Synchronizing local compiler cache.
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +116 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/distilbert/distilbert-base-uncased-finetuned-sst-2-english/843d9f5ba8d442721b5e.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/distilbert/hf-internal-testing/tiny-random-DistilBertModel/18ea862943d46e9502fe.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/d8d5221e2ff47fe2e810.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/499a6f3c535d93bcd8c9.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev0/inference/qwen2/Qwen/Qwen2.5-0.5B/08b82ea5dab18178ad7f.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/gpt2/gpt2/4a0fe61f82a71cd05cad.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4e6fd20c0862130b2f01.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4ec24af550bea736dba0.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/5188b60acf9ad77c8ef5.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/7555805b6a593a366a21.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/b2cf188b9d58ab827ad9.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/b53f0d2daef297d8794a.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/da9452c0fcbe80e153f5.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/ibm-granite/granite-3.1-2b-instruct/86817be9d58337936129.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/ibm-granite/granite-3.1-2b-instruct/a2d65ee224bccfbf33c2.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/ibm-granite/granite-3.1-2b-instruct/bf71032506a251068193.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/0af73583385b26dcf000.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/2e8cb42c92e334dfbaa9.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/51231e30eb944c5bc1f8.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/5433fffb45752137c8de.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/588e5102c25f59898011.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/5c109283b389f09f634b.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/648252251e4a8bcdcbed.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/6af26305eda23594815e.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/8c48d1da1325809763e8.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/b3814f2986268efcd29c.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/c74d843980295535d5ea.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/c7c2db71d0de15fb6862.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/e76fd07fe3037f2e366b.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/unsloth/Llama-3.2-1B-Instruct/08c70e54d07a8a28e136.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/unsloth/Llama-3.2-1B-Instruct/49d61e18927b113552d1.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/unsloth/Llama-3.2-1B-Instruct/6ff803c42db4ecee05a3.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mistral/optimum/mistral-1.1b-testing/26e0edb6fea0d3bc9667.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mixtral/dacorvo/Mixtral-tiny/678cf23ea51877d5956c.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/microsoft/Phi-3-mini-4k-instruct/352a3518452cfb4a7d84.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/microsoft/Phi-3-mini-4k-instruct/89baef7b06c4231392e4.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/microsoft/Phi-3-mini-4k-instruct/9e1ede42fd1a2ceef459.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/microsoft/Phi-3-mini-4k-instruct/c9f481c0e2f6fd992637.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/05491c46e49b1857820c.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/4e88b70b02777e345f13.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/70bc53d4dc1ebe9f4e54.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/9854f57bdc6009b4290a.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/aec03923c7147a6162cb.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/d82c490f84f2b1e1522c.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/f525ffd2f160d6993f6c.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/qwen2/Qwen/Qwen2.5-0.5B/734242ffd55de3545f50.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/qwen2/Qwen/Qwen2.5-0.5B/9d442ba21d7a61100a33.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/qwen2/Qwen/Qwen2.5-0.5B/e28ef40ae22096954a46.json +1 -0
- neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/qwen2/Qwen/Qwen2.5-0.5B/eb9dc14053f0f9d06257.json +1 -0
.gitattributes
CHANGED
|
@@ -7931,3 +7931,119 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_b8989b1ce053b19f193d+613edded/model.neff fi
|
|
| 7931 |
neuronxcc-2.16.372.0+4a9b2326/MODULE_f275897da2e206eb43ea+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7932 |
neuronxcc-2.17.194.0+d312836f/MODULE_b8989b1ce053b19f193d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7933 |
neuronxcc-2.17.194.0+d312836f/MODULE_f275897da2e206eb43ea+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7931 |
neuronxcc-2.16.372.0+4a9b2326/MODULE_f275897da2e206eb43ea+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7932 |
neuronxcc-2.17.194.0+d312836f/MODULE_b8989b1ce053b19f193d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7933 |
neuronxcc-2.17.194.0+d312836f/MODULE_f275897da2e206eb43ea+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7934 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_01c445025d99d71be2b3+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7935 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_0b137632bac8c4726d4f/decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7936 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_0b137632bac8c4726d4f/encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7937 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_11648890582807925826+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7938 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_12186797013122181295+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7939 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_13309912121921126684+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7940 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_1505680390210029555+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7941 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_15431189573610337239+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7942 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_1545167900966233290+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7943 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_15eb37e3fb556fd3decb+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7944 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_1649fc77b87fff02e370+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7945 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_16885846486752037550+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7946 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_17147817242878056900+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7947 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_17215669526000154054+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7948 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_18ea862943d46e9502fe/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7949 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_2053b1e0fa543cbd84dd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7950 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_22cf23062ec53b3fd95d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7951 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_2ae37ee2c7255cce8028+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7952 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_2ef52130792b59d66c66+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7953 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_3da832fdaa3d62981800+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7954 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_40b73cdf6e14999378ef+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7955 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_4229851826662473223+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7956 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_4610853575678388020+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7957 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_4678455820992380476+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7958 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_498320a96768c9eab266+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7959 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_499a6f3c535d93bcd8c9/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7960 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_499a6f3c535d93bcd8c9/text_encoder_2/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7961 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_499a6f3c535d93bcd8c9/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7962 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_499a6f3c535d93bcd8c9/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7963 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_499a6f3c535d93bcd8c9/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7964 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_4dea33d55b39527f7fc4+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7965 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_53d5c248a142eced45e6+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7966 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_54947fa9c379486e4f5b+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7967 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_6302731493553409576+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7968 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_6f479fa0ca80b88a5b46+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7969 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_70e2b073f2bbeab1aac7/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7970 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_70e2b073f2bbeab1aac7/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7971 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_70e2b073f2bbeab1aac7/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7972 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_70e2b073f2bbeab1aac7/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7973 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_74a533aa34a2ab0fc7aa+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7974 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7975 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_843d9f5ba8d442721b5e/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7976 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_857e6d9a3a28c7fe8c0c+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7977 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_892a0bb27ce39228be75+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7978 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_8ea2de719456a80196f9+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7979 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_913f4e1e2b4632438fe9+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7980 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_9294048697624734381+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7981 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_9402963399160769132+3cc9a3cb/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7982 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_9b4b8c3000ad341d2ddc+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7983 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_a361a81ac38223fcadef+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7984 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_a71e46095542b60896d4/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7985 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_a71e46095542b60896d4/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7986 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_a71e46095542b60896d4/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7987 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_a71e46095542b60896d4/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7988 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_c064389074584e41f54f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7989 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_c24af7fcf05443daf3b7+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7990 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_d3e5e4b762fd9115b68b+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7991 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_d6a9bb00aa7189af3ffb/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7992 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_d6a9bb00aa7189af3ffb/text_encoder_2/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7993 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_d6a9bb00aa7189af3ffb/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7994 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_d6a9bb00aa7189af3ffb/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7995 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_d6a9bb00aa7189af3ffb/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
|
| 7996 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_e9bcfc17d832317203bd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7997 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_f5b6904839bc118bcd54+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7998 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_fce469267b2ad1b5d80e+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7999 |
+
neuronxcc-2.16.372.0+4a9b2326/MODULE_fd6170cedb4fe53c8433+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8000 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_0ffcb646a5c3ca8902dc+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8001 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_16575d1d23477e66f47c+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8002 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_18a02439fa5be899e4e2+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8003 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_18a02439fa5be899e4e2+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8004 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_19677291845d5f9e90e8+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8005 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_1eeab200d3cb011df87f+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8006 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_1eeab200d3cb011df87f+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8007 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_242528f2fa438b512724+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8008 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_2da0bb9b58becd460cc8+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8009 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_3c8663c080fcf8ec7355+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8010 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_4226130b1ea4a246ad12+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8011 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_436f478c6635f2715703+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8012 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_501e832e2a453d315f02+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8013 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_501e832e2a453d315f02+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8014 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_584fbc6f07cc7a3a1ba0+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8015 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_5ced139eb4f9413aa8e0+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8016 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_6a2c4b6116eb07aa27e9+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8017 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_6a2c4b6116eb07aa27e9+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8018 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_7434c6f37c47044f71f8+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8019 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_7acb3db8b2fb8dbb1bef+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8020 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_7acb3db8b2fb8dbb1bef+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8021 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_7c383e90d7a81031bcc3+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8022 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_87bbc2837c7a34ac7e7d+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8023 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_8cdf0acdee318d4bdf69+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8024 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_8d605ae48e1a3bd443e9+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8025 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_98af2fdc49cb9249ea3d+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8026 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_98af2fdc49cb9249ea3d+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8027 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_9f44958d7c5b8c540952+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8028 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_9f44958d7c5b8c540952+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8029 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_a115386b6164b70d349a+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8030 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_a1db116f00c8bf43252e+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8031 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_a2880de6f3cd7a029740+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8032 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_a2880de6f3cd7a029740+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8033 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_a3738511b748888ed3db+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8034 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_a4ecaba50ace94d96a23+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8035 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_a5b7d8e60c4755ae19be+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8036 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_a5b7d8e60c4755ae19be+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8037 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_a9ce1b283ebf2388667c+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8038 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_a9db44a28b85c5f0cea0+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8039 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_b36d95e43385dd760fc5+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8040 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_bfb1d23ae5ee11d85871+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8041 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_bfb1d23ae5ee11d85871+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8042 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_cbaae69f32a2fe71d1d9+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8043 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_d12c8352f8de45811c1f+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8044 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_d12c8352f8de45811c1f+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8045 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_d1b677efdc213d35a822+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8046 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_d1b677efdc213d35a822+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 8047 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_ddb4b83b834889a5553c+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8048 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_fa4a1715cab5dbc60401+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 8049 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_fa4a1715cab5dbc60401+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/distilbert/distilbert-base-uncased-finetuned-sst-2-english/843d9f5ba8d442721b5e.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_attn_implementation_autoset": true, "activation": "gelu", "architectures": ["DistilBertForSequenceClassification"], "attention_dropout": 0.1, "dim": 768, "dropout": 0.1, "finetuning_task": "sst-2", "hidden_dim": 3072, "id2label": {"0": "NEGATIVE", "1": "POSITIVE"}, "initializer_range": 0.02, "label2id": {"NEGATIVE": 0, "POSITIVE": 1}, "max_position_embeddings": 512, "model_type": "distilbert", "n_heads": 12, "n_layers": 6, "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "dynamic_batch_size": false, "inline_weights_to_neff": false, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 128, "tensor_parallel_size": 1}, "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-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/distilbert/hf-internal-testing/tiny-random-DistilBertModel/18ea862943d46e9502fe.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_attn_implementation_autoset": true, "activation": "gelu", "architectures": ["DistilBertModel"], "attention_dropout": 0.1, "dim": 32, "dropout": 0.1, "hidden_act": "gelu", "hidden_dim": 37, "initializer_range": 0.02, "max_position_embeddings": 512, "model_type": "distilbert", "n_heads": 4, "n_layers": 5, "neuron": {"auto_cast": null, "auto_cast_type": null, "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "dynamic_batch_size": false, "inline_weights_to_neff": false, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 128, "tensor_parallel_size": 1}, "qa_dropout": 0.1, "seq_classif_dropout": 0.2, "sinusoidal_pos_embds": false, "task": "feature-extraction", "vocab_size": 1124}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/gpt2/hf-internal-testing/tiny-random-gpt2/d8d5221e2ff47fe2e810.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": "bf16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-gpt2", "checkpoint_revision": "71034c5d8bde858ff824298bdedc65515b97d2b9", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "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-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/stable-diffusion/echarlaix/tiny-random-stable-diffusion-xl/499a6f3c535d93bcd8c9.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model_type": "stable-diffusion", "text_encoder": {"_attn_implementation_autoset": true, "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": "2.16.372.0+4a9b2326", "dynamic_batch_size": false, "inline_weights_to_neff": false, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77, "tensor_parallel_size": 1}, "num_attention_heads": 4, "num_hidden_layers": 5, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 1000}, "text_encoder_2": {"_attn_implementation_autoset": true, "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": "2.16.372.0+4a9b2326", "dynamic_batch_size": false, "inline_weights_to_neff": false, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77, "tensor_parallel_size": 1}, "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": "2.16.372.0+4a9b2326", "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, "tensor_parallel_size": 1}, "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-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev0/inference/qwen2/Qwen/Qwen2.5-0.5B/08b82ea5dab18178ad7f.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 896, "initializer_range": 0.02, "intermediate_size": 4864, "max_position_embeddings": 32768, "max_window_layers": 24, "model_type": "qwen2", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "Qwen/Qwen2.5-0.5B", "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/gpt2/gpt2/4a0fe61f82a71cd05cad.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "gpt2", "_task": "text-generation", "activation_function": "gelu_new", "architectures": ["GPT2LMHeadModel"], "attn_pdrop": 0.1, "embd_pdrop": 0.1, "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": "2.16.372.0+4a9b2326", "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-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4e6fd20c0862130b2f01.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "attention_multiplier": 1.0, "bos_token_id": 1, "embedding_multiplier": 1.0, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 64, "logits_scaling": 1.0, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "pad_token_id": 0, "residual_multiplier": 1.0, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 49152}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/4ec24af550bea736dba0.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "attention_multiplier": 1.0, "bos_token_id": 1, "embedding_multiplier": 1.0, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 64, "logits_scaling": 1.0, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "pad_token_id": 0, "residual_multiplier": 1.0, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 49152}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/5188b60acf9ad77c8ef5.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "attention_multiplier": 1.0, "bos_token_id": 1, "embedding_multiplier": 1.0, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 64, "logits_scaling": 1.0, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "granite", "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "pad_token_id": 0, "residual_multiplier": 1.0, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 49152}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/7555805b6a593a366a21.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "attention_multiplier": 1.0, "bos_token_id": 1, "embedding_multiplier": 1.0, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 64, "logits_scaling": 1.0, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "pad_token_id": 0, "residual_multiplier": 1.0, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 49152}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/b2cf188b9d58ab827ad9.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "attention_multiplier": 1.0, "bos_token_id": 1, "embedding_multiplier": 1.0, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 64, "logits_scaling": 1.0, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "pad_token_id": 0, "residual_multiplier": 1.0, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 49152}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/b53f0d2daef297d8794a.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "attention_multiplier": 1.0, "bos_token_id": 1, "embedding_multiplier": 1.0, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 64, "logits_scaling": 1.0, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "pad_token_id": 0, "residual_multiplier": 1.0, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 49152}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/da9452c0fcbe80e153f5.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "attention_multiplier": 1.0, "bos_token_id": 1, "embedding_multiplier": 1.0, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 32, "initializer_range": 0.02, "intermediate_size": 64, "logits_scaling": 1.0, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "pad_token_id": 0, "residual_multiplier": 1.0, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 49152}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/ibm-granite/granite-3.1-2b-instruct/86817be9d58337936129.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.1, "attention_multiplier": 0.015625, "bos_token_id": 0, "embedding_multiplier": 12.0, "eos_token_id": 0, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "logits_scaling": 8.0, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", "checkpoint_revision": "374ef54e020a3ce208c65e96d6213922a87d8952", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096}, "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "pad_token_id": 0, "residual_multiplier": 0.22, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 5000000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 49155}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/ibm-granite/granite-3.1-2b-instruct/a2d65ee224bccfbf33c2.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "ibm-granite/granite-3.1-2b-instruct", "_task": "text-generation", "architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.1, "attention_multiplier": 0.015625, "embedding_multiplier": 12.0, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "logits_scaling": 8.0, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", "checkpoint_revision": "374ef54e020a3ce208c65e96d6213922a87d8952", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "residual_multiplier": 0.22, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 5000000.0, "tie_word_embeddings": true, "use_cache": true, "vocab_size": 49155}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/granite/ibm-granite/granite-3.1-2b-instruct/bf71032506a251068193.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["GraniteForCausalLM"], "attention_bias": false, "attention_dropout": 0.1, "attention_multiplier": 0.015625, "bos_token_id": 0, "embedding_multiplier": 12.0, "eos_token_id": 0, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "logits_scaling": 8.0, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "granite", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", "checkpoint_revision": "374ef54e020a3ce208c65e96d6213922a87d8952", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 8, "pad_token_id": 0, "residual_multiplier": 0.22, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 5000000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 49155}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/0af73583385b26dcf000.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], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "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": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/2e8cb42c92e334dfbaa9.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], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "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": {"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": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/51231e30eb944c5bc1f8.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], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 2, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 1, "sequence_length": 128, "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": {"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": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/5433fffb45752137c8de.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], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "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": {"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": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/588e5102c25f59898011.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], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 131072, "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": {"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": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/5c109283b389f09f634b.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], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 512, "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": {"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": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/648252251e4a8bcdcbed.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], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 2, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 128, "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": {"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": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/6af26305eda23594815e.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], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "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": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/8c48d1da1325809763e8.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], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "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": {"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": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/b3814f2986268efcd29c.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], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 131072}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "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": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/c74d843980295535d5ea.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], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "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": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/c7c2db71d0de15fb6862.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], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 4, "num_hidden_layers": 2, "num_key_value_heads": 4, "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": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/llamafactory/tiny-random-Llama-3/e76fd07fe3037f2e366b.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], "head_dim": 4, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 64, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "llamafactory/tiny-random-Llama-3", "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 1, "sequence_length": 512, "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": {"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": "float16", "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/unsloth/Llama-3.2-1B-Instruct/08c70e54d07a8a28e136.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", "checkpoint_revision": "9b58d4a36161a1e49ecf0a69d20b2736fef8e438", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096}, "num_attention_heads": 32, "num_hidden_layers": 16, "num_key_value_heads": 8, "pad_token_id": 128004, "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", "unsloth_fixed": true, "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/unsloth/Llama-3.2-1B-Instruct/49d61e18927b113552d1.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128009, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", "checkpoint_revision": "9b58d4a36161a1e49ecf0a69d20b2736fef8e438", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 16, "num_key_value_heads": 8, "pad_token_id": 128004, "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", "unsloth_fixed": true, "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/llama/unsloth/Llama-3.2-1B-Instruct/6ff803c42db4ecee05a3.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "unsloth/Llama-3.2-1B-Instruct", "_task": "text-generation", "architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "head_dim": 64, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", "checkpoint_revision": "9b58d4a36161a1e49ecf0a69d20b2736fef8e438", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 16, "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, "unsloth_fixed": true, "use_cache": true, "vocab_size": 128256}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mistral/optimum/mistral-1.1b-testing/26e0edb6fea0d3bc9667.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "optimum/mistral-1.1b-testing", "_task": "text-generation", "architectures": ["MistralForCausalLM"], "attention_dropout": 0.0, "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": "2.16.372.0+4a9b2326", "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, "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/mixtral/dacorvo/Mixtral-tiny/678cf23ea51877d5956c.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "dacorvo/Mixtral-tiny", "_task": "text-generation", "architectures": ["MixtralForCausalLM"], "attention_dropout": 0.0, "head_dim": 32, "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": "2.16.372.0+4a9b2326", "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, "use_cache": true, "vocab_size": 32000}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/microsoft/Phi-3-mini-4k-instruct/352a3518452cfb4a7d84.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {"AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"}, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 4096, "model_type": "phi3", "neuron": {"auto_cast_type": "bf16", "batch_size": 2, "checkpoint_id": "microsoft/Phi-3-mini-4k-instruct", "checkpoint_revision": "0a67737cc96d2554230f90338b163bc6380a2a85", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 1024}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "sliding_window": 2047, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32064}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/microsoft/Phi-3-mini-4k-instruct/89baef7b06c4231392e4.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {"AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"}, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 4096, "model_type": "phi3", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "microsoft/Phi-3-mini-4k-instruct", "checkpoint_revision": "0a67737cc96d2554230f90338b163bc6380a2a85", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "sliding_window": 2047, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32064}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/microsoft/Phi-3-mini-4k-instruct/9e1ede42fd1a2ceef459.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_entry_class": "SingleModelCacheEntry", "_model_id": "microsoft/Phi-3-mini-4k-instruct", "_task": "text-generation", "architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {"AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"}, "embd_pdrop": 0.0, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 4096, "model_type": "phi3", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "microsoft/Phi-3-mini-4k-instruct", "checkpoint_revision": "0a67737cc96d2554230f90338b163bc6380a2a85", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "sliding_window": 2047, "tie_word_embeddings": false, "use_cache": true, "vocab_size": 32064}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/microsoft/Phi-3-mini-4k-instruct/c9f481c0e2f6fd992637.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {"AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"}, "bos_token_id": 1, "embd_pdrop": 0.0, "eos_token_id": 32000, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 4096, "model_type": "phi3", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "microsoft/Phi-3-mini-4k-instruct", "checkpoint_revision": "0a67737cc96d2554230f90338b163bc6380a2a85", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "original_max_position_embeddings": 4096, "pad_token_id": 32000, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "sliding_window": 2047, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32064}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/05491c46e49b1857820c.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {}, "bos_token_id": 100257, "embd_pdrop": 0.0, "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 32, "max_position_embeddings": 16384, "model_type": "phi3", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "yujiepan/phi-4-tiny-random", "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 1, "original_max_position_embeddings": 16384, "pad_token_id": 100257, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 250000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 100352}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/4e88b70b02777e345f13.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {}, "bos_token_id": 100257, "embd_pdrop": 0.0, "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 32, "max_position_embeddings": 16384, "model_type": "phi3", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "yujiepan/phi-4-tiny-random", "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 1, "original_max_position_embeddings": 16384, "pad_token_id": 100257, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 250000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 100352}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/70bc53d4dc1ebe9f4e54.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {}, "bos_token_id": 100257, "embd_pdrop": 0.0, "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 32, "max_position_embeddings": 16384, "model_type": "phi3", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "yujiepan/phi-4-tiny-random", "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 1, "original_max_position_embeddings": 16384, "pad_token_id": 100257, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 250000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 100352}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/9854f57bdc6009b4290a.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {}, "bos_token_id": 100257, "embd_pdrop": 0.0, "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 32, "max_position_embeddings": 16384, "model_type": "phi3", "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 1, "original_max_position_embeddings": 16384, "pad_token_id": 100257, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 250000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 100352}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/aec03923c7147a6162cb.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {}, "bos_token_id": 100257, "embd_pdrop": 0.0, "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 32, "max_position_embeddings": 16384, "model_type": "phi3", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "yujiepan/phi-4-tiny-random", "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 1, "original_max_position_embeddings": 16384, "pad_token_id": 100257, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 250000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 100352}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/d82c490f84f2b1e1522c.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {}, "bos_token_id": 100257, "embd_pdrop": 0.0, "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 32, "max_position_embeddings": 16384, "model_type": "phi3", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "yujiepan/phi-4-tiny-random", "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100, "task": "text-generation"}, "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 1, "original_max_position_embeddings": 16384, "pad_token_id": 100257, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 250000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 100352}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/phi3/yujiepan/phi-4-tiny-random/f525ffd2f160d6993f6c.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Phi3ForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "auto_map": {}, "bos_token_id": 100257, "embd_pdrop": 0.0, "eos_token_id": 100257, "hidden_act": "silu", "hidden_size": 16, "initializer_range": 0.02, "intermediate_size": 32, "max_position_embeddings": 16384, "model_type": "phi3", "neuron": {"auto_cast_type": "fp16", "batch_size": 2, "checkpoint_id": "yujiepan/phi-4-tiny-random", "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 100}, "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 1, "original_max_position_embeddings": 16384, "pad_token_id": 100257, "partial_rotary_factor": 1.0, "resid_pdrop": 0.0, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 250000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 100352}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/qwen2/Qwen/Qwen2.5-0.5B/734242ffd55de3545f50.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 896, "initializer_range": 0.02, "intermediate_size": 4864, "max_position_embeddings": 32768, "max_window_layers": 24, "model_type": "qwen2", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "Qwen/Qwen2.5-0.5B", "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096}, "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/qwen2/Qwen/Qwen2.5-0.5B/9d442ba21d7a61100a33.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 896, "initializer_range": 0.02, "intermediate_size": 4864, "max_position_embeddings": 32768, "max_window_layers": 24, "model_type": "qwen2", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "Qwen/Qwen2.5-0.5B", "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 128}, "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/qwen2/Qwen/Qwen2.5-0.5B/e28ef40ae22096954a46.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 896, "initializer_range": 0.02, "intermediate_size": 4864, "max_position_embeddings": 32768, "max_window_layers": 24, "model_type": "qwen2", "neuron": {"auto_cast_type": "fp32", "batch_size": 1, "checkpoint_id": "Qwen/Qwen2.5-0.5B", "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 24, "sequence_length": 128, "task": "text-generation"}, "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936}
|
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.2.0.dev1/inference/qwen2/Qwen/Qwen2.5-0.5B/eb9dc14053f0f9d06257.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 896, "initializer_range": 0.02, "intermediate_size": 4864, "max_position_embeddings": 32768, "max_window_layers": 24, "model_type": "qwen2", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "Qwen/Qwen2.5-0.5B", "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936}
|