Synchronizing local compiler cache.
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +84 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/02d4a301af66436b83a4.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/12c129f098b7cebc86c4.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/llamafactory/tiny-random-Llama-3/10d28b5670f7b4296e0f.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/llamafactory/tiny-random-Llama-3/3f93b3fc07ac7e8663a3.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/llamafactory/tiny-random-Llama-3/712160aa9962bdbc48b7.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-3.1-8B-Instruct/b4a7573c4f811bffe269.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-3.1-8B-Instruct/c38f7bf56dcb224f566b.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-3.2-3B/dd3613d57f885e5e99ae.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/12469cfbaa2be7979be9.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/3047f14e5cd104f6da88.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/cbf5e07921ee14bd6483.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/distilbert/philschmid/tiny-distilbert-classification/f38fc51a7949ff88adae.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/gpt2/gpt2/98f807ee88912bf4b9d8.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/gpt2/hf-internal-testing/tiny-random-gpt2/0b5b5348467d20a868da.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/gpt2/hf-internal-testing/tiny-random-gpt2/3a30f319d7cae1f3076c.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/gpt2/hf-internal-testing/tiny-random-gpt2/8a6582d10bf46ea7004e.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/gpt2/hf-internal-testing/tiny-random-gpt2/f6a893091677c8cb5c41.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/02d4a301af66436b83a4.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/llamafactory/tiny-random-Llama-3/10d28b5670f7b4296e0f.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/llamafactory/tiny-random-Llama-3/3f93b3fc07ac7e8663a3.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/llamafactory/tiny-random-Llama-3/712160aa9962bdbc48b7.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/meta-llama/Llama-3.1-8B-Instruct/b4a7573c4f811bffe269.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/meta-llama/Llama-3.1-8B-Instruct/c38f7bf56dcb224f566b.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/3bdcb3d6d5fb4b0b7097.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/3d676d12f1566545d6b0.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/ad4d8b389573be75fbee.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mistral/optimum/mistral-1.1b-testing/081b187113a5f417a9e0.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mixtral/dacorvo/Mixtral-tiny/3a688b7dcd45d9a80b14.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mixtral/dacorvo/Mixtral-tiny/89980755d7c8bc1b31b0.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mixtral/dacorvo/Mixtral-tiny/9f85ef35436cc6a20682.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mixtral/dacorvo/Mixtral-tiny/f1477b1f14a6669df1a7.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/63ef91a527f73ba3b87e.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/aa9fef08c5f79c9217fb.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/fe9dc58f7d028523a0a6.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/asntr/tiny-stable-diffusion-pix2pix-torch/ea7b1231493b4770ef5c.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-latent-consistency/a0266aea820b4bdc6179.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/32eb77afae7beb1b6a46.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/69ca6952a5ae96368225.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/929dae9e65a3e8ca843a.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/daff12b814ed88f2ab94.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/e0424cc49086a4e14ecf.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/3b9c2d8b0685c83df7a8.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/9ebf77ef54b550a7aeea.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/bb8d7ab74e3895d55e5a.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/bf44efc41469e0a7cc8c.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/de03d21e9973871dbb35.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.27.dev0/inference/gpt2/gpt2/98f807ee88912bf4b9d8.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.27.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/6b3192766c61d426df54.json +1 -0
- neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.27.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/12c129f098b7cebc86c4.json +1 -0
.gitattributes
CHANGED
|
@@ -5954,3 +5954,87 @@ neuronxcc-2.15.128.0+56dc5a86/MODULE_8853125480725449932+df3e6f3f/model.neff fil
|
|
| 5954 |
neuronxcc-2.15.128.0+56dc5a86/MODULE_12094726845982372710+df3e6f3f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5955 |
neuronxcc-2.15.128.0+56dc5a86/MODULE_15554787448610520234+df3e6f3f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5956 |
neuronxcc-2.15.128.0+56dc5a86/MODULE_15574943571739609130+df3e6f3f/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5954 |
neuronxcc-2.15.128.0+56dc5a86/MODULE_12094726845982372710+df3e6f3f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5955 |
neuronxcc-2.15.128.0+56dc5a86/MODULE_15554787448610520234+df3e6f3f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5956 |
neuronxcc-2.15.128.0+56dc5a86/MODULE_15574943571739609130+df3e6f3f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5957 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_11654131318873123016+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5958 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_12874312700001148778+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5959 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_15051065331470346867+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5960 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_15473681725457350439+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5961 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_15748385273906273062+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5962 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_18075028104588171687+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5963 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_204ebebf25942a01d1c2+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5964 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_2091506504151733078+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5965 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_2466414372820998287+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5966 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_2dfe883f70d43532f8a4+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5967 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_32eb77afae7beb1b6a46/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5968 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_32eb77afae7beb1b6a46/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5969 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_32eb77afae7beb1b6a46/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5970 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_3419338939774422803+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5971 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_3b9c2d8b0685c83df7a8/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5972 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_3b9c2d8b0685c83df7a8/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5973 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_3b9c2d8b0685c83df7a8/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5974 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_410438226797912832+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5975 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_4144779976049691510+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5976 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_4b58fe8567be9e65d26f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5977 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_4e375a5e1d159c319c4a+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5978 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_5969785301766543355+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5979 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_5e718c7a1066e741c8dd+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5980 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_6503304240059240709+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5981 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_6924851687386500240+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5982 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_69ca6952a5ae96368225/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5983 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_69ca6952a5ae96368225/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5984 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_69ca6952a5ae96368225/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5985 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_70ee399e6fa6b6235418+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5986 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_7410465257773667141+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5987 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_8537207931352873960+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5988 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_8539618823351053457+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5989 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_8a7c00a8b0553e557d61+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5990 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_8c93cc9f80cd5bfc3ec7+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5991 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_9211227249597385740+d7517139/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5992 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_929dae9e65a3e8ca843a/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5993 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_929dae9e65a3e8ca843a/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5994 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_929dae9e65a3e8ca843a/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5995 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_9ebf77ef54b550a7aeea/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5996 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_9ebf77ef54b550a7aeea/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5997 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_9ebf77ef54b550a7aeea/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5998 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_a0266aea820b4bdc6179/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 5999 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_a0266aea820b4bdc6179/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6000 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_a0266aea820b4bdc6179/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6001 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_a8879c3265be017037a3+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 6002 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_b0cf61abda16eb6dab0b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 6003 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_bb8d7ab74e3895d55e5a/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6004 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_bb8d7ab74e3895d55e5a/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6005 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_bb8d7ab74e3895d55e5a/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6006 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_bf44efc41469e0a7cc8c/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6007 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_bf44efc41469e0a7cc8c/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6008 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_bf44efc41469e0a7cc8c/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6009 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_caf1acf2b79f887a9c1f+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 6010 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_daff12b814ed88f2ab94/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6011 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_daff12b814ed88f2ab94/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6012 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_daff12b814ed88f2ab94/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6013 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_de03d21e9973871dbb35/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6014 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_de03d21e9973871dbb35/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6015 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_de03d21e9973871dbb35/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6016 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_e0424cc49086a4e14ecf/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6017 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_e0424cc49086a4e14ecf/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6018 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_e0424cc49086a4e14ecf/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6019 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_ea7b1231493b4770ef5c/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6020 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_ea7b1231493b4770ef5c/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6021 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_ea7b1231493b4770ef5c/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6022 |
+
neuronxcc-2.15.128.0+56dc5a86/MODULE_eebabf12988462d4bdc0+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 6023 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_4d4c73fd7fa7218f1acc/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6024 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_4d4c73fd7fa7218f1acc/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6025 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_4d4c73fd7fa7218f1acc/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6026 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_5e718c7a1066e741c8dd+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 6027 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_70ee399e6fa6b6235418+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 6028 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_8c93cc9f80cd5bfc3ec7+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 6029 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_b0cf61abda16eb6dab0b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 6030 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_cf952e4c0d1c040d9d64/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6031 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_cf952e4c0d1c040d9d64/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6032 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_cf952e4c0d1c040d9d64/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6033 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_daacf5f978d57e3fca76/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6034 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_daacf5f978d57e3fca76/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6035 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_daacf5f978d57e3fca76/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6036 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_e5da7e4a5bee80b3a22a/controlnet_0/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6037 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_e5da7e4a5bee80b3a22a/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6038 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_e5da7e4a5bee80b3a22a/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6039 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_e5da7e4a5bee80b3a22a/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 6040 |
+
neuronxcc-2.15.143.0+e39249ad/MODULE_ff056ff915e121ff695e+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/02d4a301af66436b83a4.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128003, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "NousResearch/Hermes-2-Theta-Llama-3-8B", "checkpoint_revision": "57a73110702e7b05ba3f39fef36297454c680725", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 2048, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/12c129f098b7cebc86c4.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128003, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "NousResearch/Hermes-2-Theta-Llama-3-8B", "checkpoint_revision": "57a73110702e7b05ba3f39fef36297454c680725", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/llamafactory/tiny-random-Llama-3/10d28b5670f7b4296e0f.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/llamafactory/tiny-random-Llama-3/3f93b3fc07ac7e8663a3.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/llamafactory/tiny-random-Llama-3/712160aa9962bdbc48b7.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-3.1-8B-Instruct/b4a7573c4f811bffe269.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct", "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-3.1-8B-Instruct/c38f7bf56dcb224f566b.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 2, "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct", "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-3.2-3B/dd3613d57f885e5e99ae.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "head_dim": 128, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-3.2-3B", "checkpoint_revision": "43fa890183375f5f69cb9646f29aa99ef3207c22", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 24, "num_hidden_layers": 28, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 32.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/12469cfbaa2be7979be9.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/3047f14e5cd104f6da88.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/bloom/hf-internal-testing/tiny-random-BloomForCausalLM/cbf5e07921ee14bd6483.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/distilbert/philschmid/tiny-distilbert-classification/f38fc51a7949ff88adae.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"activation": "gelu", "architectures": ["DistilBertForSequenceClassification"], "attention_dropout": 0.1, "dim": 2, "dropout": 0.1, "finetuning_task": "sst-2", "hidden_dim": 2, "id2label": {"0": "NEGATIVE", "1": "POSITIVE"}, "initializer_range": 0.02, "label2id": {"NEGATIVE": 0, "POSITIVE": 1}, "max_position_embeddings": 512, "model_type": "distilbert", "n_heads": 2, "n_layers": 2, "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "disable_fallback": false, "disable_fast_relayout": false, "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 128}, "output_past": true, "qa_dropout": 0.1, "seq_classif_dropout": 0.2, "sinusoidal_pos_embds": false, "task": "text-classification", "tie_weights_": true, "vocab_size": 30522}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/gpt2/gpt2/98f807ee88912bf4b9d8.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/gpt2/hf-internal-testing/tiny-random-gpt2/0b5b5348467d20a868da.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/gpt2/hf-internal-testing/tiny-random-gpt2/3a30f319d7cae1f3076c.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/gpt2/hf-internal-testing/tiny-random-gpt2/8a6582d10bf46ea7004e.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/gpt2/hf-internal-testing/tiny-random-gpt2/f6a893091677c8cb5c41.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": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 128, "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/02d4a301af66436b83a4.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128003, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "NousResearch/Hermes-2-Theta-Llama-3-8B", "checkpoint_revision": "57a73110702e7b05ba3f39fef36297454c680725", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 2048, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/llamafactory/tiny-random-Llama-3/10d28b5670f7b4296e0f.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/llamafactory/tiny-random-Llama-3/3f93b3fc07ac7e8663a3.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/llamafactory/tiny-random-Llama-3/712160aa9962bdbc48b7.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/meta-llama/Llama-3.1-8B-Instruct/b4a7573c4f811bffe269.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct", "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/llama/meta-llama/Llama-3.1-8B-Instruct/c38f7bf56dcb224f566b.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 2, "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct", "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 24, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/3bdcb3d6d5fb4b0b7097.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/3d676d12f1566545d6b0.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mistral/dacorvo/tiny-random-MistralForCausalLM/ad4d8b389573be75fbee.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mistral/optimum/mistral-1.1b-testing/081b187113a5f417a9e0.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 5632, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "optimum/mistral-1.1b-testing", "checkpoint_revision": "ce03bc8d47dbd2c173ff65f3a8de1325ba724195", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 22, "num_key_value_heads": 4, "rms_norm_eps": 1e-05, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mixtral/dacorvo/Mixtral-tiny/3a688b7dcd45d9a80b14.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mixtral/dacorvo/Mixtral-tiny/89980755d7c8bc1b31b0.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": 4, "checkpoint_id": "dacorvo/Mixtral-tiny", "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 1024, "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mixtral/dacorvo/Mixtral-tiny/9f85ef35436cc6a20682.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/mixtral/dacorvo/Mixtral-tiny/f1477b1f14a6669df1a7.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/63ef91a527f73ba3b87e.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": "190d1f4fc0011d2eaeaa05282e0fbd2445e4b11f", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/aa9fef08c5f79c9217fb.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": "190d1f4fc0011d2eaeaa05282e0fbd2445e4b11f", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/opt/hf-internal-testing/tiny-random-OPTForCausalLM/fe9dc58f7d028523a0a6.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": "190d1f4fc0011d2eaeaa05282e0fbd2445e4b11f", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/asntr/tiny-stable-diffusion-pix2pix-torch/ea7b1231493b4770ef5c.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": 8, "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 32, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 8, "layers_per_block": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 8, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": null, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "task": "semantic-segmentation", "time_cond_proj_dim": null, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": 1, "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": false}}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-latent-consistency/a0266aea820b4bdc6179.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 64, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 8, "num_hidden_layers": 3, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": 8, "attention_type": "default", "block_out_channels": [4, 8], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 32, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "layers_per_block": 1, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 2, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": null, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "task": "semantic-segmentation", "time_cond_proj_dim": 32, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": 1, "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": false}}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/32eb77afae7beb1b6a46.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "text_encoder_2": {"architectures": ["CLIPTextModelWithProjection"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": "text_time", "addition_embed_type_num_heads": 64, "addition_time_embed_dim": 8, "attention_head_dim": [2, 4], "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 64, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "layers_per_block": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": 80, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "task": "semantic-segmentation", "time_cond_proj_dim": null, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": [1, 2], "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": true}}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/69ca6952a5ae96368225.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "text_encoder_2": {"architectures": ["CLIPTextModelWithProjection"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": "text_time", "addition_embed_type_num_heads": 64, "addition_time_embed_dim": 8, "attention_head_dim": [2, 4], "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 64, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "layers_per_block": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": 80, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "task": "semantic-segmentation", "time_cond_proj_dim": null, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": [1, 2], "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": true}}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/929dae9e65a3e8ca843a.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": true, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "text_encoder_2": {"architectures": ["CLIPTextModelWithProjection"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": true, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": "text_time", "addition_embed_type_num_heads": 64, "addition_time_embed_dim": 8, "attention_head_dim": [2, 4], "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 64, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "layers_per_block": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": 80, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "task": "semantic-segmentation", "time_cond_proj_dim": null, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": [1, 2], "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": true}}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/daff12b814ed88f2ab94.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "text_encoder_2": {"architectures": ["CLIPTextModelWithProjection"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": "text_time", "addition_embed_type_num_heads": 64, "addition_time_embed_dim": 8, "attention_head_dim": [2, 4], "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 64, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "layers_per_block": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "all", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 4, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": 80, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "task": "semantic-segmentation", "time_cond_proj_dim": null, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": [1, 2], "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": true}}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/e0424cc49086a4e14ecf.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "text_encoder_2": {"architectures": ["CLIPTextModelWithProjection"], "attention_dropout": 0.0, "hidden_act": "gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": "text_time", "addition_embed_type_num_heads": 64, "addition_time_embed_dim": 8, "attention_head_dim": [2, 4], "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 64, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "layers_per_block": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 4, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": 80, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "task": "semantic-segmentation", "time_cond_proj_dim": null, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": [1, 2], "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": true}}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/3b9c2d8b0685c83df7a8.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": 8, "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 32, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "layers_per_block": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": true, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": null, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "task": "semantic-segmentation", "time_cond_proj_dim": null, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": 1, "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": false}}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/9ebf77ef54b550a7aeea.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"controlnet_0": {"_class_name": "ControlNetModel", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": 8, "block_out_channels": [32, 64], "class_embed_type": null, "conditioning_channels": 3, "conditioning_embedding_out_channels": [16, 32], "controlnet_conditioning_channel_order": "rgb", "cross_attention_dim": 32, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "global_pool_conditions": false, "in_channels": 4, "layers_per_block": 2, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_encoder_hidden_size": 32, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "projection_class_embeddings_input_dim": null, "resnet_time_scale_shift": "default", "task": "semantic-segmentation", "transformer_layers_per_block": 1, "upcast_attention": false, "use_linear_projection": false}, "model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": 8, "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 32, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "layers_per_block": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": null, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "task": "semantic-segmentation", "time_cond_proj_dim": null, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": 1, "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": false}}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/bb8d7ab74e3895d55e5a.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"controlnet_0": {"_class_name": "ControlNetModel", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": 8, "block_out_channels": [32, 64], "class_embed_type": null, "conditioning_channels": 3, "conditioning_embedding_out_channels": [16, 32], "controlnet_conditioning_channel_order": "rgb", "cross_attention_dim": 32, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "global_pool_conditions": false, "in_channels": 4, "layers_per_block": 2, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_encoder_hidden_size": 32, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "projection_class_embeddings_input_dim": null, "resnet_time_scale_shift": "default", "task": "semantic-segmentation", "transformer_layers_per_block": 1, "upcast_attention": false, "use_linear_projection": false}, "controlnet_1": {"_class_name": "ControlNetModel", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": 8, "block_out_channels": [32, 64], "class_embed_type": null, "conditioning_channels": 3, "conditioning_embedding_out_channels": [16, 32], "controlnet_conditioning_channel_order": "rgb", "cross_attention_dim": 32, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "global_pool_conditions": false, "in_channels": 4, "layers_per_block": 2, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_encoder_hidden_size": 32, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "projection_class_embeddings_input_dim": null, "resnet_time_scale_shift": "default", "task": "semantic-segmentation", "transformer_layers_per_block": 1, "upcast_attention": false, "use_linear_projection": false}, "model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": 8, "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 32, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "layers_per_block": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": null, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "task": "semantic-segmentation", "time_cond_proj_dim": null, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": 1, "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": false}}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/bf44efc41469e0a7cc8c.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": 8, "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 32, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "layers_per_block": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 4, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": null, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "task": "semantic-segmentation", "time_cond_proj_dim": null, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": 1, "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": false}}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25/inference/stable-diffusion/hf-internal-testing/tiny-stable-diffusion-torch/de03d21e9973871dbb35.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 32, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 37, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 4, "num_hidden_layers": 5, "task": "feature-extraction", "vocab_size": 1000}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": 8, "attention_type": "default", "block_out_channels": [32, 64], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 32, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D"], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "layers_per_block": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 32, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 2, "static_width": 32}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": null, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "task": "semantic-segmentation", "time_cond_proj_dim": null, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": 1, "up_block_types": ["CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": false, "use_linear_projection": false}}
|
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.27.dev0/inference/gpt2/gpt2/98f807ee88912bf4b9d8.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": "2.15.128.0+56dc5a86", "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.27.dev0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/6b3192766c61d426df54.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": "2.15.128.0+56dc5a86", "num_cores": 24, "sequence_length": 512, "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-2.15.128.0+56dc5a86/0_REGISTRY/0.0.27.dev0/inference/llama/NousResearch/Hermes-2-Theta-Llama-3-8B/12c129f098b7cebc86c4.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128003, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "NousResearch/Hermes-2-Theta-Llama-3-8B", "checkpoint_revision": "57a73110702e7b05ba3f39fef36297454c680725", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
|