Synchronizing local compiler cache.
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +107 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-0.5B/5f1a2111604ccf1723b9.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-0.5B/fa9a9e1f6a33e2f83027.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-1.5B/842677cbddc5f7674b52.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-1.5B/9c442126814a181b6b08.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-14B/4d344eef5c363f6851d8.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-14B/703843f253e4eab07ed2.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-32B-Instruct/903c83b2adc41caef7b2.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-32B-Instruct/97fad9b9d7ca5c477782.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-72B-Instruct/058a352bb7d4c0e8af68.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-72B-Instruct/090bc30b9eaa90b56de8.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-72B-Instruct/355ef61d7e21c9ca4dfd.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-72B-Instruct/5feb3df570ed48ce4ef9.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-72B-Instruct/62d648e67c1df9861c81.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-72B-Instruct/b0090f8c5a66f58c402e.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/2104c2569f8076fd08e8.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/2bdd504102100c9d1a90.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/8be3a002e240a4aad032.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/e9d0ac3eb014579d6b51.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/febd5daac4e51196a9ec.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-Coder-32B-Instruct/39b69bbd54bed005e329.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-Coder-7B-Instruct/c19875bdff42cd555d4c.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-Math-7B-Instruct/73abe935a165dd5a8d7d.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/4538babd01182da34f41.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/b40a794eff5ea470980f.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/cdbdbf737272e98ae974.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/gpt2/gpt2/aadac442fccfdd730bb5.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/gpt2/hf-internal-testing/tiny-random-gpt2/1f8668afaa87da7a4bc8.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/gpt2/hf-internal-testing/tiny-random-gpt2/af0ef68e4ec57e23cab5.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/gpt2/hf-internal-testing/tiny-random-gpt2/e0c5534b610fbfb22b6e.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/llama/llamafactory/tiny-random-Llama-3/1ef3929e28ba91cc3cc6.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/llama/llamafactory/tiny-random-Llama-3/71ec0a49c3535c618d03.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/llama/llamafactory/tiny-random-Llama-3/eb3f26aa23141bff2292.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/7d2df9c19098ee676fa8.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/ac0287246ef4575f8b78.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/af0f1b79454574c744eb.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/mixtral/dacorvo/Mixtral-tiny/8dde518ab8e435c4c830.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/mixtral/dacorvo/Mixtral-tiny/9ac32cae9a1e9b72b9ed.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/mixtral/dacorvo/Mixtral-tiny/d777c911e955212a0132.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/93d7843b7abe79348924.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/b392ca0eec3368da72ec.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/f829b04255e2c75cd7c8.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/MODULE_0159cebf2bdd30fd3a27+39f12043/compile_flags.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/MODULE_0159cebf2bdd30fd3a27+39f12043/model.done +0 -0
- neuronxcc-2.15.143.0+e39249ad/MODULE_0159cebf2bdd30fd3a27+39f12043/model.hlo_module.pb +3 -0
- neuronxcc-2.15.143.0+e39249ad/MODULE_0159cebf2bdd30fd3a27+39f12043/model.neff +3 -0
- neuronxcc-2.15.143.0+e39249ad/MODULE_05887d2cc91ed79b4acc+39f12043/compile_flags.json +1 -0
- neuronxcc-2.15.143.0+e39249ad/MODULE_05887d2cc91ed79b4acc+39f12043/model.done +0 -0
- neuronxcc-2.15.143.0+e39249ad/MODULE_05887d2cc91ed79b4acc+39f12043/model.hlo_module.pb +3 -0
- neuronxcc-2.15.143.0+e39249ad/MODULE_05887d2cc91ed79b4acc+39f12043/model.neff +3 -0
.gitattributes
CHANGED
|
@@ -1337,3 +1337,110 @@ neuronxcc-2.15.143.0+e39249ad/MODULE_e5da7e4a5bee80b3a22a/unet/model.neuron filt
|
|
| 1337 |
neuronxcc-2.15.143.0+e39249ad/MODULE_e5da7e4a5bee80b3a22a/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 1338 |
neuronxcc-2.15.143.0+e39249ad/MODULE_e5da7e4a5bee80b3a22a/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 1339 |
neuronxcc-2.15.143.0+e39249ad/MODULE_e63ec966f940f9aac5ed+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1337 |
neuronxcc-2.15.143.0+e39249ad/MODULE_e5da7e4a5bee80b3a22a/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 1338 |
neuronxcc-2.15.143.0+e39249ad/MODULE_e5da7e4a5bee80b3a22a/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 1339 |
neuronxcc-2.15.143.0+e39249ad/MODULE_e63ec966f940f9aac5ed+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1340 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_0159cebf2bdd30fd3a27+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1341 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_05887d2cc91ed79b4acc+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1342 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_0b1b2ca56aec724cedf0+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1343 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_1093474e713312970c70+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1344 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_1402856c53fd57c1f269+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1345 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_15012bce164db408f76c+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1346 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_19508710902bacc178f4+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1347 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_1c5e2bca6d2a08e356c9+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1348 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_1da29785524fea1d5eb1+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1349 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_1ff9c96376b424d1b0c3+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1350 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_200e1fdf88ed805006b2+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1351 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_23e2e56387f2b7a67609+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1352 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_26a5181917a99c6440c2+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1353 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_31958ddae33067519c77+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1354 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_38e952fa2492adf691ff+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1355 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_395d6fa9734fb33b488a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1356 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_3d12da8df40d3b92f9e8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1357 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_3d233b92205d349fd51b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1358 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_3f4d142fee0aa97ae95f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1359 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_420e05adc25e62ff16f2+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1360 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_438055dff8c89c0e98dc+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1361 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_445d572321d7551de96d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1362 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_4d076c0c56a5768c4069+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1363 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_5093ab9ddab25bb9a8c6+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1364 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_5263f71385ed4e05d605+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1365 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_5425d7325a97f7a4932e+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1366 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_5628a59e526474f498d9+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1367 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_577ca4a419d665365921+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1368 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_57a5bd13163df1234547+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1369 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_5841037c256dff723d2b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1370 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_59be9cdd139133955871+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1371 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_5a8879e0903fec255916+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1372 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_5bba44dbf59b43b3d1f0+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1373 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_5d92b305ea13c18301f4+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1374 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_60c61b4f080d83463681+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1375 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_6158c090f65032e00f74+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1376 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_6402a35ae65f70f2e6b3+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1377 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_6411989b6eb15069d2ef+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1378 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_64fd1c875de8eac8f497+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1379 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_65c9007aa32dd35acac0+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1380 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_65ef5ce48d49cf19ab37+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1381 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_68922f07d27e29cb1bc0+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1382 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_692c2b4140606a11922e+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1383 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_698c4cfd6500b20d87fd+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1384 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_6e446bc9fb621acf17ec+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1385 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_7089c3d642130607440b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1386 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_71a6fdf74ae87fb07604+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1387 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_734af09fdf0599748b70+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1388 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_7509667fcd84787e8e39+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1389 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_7dff79b209c4936eccf6+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1390 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_7f495f1e5eab37e231f8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1391 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_80a0e5d4da88e851f021+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1392 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_822748c7e4759c0698fc+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1393 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_852b4e6d495459bee9e2+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1394 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_891c926fc39f5f557aa7+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1395 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_8e94f7f62a38ca9b2468+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1396 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_8eb7c7f43b1ddb9995d7+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1397 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_9044f94e3b63069f14ef+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1398 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_90d1600ea7397d047f5a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1399 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_96ee49931a38b70b8543+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1400 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_98231f8d3edd3dbf35c5+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1401 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_98773a4d5b572f0b4e19+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1402 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_9a1fc9ff17795f0f7cd3+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1403 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_9bf7d4560f134fd504aa+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1404 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_9c3a05bace15af5d38e1+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1405 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_9e2fc53aa459bd51819c+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1406 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_9e83eff284bc494306f8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1407 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_9f1c79cbf97904719c95+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1408 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_b6d1e63d522c57afb5b8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1409 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_b72685fd24107a1343ae+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1410 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_b7bb49e658395a9bbb2e+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1411 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_b90b7672699efbad4311+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1412 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_c31a129b6bf5d507b474+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1413 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_c44a698b067b57c54462+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1414 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_c562f9a17a67f8deef71+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1415 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_c59ef31c53c35de18bfa+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1416 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_c6f724a4f4b24713581a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1417 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_c77a4c346f71585d4acb+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1418 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_c8f106c70a445e128e0b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1419 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_ca738100aeb1ec8c5f0a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1420 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_cc4ecad1f6c718dbbdd1+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1421 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_cdc14e51d8d28a61d202+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1422 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_d113bd81173024bfbef8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1423 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_d1a9a59715f2f97dd0d9+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1424 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_d24c5b0350e3550bbe08+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1425 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_d339b0175b76e8d1c16a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1426 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_d6c0e697f0139f6cf10d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1427 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_d6ec68ed208a50f386ce+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1428 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_d6fe5a2bffe1c14c5604+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1429 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_d71ff4a9a47bb2779232+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1430 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_da0ff7c9479056cfc0a9+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1431 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_e00e29076f606df4175f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1432 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_e02f71073a5bbd82b90b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1433 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_e1d450ba162daa1e9232+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1434 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_e46e7cf77becae9009a2+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1435 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_e9793fe7a8c6f39badef+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1436 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_ea50fe5995d21d3d8a19+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1437 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_ea96c1d94b434ab56b6a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1438 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_eae3a509248ee092e093+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1439 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_eb1527f4edaf7d3d29bc+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1440 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_f38132b77abfd4e8365f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1441 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_f3be297c3485132cc12f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1442 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_f4cf938415821e326a97+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1443 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_f7f5761cfc68a7c66eb3+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1444 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_fbc0c1dcbdfb5e889d3e+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1445 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_fbfe999e7918c5e3c314+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 1446 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_fe705993427e4cf84ece+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-0.5B/5f1a2111604ccf1723b9.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 896, "initializer_range": 0.02, "intermediate_size": 4864, "max_position_embeddings": 32768, "max_window_layers": 24, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "Qwen/Qwen2.5-0.5B", "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-0.5B/fa9a9e1f6a33e2f83027.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 896, "initializer_range": 0.02, "intermediate_size": 4864, "max_position_embeddings": 32768, "max_window_layers": 24, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "Qwen/Qwen2.5-0.5B", "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-1.5B/842677cbddc5f7674b52.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 1536, "initializer_range": 0.02, "intermediate_size": 8960, "max_position_embeddings": 131072, "max_window_layers": 28, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "Qwen/Qwen2.5-1.5B", "checkpoint_revision": "8faed761d45a263340a0528343f099c05c9a4323", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 12, "num_hidden_layers": 28, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-1.5B/9c442126814a181b6b08.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 1536, "initializer_range": 0.02, "intermediate_size": 8960, "max_position_embeddings": 131072, "max_window_layers": 28, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "Qwen/Qwen2.5-1.5B", "checkpoint_revision": "8faed761d45a263340a0528343f099c05c9a4323", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 12, "num_hidden_layers": 28, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-14B/4d344eef5c363f6851d8.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 131072, "max_window_layers": 48, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 16, "checkpoint_id": "Qwen/Qwen2.5-14B", "checkpoint_revision": "97e1e76335b7017d8f67c08a19d103c0504298c9", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 48, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-14B/703843f253e4eab07ed2.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 131072, "max_window_layers": 48, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "Qwen/Qwen2.5-14B", "checkpoint_revision": "97e1e76335b7017d8f67c08a19d103c0504298c9", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 48, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-32B-Instruct/903c83b2adc41caef7b2.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 27648, "max_position_embeddings": 32768, "max_window_layers": 70, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "Qwen/Qwen2.5-32B-Instruct", "checkpoint_revision": "5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 64, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-32B-Instruct/97fad9b9d7ca5c477782.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 27648, "max_position_embeddings": 32768, "max_window_layers": 70, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "Qwen/Qwen2.5-32B-Instruct", "checkpoint_revision": "5ede1c97bbab6ce5cda5812749b4c0bdf79b18dd", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 64, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-72B-Instruct/058a352bb7d4c0e8af68.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 29568, "max_position_embeddings": 32768, "max_window_layers": 70, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "Qwen/Qwen2.5-72B-Instruct", "checkpoint_revision": "d3d951150c1e5848237cd6a7ad11df4836aee842", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 32768, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-72B-Instruct/090bc30b9eaa90b56de8.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 29568, "max_position_embeddings": 32768, "max_window_layers": 70, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "Qwen/Qwen2.5-72B-Instruct", "checkpoint_revision": "d3d951150c1e5848237cd6a7ad11df4836aee842", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-72B-Instruct/355ef61d7e21c9ca4dfd.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 29568, "max_position_embeddings": 32768, "max_window_layers": 70, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "Qwen/Qwen2.5-72B-Instruct", "checkpoint_revision": "d3d951150c1e5848237cd6a7ad11df4836aee842", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 32768, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-72B-Instruct/5feb3df570ed48ce4ef9.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 29568, "max_position_embeddings": 32768, "max_window_layers": 70, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "Qwen/Qwen2.5-72B-Instruct", "checkpoint_revision": "d3d951150c1e5848237cd6a7ad11df4836aee842", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 2048, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-72B-Instruct/62d648e67c1df9861c81.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 29568, "max_position_embeddings": 32768, "max_window_layers": 70, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "Qwen/Qwen2.5-72B-Instruct", "checkpoint_revision": "d3d951150c1e5848237cd6a7ad11df4836aee842", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 3072, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-72B-Instruct/b0090f8c5a66f58c402e.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 29568, "max_position_embeddings": 32768, "max_window_layers": 70, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "Qwen/Qwen2.5-72B-Instruct", "checkpoint_revision": "d3d951150c1e5848237cd6a7ad11df4836aee842", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 3072, "task": "text-generation"}, "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/2104c2569f8076fd08e8.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "Qwen/Qwen2.5-7B-Instruct", "checkpoint_revision": "bb46c15ee4bb56c5b63245ef50fd7637234d6f75", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/2bdd504102100c9d1a90.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "Qwen/Qwen2.5-7B-Instruct", "checkpoint_revision": "bb46c15ee4bb56c5b63245ef50fd7637234d6f75", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/8be3a002e240a4aad032.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "Qwen/Qwen2.5-7B-Instruct", "checkpoint_revision": "bb46c15ee4bb56c5b63245ef50fd7637234d6f75", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/e9d0ac3eb014579d6b51.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "Qwen/Qwen2.5-7B-Instruct", "checkpoint_revision": "bb46c15ee4bb56c5b63245ef50fd7637234d6f75", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-7B-Instruct/febd5daac4e51196a9ec.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "Qwen/Qwen2.5-7B-Instruct", "checkpoint_revision": "bb46c15ee4bb56c5b63245ef50fd7637234d6f75", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-Coder-32B-Instruct/39b69bbd54bed005e329.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 27648, "max_position_embeddings": 32768, "max_window_layers": 64, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 8, "checkpoint_id": "Qwen/Qwen2.5-Coder-32B-Instruct", "checkpoint_revision": "b47205940b83b5b484577359f71ee7b88472df67", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 64, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-Coder-7B-Instruct/c19875bdff42cd555d4c.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "Qwen/Qwen2.5-Coder-7B-Instruct", "checkpoint_revision": "0eb6b1ed2d0c4306bc637d09ecef51e59d3dfe05", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27.dev0/inference/qwen2/Qwen/Qwen2.5-Math-7B-Instruct/73abe935a165dd5a8d7d.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 4096, "max_window_layers": 28, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 32, "checkpoint_id": "Qwen/Qwen2.5-Math-7B-Instruct", "checkpoint_revision": "ef9926d75ab1d54532f6a30dd5e760355eb9aa4d", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/4538babd01182da34f41.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"apply_residual_connection_post_layernorm": false, "architectures": ["BloomForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "gradient_checkpointing": false, "hidden_dropout": 0.1, "hidden_size": 32, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "initializer_range": 0.02, "is_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "layer_norm_epsilon": 1e-05, "model_type": "bloom", "n_head": 4, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 3, "pretraining_tp": 1, "seq_length": 7, "slow_but_exact": true, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1024}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/b40a794eff5ea470980f.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"apply_residual_connection_post_layernorm": false, "architectures": ["BloomForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "gradient_checkpointing": false, "hidden_dropout": 0.1, "hidden_size": 32, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "initializer_range": 0.02, "is_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "layer_norm_epsilon": 1e-05, "model_type": "bloom", "n_head": 4, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 3, "pretraining_tp": 1, "seq_length": 7, "slow_but_exact": true, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1024}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/cdbdbf737272e98ae974.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"apply_residual_connection_post_layernorm": false, "architectures": ["BloomForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "gradient_checkpointing": false, "hidden_dropout": 0.1, "hidden_size": 32, "id2label": {"0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2"}, "initializer_range": 0.02, "is_decoder": true, "label2id": {"LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2}, "layer_norm_epsilon": 1e-05, "model_type": "bloom", "n_head": 4, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-BloomForCausalLM", "checkpoint_revision": "92b07e9b7b4f986fa7c54e2ac3b9201b4ba5212e", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 3, "pretraining_tp": 1, "seq_length": 7, "slow_but_exact": true, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 1024}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/gpt2/gpt2/aadac442fccfdd730bb5.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "bos_token_id": 50256, "embd_pdrop": 0.1, "eos_token_id": 50256, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 1024, "n_embd": 768, "n_head": 12, "n_inner": null, "n_layer": 12, "n_positions": 1024, "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "gpt2", "checkpoint_revision": "607a30d783dfa663caf39e06633721c8d4cfcd7e", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 1024, "task": "text-generation"}, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "task_specific_params": {"text-generation": {"do_sample": true, "max_length": 50}}, "use_cache": true, "vocab_size": 50257}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/gpt2/hf-internal-testing/tiny-random-gpt2/1f8668afaa87da7a4bc8.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/gpt2/hf-internal-testing/tiny-random-gpt2/af0ef68e4ec57e23cab5.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/gpt2/hf-internal-testing/tiny-random-gpt2/e0c5534b610fbfb22b6e.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"activation_function": "gelu_new", "attention_probs_dropout_prob": 0.1, "attn_pdrop": 0.1, "bos_token_id": 98, "embd_pdrop": 0.1, "eos_token_id": 98, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_epsilon": 1e-05, "model_type": "gpt2", "n_ctx": 512, "n_embd": 32, "n_head": 4, "n_inner": null, "n_layer": 5, "n_positions": 512, "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "pad_token_id": 98, "reorder_and_upcast_attn": false, "resid_pdrop": 0.1, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "type_vocab_size": 16, "use_cache": true, "vocab_size": 1000}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/llama/llamafactory/tiny-random-Llama-3/1ef3929e28ba91cc3cc6.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "2d9d8c1112e9cd4b0d66bb612e09be7da7997b18", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/llama/llamafactory/tiny-random-Llama-3/71ec0a49c3535c618d03.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "2d9d8c1112e9cd4b0d66bb612e09be7da7997b18", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/llama/llamafactory/tiny-random-Llama-3/eb3f26aa23141bff2292.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "2d9d8c1112e9cd4b0d66bb612e09be7da7997b18", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/7d2df9c19098ee676fa8.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 8, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "is_decoder": true, "max_position_embeddings": 512, "model_type": "mistral", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "dacorvo/tiny-random-MistralForCausalLM", "checkpoint_revision": "81d453e3c8985649e9ee3d4c9378461029d1c73a", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/ac0287246ef4575f8b78.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 8, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "is_decoder": true, "max_position_embeddings": 512, "model_type": "mistral", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "dacorvo/tiny-random-MistralForCausalLM", "checkpoint_revision": "81d453e3c8985649e9ee3d4c9378461029d1c73a", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/af0f1b79454574c744eb.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 8, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 37, "is_decoder": true, "max_position_embeddings": 512, "model_type": "mistral", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "dacorvo/tiny-random-MistralForCausalLM", "checkpoint_revision": "81d453e3c8985649e9ee3d4c9378461029d1c73a", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 2, "pad_token_id": 0, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float32", "type_vocab_size": 16, "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/mixtral/dacorvo/Mixtral-tiny/8dde518ab8e435c4c830.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 1024, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/mixtral/dacorvo/Mixtral-tiny/9ac32cae9a1e9b72b9ed.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 1024, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/mixtral/dacorvo/Mixtral-tiny/d777c911e955212a0132.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3584, "max_position_embeddings": 1024, "model_type": "mixtral", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 32, "num_experts_per_tok": 2, "num_hidden_layers": 2, "num_key_value_heads": 8, "num_local_experts": 8, "output_router_logits": false, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "router_aux_loss_coef": 0.001, "router_jitter_noise": 0.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float16", "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/93d7843b7abe79348924.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_remove_final_layer_norm": false, "activation_function": "relu", "architectures": ["OPTForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 2, "do_layer_norm_before": true, "dropout": 0.1, "embed_dim": 16, "enable_bias": true, "eos_token_id": 2, "ffn_dim": 4, "hidden_size": 16, "init_std": 0.02, "is_decoder": true, "layer_norm_elementwise_affine": true, "layerdrop": 0.0, "max_position_embeddings": 100, "model_type": "opt", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-OPTForCausalLM", "checkpoint_revision": "3f3f2ee1e499cb7ad89b877068684fdc9d9513c3", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 5, "pad_token_id": 1, "torch_dtype": "float32", "use_cache": true, "vocab_size": 50265, "word_embed_proj_dim": 16}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/b392ca0eec3368da72ec.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_remove_final_layer_norm": false, "activation_function": "relu", "architectures": ["OPTForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 2, "do_layer_norm_before": true, "dropout": 0.1, "embed_dim": 16, "enable_bias": true, "eos_token_id": 2, "ffn_dim": 4, "hidden_size": 16, "init_std": 0.02, "is_decoder": true, "layer_norm_elementwise_affine": true, "layerdrop": 0.0, "max_position_embeddings": 100, "model_type": "opt", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-OPTForCausalLM", "checkpoint_revision": "3f3f2ee1e499cb7ad89b877068684fdc9d9513c3", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 5, "pad_token_id": 1, "torch_dtype": "float32", "use_cache": true, "vocab_size": 50265, "word_embed_proj_dim": 16}
|
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.0.27/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/f829b04255e2c75cd7c8.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_remove_final_layer_norm": false, "activation_function": "relu", "architectures": ["OPTForCausalLM"], "attention_dropout": 0.1, "bos_token_id": 2, "do_layer_norm_before": true, "dropout": 0.1, "embed_dim": 16, "enable_bias": true, "eos_token_id": 2, "ffn_dim": 4, "hidden_size": 16, "init_std": 0.02, "is_decoder": true, "layer_norm_elementwise_affine": true, "layerdrop": 0.0, "max_position_embeddings": 100, "model_type": "opt", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-OPTForCausalLM", "checkpoint_revision": "3f3f2ee1e499cb7ad89b877068684fdc9d9513c3", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 5, "pad_token_id": 1, "torch_dtype": "float32", "use_cache": true, "vocab_size": 50265, "word_embed_proj_dim": 16}
|
neuronxcc-2.15.143.0+e39249ad/MODULE_0159cebf2bdd30fd3a27+39f12043/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
|
neuronxcc-2.15.143.0+e39249ad/MODULE_0159cebf2bdd30fd3a27+39f12043/model.done
ADDED
|
File without changes
|
neuronxcc-2.15.143.0+e39249ad/MODULE_0159cebf2bdd30fd3a27+39f12043/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e105fdc77f563ee2562f24b76a235e47bb1a8866172b3b7b071cd1016ec1f6d6
|
| 3 |
+
size 447915
|
neuronxcc-2.15.143.0+e39249ad/MODULE_0159cebf2bdd30fd3a27+39f12043/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b484002104bf3e4ef6b49621d162fcd3a0ba5a794ec8cbb202fbc3893cd7024
|
| 3 |
+
size 6636544
|
neuronxcc-2.15.143.0+e39249ad/MODULE_05887d2cc91ed79b4acc+39f12043/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
|
neuronxcc-2.15.143.0+e39249ad/MODULE_05887d2cc91ed79b4acc+39f12043/model.done
ADDED
|
File without changes
|
neuronxcc-2.15.143.0+e39249ad/MODULE_05887d2cc91ed79b4acc+39f12043/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:607a3bb173593322f2999032bac7d52fe5782f01fa1d0c9bed5bd7915e789f18
|
| 3 |
+
size 560480
|
neuronxcc-2.15.143.0+e39249ad/MODULE_05887d2cc91ed79b4acc+39f12043/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a49d282382403d3aa53025ab3dd715c462c98801e029e1f53618069931837155
|
| 3 |
+
size 4752384
|