qk_bmm": {
+        "input": [
+            -9.462581634521484,
+            10.154966354370117
+        ],
+        "input2": [
+            -19.422739028930664,
+            19.575674057006836
+        ],
+        "output": [
+            -327.813720703125,
+            297.045166015625
+        ]
+    },
+    "model.layers.16.self_attn.v_proj": {
+        "output": [
+            -1.5520508289337158,
+            1.1963725090026855
+        ]
+    },
+    "model.layers.17.input_layernorm": {
+        "input": [
+            -69.5985107421875,
+            7.65130615234375
+        ],
+        "output": [
+            -1.562252163887024,
+            1.9631842374801636
+        ]
+    },
+    "model.layers.17.mlp.act_fn": {
+        "input2": [
+            3.43927308676939e-06,
+            0.9986145496368408
+        ],
+        "output": [
+            -0.2538253664970398,
+            10.493779182434082
+        ]
+    },
+    "model.layers.17.mlp.w1": {
+        "output": [
+            -8.031157493591309,
+            7.366927146911621
+        ]
+    },
+    "model.layers.17.mlp.w2": {
+        "input": [
+            -0.7215433716773987,
+            1.100175142288208
+        ],
+        "output": [
+            -1.9865412712097168,
+            2.7032275199890137
+        ]
+    },
+    "model.layers.17.mlp.w3": {
+        "output": [
+            -0.8852017521858215,
+            0.6933049559593201
+        ]
+    },
+    "model.layers.17.post_attention_layernorm": {
+        "input": [
+            -60.717594146728516,
+            6.662433624267578
+        ],
+        "output": [
+            -1.0898340940475464,
+            0.8811424970626831
+        ]
+    },
+    "model.layers.17.self_attn.k_proj": {
+        "output": [
+            -17.243209838867188,
+            20.019657135009766
+        ]
+    },
+    "model.layers.17.self_attn.o_proj": {
+        "output": [
+            -1.8149468898773193,
+            1.7124121189117432
+        ]
+    },
+    "model.layers.17.self_attn.pv_bmm": {
+        "input": [
+            -1.9625843172832447e-09,
+            24.50324058532715
+        ],
+        "input2": [
+            -1.8348536491394043,
+            1.6309809684753418
+        ],
+        "output": [
+            -1.139207124710083,
+            1.0449869632720947
+        ]
+    },
+    "model.layers.17.self_attn.q_proj": {
+        "output": [
+            -11.556499481201172,
+            10.272443771362305
+        ]
+    },
+    "model.layers.17.self_attn.qk_bmm": {
+        "input": [
+            -9.140716552734375,
+            11.486564636230469
+        ],
+        "input2": [
+            -19.73405647277832,
+            20.20391273498535
+        ],
+        "output": [
+            -374.51507568359375,
+            302.01531982421875
+        ]
+    },
+    "model.layers.17.self_attn.v_proj": {
+        "output": [
+            -1.8348592519760132,
+            1.6309860944747925
+        ]
+    },
+    "model.layers.18.input_layernorm": {
+        "input": [
+            -99.9640121459961,
+            10.972625732421875
+        ],
+        "output": [
+            -1.8908522129058838,
+            2.1609737873077393
+        ]
+    },
+    "model.layers.18.mlp.act_fn": {
+        "input2": [
+            2.1923647182120476e-06,
+            0.9952065944671631
+        ],
+        "output": [
+            -0.2591128349304199,
+            9.149469375610352
+        ]
+    },
+    "model.layers.18.mlp.w1": {
+        "output": [
+            -4.569403171539307,
+            5.83414888381958
+        ]
+    },
+    "model.layers.18.mlp.w2": {
+        "input": [
+            -1.471362829208374,
+            1.2874424457550049
+        ],
+        "output": [
+            -1.6179473400115967,
+            2.5631320476531982
+        ]
+    },
+    "model.layers.18.mlp.w3": {
+        "output": [
+            -0.9652486443519592,
+            1.1750853061676025
+        ]
+    },
+    "model.layers.18.post_attention_layernorm": {
+        "input": [
+            -81.42882537841797,
+            8.924331665039062
+        ],
+        "output": [
+            -1.0480235815048218,
+            0.9463497400283813
+        ]
+    },
+    "model.layers.18.self_attn.k_proj": {
+        "output": [
+            -20.276676177978516,
+            13.96539306640625
+        ]
+    },
+    "model.layers.18.self_attn.o_proj": {
+        "output": [
+            -1.4689831733703613,
+            3.1518197059631348
+        ]
+    },
+    "model.layers.18.self_attn.pv_bmm": {
+        "input": [
+            -2.13810147364768e-09,
+            9.233264923095703
+        ],
+        "input2": [
+            -2.1445376873016357,
+            2.1277835369110107
+        ],
+        "output": [
+            -1.4730726480484009,
+            1.3943589925765991
+        ]
+    },
+    "model.layers.18.self_attn.q_proj": {
+        "output": [
+            -11.622716903686523,
+            11.89944839477539
+        ]
+    },
+    "model.layers.18.self_attn.qk_bmm": {
+        "input": [
+            -10.726187705993652,
+            11.693303108215332
+        ],
+        "input2": [
+            -18.65675163269043,
+            17.384702682495117
+        ],
+        "output": [
+            -323.7893371582031,
+            281.9984436035156
+        ]
+    },
+    "model.layers.18.self_attn.v_proj": {
+        "output": [
+            -2.1445248126983643,
+            2.1277706623077393
+        ]
+    },
+    "model.layers.19.input_layernorm": {
+        "input": [
+            -78.49484252929688,
+            8.620475769042969
+        ],
+        "output": [
+            -1.798056960105896,
+            1.8699792623519897
+        ]
+    },
+    "model.layers.19.mlp.act_fn": {
+        "input2": [
+            1.7838705446138192e-07,
+            1.007856011390686
+        ],
+        "output": [
+            -0.2515661120414734,
+            12.509735107421875
+        ]
+    },
+    "model.layers.19.mlp.w1": {
+        "output": [
+            -7.22218656539917,
+            8.253927230834961
+        ]
+    },
+    "model.layers.19.mlp.w2": {
+        "input": [
+            -1.2253239154815674,
+            1.445253849029541
+        ],
+        "output": [
+            -4.075857639312744,
+            5.675578594207764
+        ]
+    },
+    "model.layers.19.mlp.w3": {
+        "output": [
+            -0.8933815360069275,
+            0.7455558180809021
+        ]
+    },
+    "model.layers.19.post_attention_layernorm": {
+        "input": [
+            -105.57499694824219,
+            11.590507507324219
+        ],
+        "output": [
+            -1.3605623245239258,
+            0.863433837890625
+        ]
+    },
+    "model.layers.19.self_attn.k_proj": {
+        "output": [
+            -21.901290893554688,
+            20.40802001953125
+        ]
+    },
+    "model.layers.19.self_attn.o_proj": {
+        "output": [
+            -1.9629877805709839,
+            1.8841489553451538
+        ]
+    },
+    "model.layers.19.self_attn.pv_bmm": {
+        "input": [
+            -6.853270173579062e-10,
+            21.860992431640625
+        ],
+        "input2": [
+            -2.382417678833008,
+            2.4391417503356934
+        ],
+        "output": [
+            -1.411903738975525,
+            1.1782792806625366
+        ]
+    },
+    "model.layers.19.self_attn.q_proj": {
+        "output": [
+            -15.740455627441406,
+            13.135919570922852
+        ]
+    },
+    "model.layers.19.self_attn.qk_bmm": {
+        "input": [
+            -17.215229034423828,
+            15.545093536376953
+        ],
+        "input2": [
+            -20.727087020874023,
+            19.313875198364258
+        ],
+        "output": [
+            -431.6451721191406,
+            358.5186462402344
+        ]
+    },
+    "model.layers.19.self_attn.v_proj": {
+        "output": [
+            -2.3823821544647217,
+            2.439105272293091
+        ]
+    },
+    "model.layers.2.input_layernorm": {
+        "input": [
+            -0.8590171933174133,
+            1.0888631343841553
+        ],
+        "output": [
+            -1.7529939413070679,
+            1.168662667274475
+        ]
+    },
+    "model.layers.2.mlp.act_fn": {
+        "input2": [
+            3.966258191212546e-06,
+            0.9987732768058777
+        ],
+        "output": [
+            -0.18402370810508728,
+            11.531486511230469
+        ]
+    },
+    "model.layers.2.mlp.w1": {
+        "output": [
+            -19.380216598510742,
+            14.468793869018555
+        ]
+    },
+    "model.layers.2.mlp.w2": {
+        "input": [
+            -0.6558618545532227,
+            8.63491439819336
+        ],
+        "output": [
+            -75.92266082763672,
+            11.691207885742188
+        ]
+    },
+    "model.layers.2.mlp.w3": {
+        "output": [
+            -9.166142463684082,
+            2.6387386322021484
+        ]
+    },
+    "model.layers.2.post_attention_layernorm": {
+        "input": [
+            -0.7533947229385376,
+            0.8142738342285156
+        ],
+        "output": [
+            -0.4843924641609192,
+            0.5449416041374207
+        ]
+    },
+    "model.layers.2.self_attn.k_proj": {
+        "output": [
+            -9.543099403381348,
+            10.241374015808105
+        ]
+    },
+    "model.layers.2.self_attn.o_proj": {
+        "output": [
+            -0.726354718208313,
+            0.5078719854354858
+        ]
+    },
+    "model.layers.2.self_attn.pv_bmm": {
+        "input": [
+            -6.111011696674495e-11,
+            1.5878328084945679
+        ],
+        "input2": [
+            -0.338035523891449,
+            0.36276984214782715
+        ],
+        "output": [
+            -0.20621609687805176,
+            0.22130507230758667
+        ]
+    },
+    "model.layers.2.self_attn.q_proj": {
+        "output": [
+            -6.53659200668335,
+            5.810304164886475
+        ]
+    },
+    "model.layers.2.self_attn.qk_bmm": {
+        "input": [
+            -6.120059967041016,
+            6.072246551513672
+        ],
+        "input2": [
+            -10.258339881896973,
+            10.33911418914795
+        ],
+        "output": [
+            -225.0656280517578,
+            169.3107452392578
+        ]
+    },
+    "model.layers.2.self_attn.v_proj": {
+        "output": [
+            -0.33430781960487366,
+            0.35876932740211487
+        ]
+    },
+    "model.layers.20.input_layernorm": {
+        "input": [
+            -115.20829772949219,
+            12.693580627441406
+        ],
+        "output": [
+            -1.69486403465271,
+            1.5065457820892334
+        ]
+    },
+    "model.layers.20.mlp.act_fn": {
+        "input2": [
+            2.50033565407648e-07,
+            0.9959600567817688
+        ],
+        "output": [
+            -0.2553894817829132,
+            10.56139850616455
+        ]
+    },
+    "model.layers.20.mlp.w1": {
+        "output": [
+            -5.983047962188721,
+            7.761791706085205
+        ]
+    },
+    "model.layers.20.mlp.w2": {
+        "input": [
+            -7.271407604217529,
+            2.8058152198791504
+        ],
+        "output": [
+            -11.011977195739746,
+            6.784623146057129
+        ]
+    },
+    "model.layers.20.mlp.w3": {
+        "output": [
+            -3.3427953720092773,
+            2.2285304069519043
+        ]
+    },
+    "model.layers.20.post_attention_layernorm": {
+        "input": [
+            -113.40253448486328,
+            12.49249267578125
+        ],
+        "output": [
+            -1.8028979301452637,
+            0.9336435794830322
+        ]
+    },
+    "model.layers.20.self_attn.k_proj": {
+        "output": [
+            -21.391155242919922,
+            19.014358520507812
+        ]
+    },
+    "model.layers.20.self_attn.o_proj": {
+        "output": [
+            -2.64984393119812,
+            3.5715410709381104
+        ]
+    },
+    "model.layers.20.self_attn.pv_bmm": {
+        "input": [
+            -1.4543530824084883e-09,
+            17.021509170532227
+        ],
+        "input2": [
+            -2.695246458053589,
+            2.2139523029327393
+        ],
+        "output": [
+            -2.0278091430664062,
+            1.692272424697876
+        ]
+    },
+    "model.layers.20.self_attn.q_proj": {
+        "output": [
+            -17.26282501220703,
+            15.835071563720703
+        ]
+    },
+    "model.layers.20.self_attn.qk_bmm": {
+        "input": [
+            -15.574592590332031,
+            14.286468505859375
+        ],
+        "input2": [
+            -18.195837020874023,
+            19.527238845825195
+        ],
+        "output": [
+            -459.4617919921875,
+            400.9951171875
+        ]
+    },
+    "model.layers.20.self_attn.v_proj": {
+        "output": [
+            -2.695233106613159,
+            2.2139413356781006
+        ]
+    },
+    "model.layers.21.input_layernorm": {
+        "input": [
+            -146.54869079589844,
+            16.176971435546875
+        ],
+        "output": [
+            -1.708757758140564,
+            1.6174501180648804
+        ]
+    },
+    "model.layers.21.mlp.act_fn": {
+        "input2": [
+            -8.81209771819158e-09,
+            0.9954389333724976
+        ],
+        "output": [
+            -0.26087066531181335,
+            13.050216674804688
+        ]
+    },
+    "model.layers.21.mlp.w1": {
+        "output": [
+            -107.37953186035156,
+            14.317276000976562
+        ]
+    },
+    "model.layers.21.mlp.w2": {
+        "input": [
+            -4.829046249389648,
+            10.758381843566895
+        ],
+        "output": [
+            -43.75098419189453,
+            143.9803466796875
+        ]
+    },
+    "model.layers.21.mlp.w3": {
+        "output": [
+            -7.738009452819824,
+            2.0302696228027344
+        ]
+    },
+    "model.layers.21.post_attention_layernorm": {
+        "input": [
+            -179.94740295410156,
+            22.532821655273438
+        ],
+        "output": [
+            -2.6346614360809326,
+            1.5907390117645264
+        ]
+    },
+    "model.layers.21.self_attn.k_proj": {
+        "output": [
+            -26.96712875366211,
+            25.128459930419922
+        ]
+    },
+    "model.layers.21.self_attn.o_proj": {
+        "output": [
+            -6.288361072540283,
+            10.057985305786133
+        ]
+    },
+    "model.layers.21.self_attn.pv_bmm": {
+        "input": [
+            -2.280847288815835e-09,
+            7.910551071166992
+        ],
+        "input2": [
+            -4.1691460609436035,
+            3.3707995414733887
+        ],
+        "output": [
+            -3.265413761138916,
+            2.725093364715576
+        ]
+    },
+    "model.layers.21.self_attn.q_proj": {
+        "output": [
+            -15.797935485839844,
+            16.689754486083984
+        ]
+    },
+    "model.layers.21.self_attn.qk_bmm": {
+        "input": [
+            -16.69371223449707,
+            16.825159072875977
+        ],
+        "input2": [
+            -24.006988525390625,
+            24.578582763671875
+        ],
+        "output": [
+            -675.0399780273438,
+            528.8992309570312
+        ]
+    },
+    "model.layers.21.self_attn.v_proj": {
+        "output": [
+            -4.104138374328613,
+            3.318239212036133
+        ]
+    },
+    "model.layers.3.input_layernorm": {
+        "input": [
+            -72.91954803466797,
+            11.20062255859375
+        ],
+        "output": [
+            -1.0544137954711914,
+            0.9825220108032227
+        ]
+    },
+    "model.layers.3.mlp.act_fn": {
+        "input2": [
+            0.0,
+            0.9181910157203674
+        ],
+        "output": [
+            -0.2546980381011963,
+            2.1507670879364014
+        ]
+    },
+    "model.layers.3.mlp.w1": {
+        "output": [
+            -2.0251128673553467,
+            1.6373252868652344
+        ]
+    },
+    "model.layers.3.mlp.w2": {
+        "input": [
+            -0.2622146010398865,
+            0.26427924633026123
+        ],
+        "output": [
+            -0.4150099754333496,
+            0.240339994430542
+        ]
+    },
+    "model.layers.3.mlp.w3": {
+        "output": [
+            -0.5215353965759277,
+            0.5596965551376343
+        ]
+    },
+    "model.layers.3.post_attention_layernorm": {
+        "input": [
+            -15.465083122253418,
+            2.37296199798584
+        ],
+        "output": [
+            -0.4020472466945648,
+            0.3408661186695099
+        ]
+    },
+    "model.layers.3.self_attn.k_proj": {
+        "output": [
+            -15.118288040161133,
+            10.582801818847656
+        ]
+    },
+    "model.layers.3.self_attn.o_proj": {
+        "output": [
+            -0.24997998774051666,
+            0.40536999702453613
+        ]
+    },
+    "model.layers.3.self_attn.pv_bmm": {
+        "input": [
+            -7.779653032891076e-10,
+            10.15169906616211
+        ],
+        "input2": [
+            -0.5302785634994507,
+            0.46399378776550293
+        ],
+        "output": [
+            -0.2814144492149353,
+            0.2462376356124878
+        ]
+    },
+    "model.layers.3.self_attn.q_proj": {
+        "output": [
+            -6.861732482910156,
+            7.025106430053711
+        ]
+    },
+    "model.layers.3.self_attn.qk_bmm": {
+        "input": [
+            -6.992506980895996,
+            7.272207260131836
+        ],
+        "input2": [
+            -15.041023254394531,
+            14.462522506713867
+        ],
+        "output": [
+            -235.2082061767578,
+            207.6825714111328
+        ]
+    },
+    "model.layers.3.self_attn.v_proj": {
+        "output": [
+            -0.5320653319358826,
+            0.4655570983886719
+        ]
+    },
+    "model.layers.4.input_layernorm": {
+        "input": [
+            -69.28654479980469,
+            10.645393371582031
+        ],
+        "output": [
+            -1.145024061203003,
+            1.0339395999908447
+        ]
+    },
+    "model.layers.4.mlp.act_fn": {
+        "input2": [
+            6.099214715504786e-07,
+            0.8969005942344666
+        ],
+        "output": [
+            -0.2554253041744232,
+            3.815385580062866
+        ]
+    },
+    "model.layers.4.mlp.w1": {
+        "output": [
+            -3.362837076187134,
+            2.0645267963409424
+        ]
+    },
+    "model.layers.4.mlp.w2": {
+        "input": [
+            -0.2999441921710968,
+            0.2929687201976776
+        ],
+        "output": [
+            -0.8785357475280762,
+            0.474479079246521
+        ]
+    },
+    "model.layers.4.mlp.w3": {
+        "output": [
+            -0.5457059144973755,
+            0.7548081874847412
+        ]
+    },
+    "model.layers.4.post_attention_layernorm": {
+        "input": [
+            -25.324718475341797,
+            3.8873672485351562
+        ],
+        "output": [
+            -0.4368909001350403,
+            0.35887467861175537
+        ]
+    },
+    "model.layers.4.self_attn.k_proj": {
+        "output": [
+            -17.51902961730957,
+            9.888040542602539
+        ]
+    },
+    "model.layers.4.self_attn.o_proj": {
+        "output": [
+            -1.472687005996704,
+            0.4930652379989624
+        ]
+    },
+    "model.layers.4.self_attn.pv_bmm": {
+        "input": [
+            -9.67083635394772e-10,
+            3.160961151123047
+        ],
+        "input2": [
+            -0.6620192527770996,
+            0.5792667865753174
+        ],
+        "output": [
+            -0.42088180780410767,
+            0.3983919620513916
+        ]
+    },
+    "model.layers.4.self_attn.q_proj": {
+        "output": [
+            -8.15958309173584,
+            7.139636039733887
+        ]
+    },
+    "model.layers.4.self_attn.qk_bmm": {
+        "input": [
+            -7.773740768432617,
+            7.834951400756836
+        ],
+        "input2": [
+            -18.371265411376953,
+            17.944026947021484
+        ],
+        "output": [
+            -286.5303649902344,
+            196.67303466796875
+        ]
+    },
+    "model.layers.4.self_attn.v_proj": {
+        "output": [
+            -0.6622653603553772,
+            0.5794822573661804
+        ]
+    },
+    "model.layers.5.input_layernorm": {
+        "input": [
+            -72.35042572021484,
+            11.107322692871094
+        ],
+        "output": [
+            -1.012054443359375,
+            1.0041477680206299
+        ]
+    },
+    "model.layers.5.mlp.act_fn": {
+        "input2": [
+            3.7543460962297104e-07,
+            0.8639066815376282
+        ],
+        "output": [
+            -0.2671676576137543,
+            2.9769954681396484
+        ]
+    },
+    "model.layers.5.mlp.w1": {
+        "output": [
+            -2.161452531814575,
+            1.832535982131958
+        ]
+    },
+    "model.layers.5.mlp.w2": {
+        "input": [
+            -0.2855253517627716,
+            0.2660577595233917
+        ],
+        "output": [
+            -1.3505405187606812,
+            0.5793709754943848
+        ]
+    },
+    "model.layers.5.mlp.w3": {
+        "output": [
+            -0.7771786451339722,
+            0.5618791580200195
+        ]
+    },
+    "model.layers.5.post_attention_layernorm": {
+        "input": [
+            -16.259342193603516,
+            2.4912033081054688
+        ],
+        "output": [
+            -0.6607040166854858,
+            0.47767114639282227
+        ]
+    },
+    "model.layers.5.self_attn.k_proj": {
+        "output": [
+            -15.729736328125,
+            17.695953369140625
+        ]
+    },
+    "model.layers.5.self_attn.o_proj": {
+        "output": [
+            -0.7585533261299133,
+            0.7648529410362244
+        ]
+    },
+    "model.layers.5.self_attn.pv_bmm": {
+        "input": [
+            0.0,
+            4.858019828796387
+        ],
+        "input2": [
+            -1.006867527961731,
+            0.48587214946746826
+        ],
+        "output": [
+            -0.42437875270843506,
+            0.33770984411239624
+        ]
+    },
+    "model.layers.5.self_attn.q_proj": {
+        "output": [
+            -7.287756443023682,
+            7.699162006378174
+        ]
+    },
+    "model.layers.5.self_attn.qk_bmm": {
+        "input": [
+            -7.554513931274414,
+            7.1508378982543945
+        ],
+        "input2": [
+            -18.049354553222656,
+            16.043872833251953
+        ],
+        "output": [
+            -262.8944396972656,
+            207.77316284179688
+        ]
+    },
+    "model.layers.5.self_attn.v_proj": {
+        "output": [
+            -1.0068272352218628,
+            0.48585259914398193
+        ]
+    },
+    "model.layers.6.input_layernorm": {
+        "input": [
+            -76.28170013427734,
+            11.689178466796875
+        ],
+        "output": [
+            -1.3052244186401367,
+            1.2748703956604004
+        ]
+    },
+    "model.layers.6.mlp.act_fn": {
+        "input2": [
+            5.687860493708286e-07,
+            0.8548686504364014
+        ],
+        "output": [
+            -0.268370658159256,
+            3.5335166454315186
+        ]
+    },
+    "model.layers.6.mlp.w1": {
+        "output": [
+            -2.3736090660095215,
+            1.772078037261963
+        ]
+    },
+    "model.layers.6.mlp.w2": {
+        "input": [
+            -0.26148250699043274,
+            0.2762435972690582
+        ],
+        "output": [
+            -1.1666910648345947,
+            0.9592397212982178
+        ]
+    },
+    "model.layers.6.mlp.w3": {
+        "output": [
+            -0.5539140701293945,
+            0.6330446004867554
+        ]
+    },
+    "model.layers.6.post_attention_layernorm": {
+        "input": [
+            -44.39370346069336,
+            6.7775421142578125
+        ],
+        "output": [
+            -0.5560799241065979,
+            0.5263656973838806
+        ]
+    },
+    "model.layers.6.self_attn.k_proj": {
+        "output": [
+            -17.042301177978516,
+            18.578903198242188
+        ]
+    },
+    "model.layers.6.self_attn.o_proj": {
+        "output": [
+            -0.4106226861476898,
+            0.5218151807785034
+        ]
+    },
+    "model.layers.6.self_attn.pv_bmm": {
+        "input": [
+            0.0,
+            10.370061874389648
+        ],
+        "input2": [
+            -0.6833804845809937,
+            0.7449966669082642
+        ],
+        "output": [
+            -0.5550251603126526,
+            0.47056490182876587
+        ]
+    },
+    "model.layers.6.self_attn.q_proj": {
+        "output": [
+            -7.373525619506836,
+            8.426886558532715
+        ]
+    },
+    "model.layers.6.self_attn.qk_bmm": {
+        "input": [
+            -6.766021251678467,
+            8.368499755859375
+        ],
+        "input2": [
+            -18.750553131103516,
+            19.50057601928711
+        ],
+        "output": [
+            -284.78106689453125,
+            221.37881469726562
+        ]
+    },
+    "model.layers.6.self_attn.v_proj": {
+        "output": [
+            -0.6834059953689575,
+            0.745024561882019
+        ]
+    },
+    "model.layers.7.input_layernorm": {
+        "input": [
+            -76.0637435913086,
+            11.614128112792969
+        ],
+        "output": [
+            -1.5509907007217407,
+            1.56320321559906
+        ]
+    },
+    "model.layers.7.mlp.act_fn": {
+        "input2": [
+            -9.137278880189115e-07,
+            0.9197782278060913
+        ],
+        "output": [
+            -0.22567085921764374,
+            18.931161880493164
+        ]
+    },
+    "model.layers.7.mlp.w1": {
+        "output": [
+            -6.370095729827881,
+            20.25897789001465
+        ]
+    },
+    "model.layers.7.mlp.w2": {
+        "input": [
+            -10.818718910217285,
+            1.442495346069336
+        ],
+        "output": [
+            -68.0284194946289,
+            5.880210876464844
+        ]
+    },
+    "model.layers.7.mlp.w3": {
+        "output": [
+            -4.026743412017822,
+            3.9330978393554688
+        ]
+    },
+    "model.layers.7.post_attention_layernorm": {
+        "input": [
+            -44.210880279541016,
+            6.738880157470703
+        ],
+        "output": [
+            -1.1832901239395142,
+            0.6792961359024048
+        ]
+    },
+    "model.layers.7.self_attn.k_proj": {
+        "output": [
+            -17.08796501159668,
+            17.494821548461914
+        ]
+    },
+    "model.layers.7.self_attn.o_proj": {
+        "output": [
+            -0.3788287341594696,
+            0.7155746221542358
+        ]
+    },
+    "model.layers.7.self_attn.pv_bmm": {
+        "input": [
+            0.0,
+            14.152711868286133
+        ],
+        "input2": [
+            -0.9549614191055298,
+            0.9624807834625244
+        ],
+        "output": [
+            -0.523362398147583,
+            0.712354302406311
+        ]
+    },
+    "model.layers.7.self_attn.q_proj": {
+        "output": [
+            -9.399189949035645,
+            10.246659278869629
+        ]
+    },
+    "model.layers.7.self_attn.qk_bmm": {
+        "input": [
+            -9.251260757446289,
+            10.74087142944336
+        ],
+        "input2": [
+            -17.5736083984375,
+            16.897701263427734
+        ],
+        "output": [
+            -341.1612548828125,
+            198.99151611328125
+        ]
+    },
+    "model.layers.7.self_attn.v_proj": {
+        "output": [
+            -0.9533576965332031,
+            0.9608644247055054
+        ]
+    },
+    "model.layers.8.input_layernorm": {
+        "input": [
+            -61.41298294067383,
+            6.890247344970703
+        ],
+        "output": [
+            -2.4262712001800537,
+            2.645033597946167
+        ]
+    },
+    "model.layers.8.mlp.act_fn": {
+        "input2": [
+            2.2724009340890916e-06,
+            0.9171198010444641
+        ],
+        "output": [
+            -0.2660808563232422,
+            4.578679084777832
+        ]
+    },
+    "model.layers.8.mlp.w1": {
+        "output": [
+            -4.160639762878418,
+            2.4291930198669434
+        ]
+    },
+    "model.layers.8.mlp.w2": {
+        "input": [
+            -0.30407947301864624,
+            0.3113194704055786
+        ],
+        "output": [
+            -0.49675124883651733,
+            0.44169193506240845
+        ]
+    },
+    "model.layers.8.mlp.w3": {
+        "output": [
+            -0.8565957546234131,
+            0.6816571950912476
+        ]
+    },
+    "model.layers.8.post_attention_layernorm": {
+        "input": [
+            -39.070579528808594,
+            4.379852294921875
+        ],
+        "output": [
+            -0.64253169298172,
+            0.589389979839325
+        ]
+    },
+    "model.layers.8.self_attn.k_proj": {
+        "output": [
+            -23.870710372924805,
+            24.439062118530273
+        ]
+    },
+    "model.layers.8.self_attn.o_proj": {
+        "output": [
+            -1.288500428199768,
+            0.9605840444564819
+        ]
+    },
+    "model.layers.8.self_attn.pv_bmm": {
+        "input": [
+            -2.849586122621872e-10,
+            5.764626502990723
+        ],
+        "input2": [
+            -0.7795315980911255,
+            1.2283529043197632
+        ],
+        "output": [
+            -0.6425102353096008,
+            1.029327630996704
+        ]
+    },
+    "model.layers.8.self_attn.q_proj": {
+        "output": [
+            -9.715987205505371,
+            10.930485725402832
+        ]
+    },
+    "model.layers.8.self_attn.qk_bmm": {
+        "input": [
+            -11.523988723754883,
+            11.433958053588867
+        ],
+        "input2": [
+            -23.01451873779297,
+            28.01767349243164
+        ],
+        "output": [
+            -531.0772705078125,
+            249.6875
+        ]
+    },
+    "model.layers.8.self_attn.v_proj": {
+        "output": [
+            -0.77955162525177,
+            1.2283843755722046
+        ]
+    },
+    "model.layers.9.input_layernorm": {
+        "input": [
+            -63.642173767089844,
+            7.1283416748046875
+        ],
+        "output": [
+            -1.4341191053390503,
+            1.5881980657577515
+        ]
+    },
+    "model.layers.9.mlp.act_fn": {
+        "input2": [
+            3.249040446462459e-06,
+            0.9275291562080383
+        ],
+        "output": [
+            -0.2559678554534912,
+            6.990260124206543
+        ]
+    },
+    "model.layers.9.mlp.w1": {
+        "output": [
+            -2.845679521560669,
+            3.5196564197540283
+        ]
+    },
+    "model.layers.9.mlp.w2": {
+        "input": [
+            -0.31340545415878296,
+            0.35817772150039673
+        ],
+        "output": [
+            -1.1538662910461426,
+            0.8241255283355713
+        ]
+    },
+    "model.layers.9.mlp.w3": {
+        "output": [
+            -0.6430490612983704,
+            0.6687710881233215
+        ]
+    },
+    "model.layers.9.post_attention_layernorm": {
+        "input": [
+            -47.34988021850586,
+            5.296352386474609
+        ],
+        "output": [
+            -0.6652911901473999,
+            0.8494342565536499
+        ]
+    },
+    "model.layers.9.self_attn.k_proj": {
+        "output": [
+            -19.59954833984375,
+            18.552242279052734
+        ]
+    },
+    "model.layers.9.self_attn.o_proj": {
+        "output": [
+            -0.9600111246109009,
+            0.7467882633209229
+        ]
+    },
+    "model.layers.9.self_attn.pv_bmm": {
+        "input": [
+            0.0,
+            10.371491432189941
+        ],
+        "input2": [
+            -1.1789764165878296,
+            0.9838939905166626
+        ],
+        "output": [
+            -0.702292263507843,
+            0.6048941016197205
+        ]
+    },
+    "model.layers.9.self_attn.q_proj": {
+        "output": [
+            -7.073794841766357,
+            7.958018779754639
+        ]
+    },
+    "model.layers.9.self_attn.qk_bmm": {
+        "input": [
+            -8.201776504516602,
+            7.064304351806641
+        ],
+        "input2": [
+            -19.554767608642578,
+            18.802661895751953
+        ],
+        "output": [
+            -267.5766296386719,
+            236.26300048828125
+        ]
+    },
+    "model.layers.9.self_attn.v_proj": {
+        "output": [
+            -1.1789911985397339,
+            0.9839063882827759
+        ]
+    }
+}

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "checkpoints/hfmodels/llama-1.1b",
+  "architectures": [
+    "HFForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 2,
+  "head_dim": null,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "l2norm_as_rmsnorm": true,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "hfmodel",
+  "norm_class": "rmsnorm",
+  "normalize_embed": false,
+  "normalizie_embed": false,
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "num_linears_per_mlp": 3,
+  "num_local_experts": 1,
+  "output_router_logits": false,
+  "parallel_residual": false,
+  "partial_rotary_factor": 1.0,
+  "pretraining_tp": 1,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.0,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "shared_attention_norm": false,
+  "sliding_window": null,
+  "static_causal_mask": false,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "use_cache": true,
+  "use_matmul_as_module": true,
+  "use_megablocks": false,
+  "use_qkv_bias_only": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.0.dev0"
+}

log_rank0_1723678604.txt

@@ -0,0 +1,4 @@
+[2024-08-14 23:36:44 root] (mobilequant.py 132): INFO Namespace(hf_path='checkpoints/hfmodels/llama-1.1b', dtype='float32', output_dir='results/llama-1.1b-e2e-w4a8-s1024-e60', cache_dir='./cache', resume=None, calib_dataset='pile', nsamples=1024, seqlen=2048, act_dict_path='checkpoints/hfmodels/llama-1.1b/act_dict.json', override_qcfg_path='checkpoints/hfmodels/llama-1.1b/default_qcfg.json', weight_bitwidth=4, weight_group_size=-1, weight_is_per_channel=True, weight_is_symmetric=False, weight_is_dynamic=False, act_bitwidth=8, act_group_size=-1, act_is_per_channel=False, act_is_symmetric=False, act_is_dynamic=False, let=True, lwc=True, lrl=True, let_lr=0.001, lwc_lr=0.01, lrl_lr=1e-06, let_min_lr=0.0001, lwc_min_lr=0.001, lrl_min_lr=1e-07, wd=0, epochs=60, warmup_epochs=0, use_shift=False, aug_loss=False, deactive_amp=True, batch_size=1, num_fewshot=0, tasks='wikitext', mode='e2e', original_omniquant=False, cache_in_gpu=False, use_8bit_softmax_input=False, use_8bit_softmax_output=False, model_family='llama')
+[2024-08-14 23:37:00 root] (mobilequant.py 218): INFO === start quantization ===
+[2024-08-14 23:37:00 root] (mobilequant.py 224): INFO load calibration set from ./cache/dataloader_llama_pile_1024.cache
+[2024-08-14 23:37:00 root] (algorithm.py 588): INFO Starting ...

log_rank0_1723719542.txt

@@ -0,0 +1 @@
+[2024-08-15 10:59:02 root] (mobilequant.py 132): INFO Namespace(hf_path='checkpoints/hfmodels/llama-1.1b', dtype='float32', output_dir='results/llama-1.1b-e2e-w4a8-s1024-e60', cache_dir='./cache', resume=None, calib_dataset='pile', nsamples=1024, seqlen=2048, act_dict_path='checkpoints/hfmodels/llama-1.1b/act_dict.json', override_qcfg_path='checkpoints/hfmodels/llama-1.1b/default_qcfg.json', weight_bitwidth=4, weight_group_size=-1, weight_is_per_channel=True, weight_is_symmetric=False, weight_is_dynamic=False, act_bitwidth=8, act_group_size=-1, act_is_per_channel=False, act_is_symmetric=False, act_is_dynamic=False, let=True, lwc=True, lrl=True, let_lr=0.001, lwc_lr=0.01, lrl_lr=1e-06, let_min_lr=0.0001, lwc_min_lr=0.001, lrl_min_lr=1e-07, wd=0, epochs=60, warmup_epochs=0, use_shift=False, aug_loss=False, deactive_amp=True, batch_size=1, num_fewshot=0, tasks='wikitext', mode='e2e', original_omniquant=False, cache_in_gpu=False, use_8bit_softmax_input=False, use_8bit_softmax_output=False, model_family='llama')

log_rank0_1723719579.txt

@@ -0,0 +1,67 @@
+[2024-08-15 10:59:39 root] (mobilequant.py 132): INFO Namespace(hf_path='checkpoints/hfmodels/llama-1.1b', dtype='float32', output_dir='results/llama-1.1b-e2e-w4a8-s1024-e60', cache_dir='./cache', resume=None, calib_dataset='pile', nsamples=1024, seqlen=2048, act_dict_path='checkpoints/hfmodels/llama-1.1b/act_dict.json', override_qcfg_path='checkpoints/hfmodels/llama-1.1b/default_qcfg.json', weight_bitwidth=4, weight_group_size=-1, weight_is_per_channel=True, weight_is_symmetric=False, weight_is_dynamic=False, act_bitwidth=8, act_group_size=-1, act_is_per_channel=False, act_is_symmetric=False, act_is_dynamic=False, let=True, lwc=True, lrl=True, let_lr=0.001, lwc_lr=0.01, lrl_lr=1e-06, let_min_lr=0.0001, lwc_min_lr=0.001, lrl_min_lr=1e-07, wd=0, epochs=60, warmup_epochs=0, use_shift=False, aug_loss=False, deactive_amp=True, batch_size=1, num_fewshot=0, tasks='wikitext', mode='e2e', original_omniquant=False, cache_in_gpu=False, use_8bit_softmax_input=False, use_8bit_softmax_output=False, model_family='llama')
+[2024-08-15 10:59:56 root] (mobilequant.py 218): INFO === start quantization ===
+[2024-08-15 10:59:56 root] (mobilequant.py 224): INFO load calibration set from ./cache/dataloader_llama_pile_1024.cache
+[2024-08-15 10:59:56 root] (algorithm.py 588): INFO Starting ...
+[2024-08-15 11:30:25 root] (algorithm.py 759): INFO Epoch 0 loss:0.16898810863494873 norm:724.4014282226562 max memory_allocated 36890.91259765625 
+[2024-08-15 11:58:21 root] (algorithm.py 759): INFO Epoch 1 loss:0.10241444408893585 norm:251.3023681640625 max memory_allocated 36891.13525390625 
+[2024-08-15 12:26:29 root] (algorithm.py 759): INFO Epoch 2 loss:0.08263994753360748 norm:235.6741180419922 max memory_allocated 36891.13525390625 
+[2024-08-15 12:54:33 root] (algorithm.py 759): INFO Epoch 3 loss:0.07116106897592545 norm:112.66700744628906 max memory_allocated 36891.13525390625 
+[2024-08-15 13:22:30 root] (algorithm.py 759): INFO Epoch 4 loss:0.06350904703140259 norm:66.97445678710938 max memory_allocated 36891.13525390625 
+[2024-08-15 13:50:37 root] (algorithm.py 759): INFO Epoch 5 loss:0.059952475130558014 norm:16.105663299560547 max memory_allocated 36891.13525390625 
+[2024-08-15 14:18:44 root] (algorithm.py 759): INFO Epoch 6 loss:0.057945333421230316 norm:11.881877899169922 max memory_allocated 36891.13525390625 
+[2024-08-15 14:46:50 root] (algorithm.py 759): INFO Epoch 7 loss:0.05706916004419327 norm:5.32889461517334 max memory_allocated 36891.13525390625 
+[2024-08-15 15:14:55 root] (algorithm.py 759): INFO Epoch 8 loss:0.05636187642812729 norm:1.0679874420166016 max memory_allocated 36891.13525390625 
+[2024-08-15 15:43:02 root] (algorithm.py 759): INFO Epoch 9 loss:0.05589071661233902 norm:1.038902759552002 max memory_allocated 36891.13525390625 
+[2024-08-15 16:10:51 root] (algorithm.py 759): INFO Epoch 10 loss:0.05579143017530441 norm:1.06354820728302 max memory_allocated 36891.13525390625 
+[2024-08-15 16:38:56 root] (algorithm.py 759): INFO Epoch 11 loss:0.05525699630379677 norm:1.446141242980957 max memory_allocated 36891.13525390625 
+[2024-08-15 17:07:06 root] (algorithm.py 759): INFO Epoch 12 loss:0.055097781121730804 norm:0.983670711517334 max memory_allocated 36891.13525390625 
+[2024-08-15 17:35:09 root] (algorithm.py 759): INFO Epoch 13 loss:0.054827820509672165 norm:1.4448797702789307 max memory_allocated 36891.13525390625 
+[2024-08-15 18:03:07 root] (algorithm.py 759): INFO Epoch 14 loss:0.054530221968889236 norm:1.4780938625335693 max memory_allocated 36891.13525390625 
+[2024-08-15 18:30:57 root] (algorithm.py 759): INFO Epoch 15 loss:0.054305657744407654 norm:1.0362352132797241 max memory_allocated 36891.13525390625 
+[2024-08-15 18:58:56 root] (algorithm.py 759): INFO Epoch 16 loss:0.054355744272470474 norm:1.0153888463974 max memory_allocated 36891.13525390625 
+[2024-08-15 19:26:47 root] (algorithm.py 759): INFO Epoch 17 loss:0.05446964502334595 norm:1.0248713493347168 max memory_allocated 36891.13525390625 
+[2024-08-15 19:54:40 root] (algorithm.py 759): INFO Epoch 18 loss:0.0539342537522316 norm:1.194250226020813 max memory_allocated 36891.13525390625 
+[2024-08-15 20:22:35 root] (algorithm.py 759): INFO Epoch 19 loss:0.053713299334049225 norm:0.9865327477455139 max memory_allocated 36891.13525390625 
+[2024-08-15 20:50:24 root] (algorithm.py 759): INFO Epoch 20 loss:0.05385317653417587 norm:1.0266972780227661 max memory_allocated 36891.13525390625 
+[2024-08-15 21:18:13 root] (algorithm.py 759): INFO Epoch 21 loss:0.05353732407093048 norm:1.0620938539505005 max memory_allocated 36891.13525390625 
+[2024-08-15 21:46:01 root] (algorithm.py 759): INFO Epoch 22 loss:0.05349891632795334 norm:1.0582232475280762 max memory_allocated 36891.13525390625 
+[2024-08-15 22:14:02 root] (algorithm.py 759): INFO Epoch 23 loss:0.053362563252449036 norm:1.1380953788757324 max memory_allocated 36891.13525390625 
+[2024-08-15 22:42:11 root] (algorithm.py 759): INFO Epoch 24 loss:0.05297514796257019 norm:1.2292181253433228 max memory_allocated 36891.13525390625 
+[2024-08-15 23:10:15 root] (algorithm.py 759): INFO Epoch 25 loss:0.05299036204814911 norm:1.0634015798568726 max memory_allocated 36891.13525390625 
+[2024-08-15 23:38:17 root] (algorithm.py 759): INFO Epoch 26 loss:0.05270509421825409 norm:1.3303881883621216 max memory_allocated 36891.13525390625 
+[2024-08-16 00:06:20 root] (algorithm.py 759): INFO Epoch 27 loss:0.052736833691596985 norm:1.5433977842330933 max memory_allocated 36891.13525390625 
+[2024-08-16 00:34:25 root] (algorithm.py 759): INFO Epoch 28 loss:0.05256371200084686 norm:1.048864722251892 max memory_allocated 36891.13525390625 
+[2024-08-16 01:02:29 root] (algorithm.py 759): INFO Epoch 29 loss:0.05262676253914833 norm:1.2224853038787842 max memory_allocated 36891.13525390625 
+[2024-08-16 01:30:23 root] (algorithm.py 759): INFO Epoch 30 loss:0.052359651774168015 norm:1.1281168460845947 max memory_allocated 36891.13525390625 
+[2024-08-16 01:58:15 root] (algorithm.py 759): INFO Epoch 31 loss:0.0523049496114254 norm:1.1409447193145752 max memory_allocated 36891.13525390625 
+[2024-08-16 02:26:12 root] (algorithm.py 759): INFO Epoch 32 loss:0.05235399305820465 norm:1.0354962348937988 max memory_allocated 36891.13525390625 
+[2024-08-16 02:54:10 root] (algorithm.py 759): INFO Epoch 33 loss:0.05214683711528778 norm:1.144018530845642 max memory_allocated 36891.13525390625 
+[2024-08-16 03:22:07 root] (algorithm.py 759): INFO Epoch 34 loss:0.05229134485125542 norm:1.271885871887207 max memory_allocated 36891.13525390625 
+[2024-08-16 03:50:07 root] (algorithm.py 759): INFO Epoch 35 loss:0.05219335854053497 norm:1.4318875074386597 max memory_allocated 36891.13525390625 
+[2024-08-16 04:18:08 root] (algorithm.py 759): INFO Epoch 36 loss:0.05219259485602379 norm:0.9434258341789246 max memory_allocated 36891.13525390625 
+[2024-08-16 04:46:09 root] (algorithm.py 759): INFO Epoch 37 loss:0.052059486508369446 norm:0.9330815076828003 max memory_allocated 36891.13525390625 
+[2024-08-16 05:14:07 root] (algorithm.py 759): INFO Epoch 38 loss:0.05192422866821289 norm:0.987342119216919 max memory_allocated 36891.13525390625 
+[2024-08-16 05:42:06 root] (algorithm.py 759): INFO Epoch 39 loss:0.05179840326309204 norm:1.1419882774353027 max memory_allocated 36891.13525390625 
+[2024-08-16 06:10:05 root] (algorithm.py 759): INFO Epoch 40 loss:0.051746975630521774 norm:1.0171027183532715 max memory_allocated 36891.13525390625 
+[2024-08-16 06:38:06 root] (algorithm.py 759): INFO Epoch 41 loss:0.05169394239783287 norm:1.0280253887176514 max memory_allocated 36891.13525390625 
+[2024-08-16 07:06:09 root] (algorithm.py 759): INFO Epoch 42 loss:0.051593586802482605 norm:1.1187621355056763 max memory_allocated 36891.13525390625 
+[2024-08-16 07:34:12 root] (algorithm.py 759): INFO Epoch 43 loss:0.05150768905878067 norm:1.1804970502853394 max memory_allocated 36891.13525390625 
+[2024-08-16 08:02:15 root] (algorithm.py 759): INFO Epoch 44 loss:0.05163747817277908 norm:1.4566706418991089 max memory_allocated 36891.13525390625 
+[2024-08-16 08:30:19 root] (algorithm.py 759): INFO Epoch 45 loss:0.05175628885626793 norm:1.216122031211853 max memory_allocated 36891.13525390625 
+[2024-08-16 08:58:25 root] (algorithm.py 759): INFO Epoch 46 loss:0.05169924348592758 norm:1.1023517847061157 max memory_allocated 36891.13525390625 
+[2024-08-16 09:26:30 root] (algorithm.py 759): INFO Epoch 47 loss:0.05157414451241493 norm:1.219941258430481 max memory_allocated 36891.13525390625 
+[2024-08-16 09:54:36 root] (algorithm.py 759): INFO Epoch 48 loss:0.05150758847594261 norm:1.1944962739944458 max memory_allocated 36891.13525390625 
+[2024-08-16 10:22:42 root] (algorithm.py 759): INFO Epoch 49 loss:0.05145324766635895 norm:1.2031457424163818 max memory_allocated 36891.13525390625 
+[2024-08-16 10:50:47 root] (algorithm.py 759): INFO Epoch 50 loss:0.05142810940742493 norm:1.1219770908355713 max memory_allocated 36891.13525390625 
+[2024-08-16 11:18:52 root] (algorithm.py 759): INFO Epoch 51 loss:0.051323194056749344 norm:1.4382984638214111 max memory_allocated 36891.13525390625 
+[2024-08-16 11:46:59 root] (algorithm.py 759): INFO Epoch 52 loss:0.051315683871507645 norm:1.1687315702438354 max memory_allocated 36891.13525390625 
+[2024-08-16 12:15:01 root] (algorithm.py 759): INFO Epoch 53 loss:0.05137581378221512 norm:1.1915956735610962 max memory_allocated 36891.13525390625 
+[2024-08-16 12:43:00 root] (algorithm.py 759): INFO Epoch 54 loss:0.05133047327399254 norm:1.1390117406845093 max memory_allocated 36891.13525390625 
+[2024-08-16 13:10:59 root] (algorithm.py 759): INFO Epoch 55 loss:0.05128314346075058 norm:1.2405548095703125 max memory_allocated 36891.13525390625 
+[2024-08-16 13:39:05 root] (algorithm.py 759): INFO Epoch 56 loss:0.05143631994724274 norm:1.617008090019226 max memory_allocated 36891.13525390625 
+[2024-08-16 14:07:13 root] (algorithm.py 759): INFO Epoch 57 loss:0.05143939331173897 norm:2.7324397563934326 max memory_allocated 36891.13525390625 
+[2024-08-16 14:35:05 root] (algorithm.py 759): INFO Epoch 58 loss:0.051326800137758255 norm:2.896402597427368 max memory_allocated 36891.13525390625 
+[2024-08-16 15:02:53 root] (algorithm.py 759): INFO Epoch 59 loss:0.051287226378917694 norm:3.160975694656372 max memory_allocated 36891.13525390625 
+[2024-08-16 15:02:56 root] (mobilequant.py 233): INFO 100980.03111195564
+[2024-08-16 15:03:02 huggingface_hub.repocard] (repocard.py 107): WARNING Repo card metadata block was not found. Setting CardData to empty.
+[2024-08-16 15:05:02 root] (mobilequant.py 110): INFO {'results': {'wikitext': {'word_perplexity': 17.062256516925927, 'byte_perplexity': 1.6997966850296349, 'bits_per_byte': 0.7653621939858745}}, 'versions': {'wikitext': 1}, 'config': {'model': None, 'model_args': None, 'num_fewshot': 0, 'batch_size': 1, 'batch_sizes': [], 'device': None, 'no_cache': True, 'limit': None, 'bootstrap_iters': 100000, 'description_dict': None}}

model.embed_tokens.weight

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e66a081d1ef1eccc5bb068971888d442942ac2451ce238ab12bf17d40e113a1
+size 262144000