Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
266
dacorvo HF staff commited on
Commit
969d1f0
•
1 Parent(s): 6b8c4b2

Synchronizing local compiler cache.

Browse files
Files changed (42) hide show
  1. .gitattributes +10 -0
  2. neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-2-13b-hf/734f858405fa9bf8f065.json +1 -0
  3. neuronxcc-2.15.128.0+56dc5a86/MODULE_142bf066a5a47eca8300+39f12043/compile_flags.json +1 -0
  4. neuronxcc-2.15.128.0+56dc5a86/MODULE_142bf066a5a47eca8300+39f12043/model.done +0 -0
  5. neuronxcc-2.15.128.0+56dc5a86/MODULE_142bf066a5a47eca8300+39f12043/model.hlo_module.pb +3 -0
  6. neuronxcc-2.15.128.0+56dc5a86/MODULE_142bf066a5a47eca8300+39f12043/model.neff +3 -0
  7. neuronxcc-2.15.128.0+56dc5a86/MODULE_1ebc304f695e7b7b1e57+39f12043/compile_flags.json +1 -0
  8. neuronxcc-2.15.128.0+56dc5a86/MODULE_1ebc304f695e7b7b1e57+39f12043/model.done +0 -0
  9. neuronxcc-2.15.128.0+56dc5a86/MODULE_1ebc304f695e7b7b1e57+39f12043/model.hlo_module.pb +3 -0
  10. neuronxcc-2.15.128.0+56dc5a86/MODULE_1ebc304f695e7b7b1e57+39f12043/model.neff +3 -0
  11. neuronxcc-2.15.128.0+56dc5a86/MODULE_572dc16488c407ea9a3d+39f12043/compile_flags.json +1 -0
  12. neuronxcc-2.15.128.0+56dc5a86/MODULE_572dc16488c407ea9a3d+39f12043/model.done +0 -0
  13. neuronxcc-2.15.128.0+56dc5a86/MODULE_572dc16488c407ea9a3d+39f12043/model.hlo_module.pb +3 -0
  14. neuronxcc-2.15.128.0+56dc5a86/MODULE_572dc16488c407ea9a3d+39f12043/model.neff +3 -0
  15. neuronxcc-2.15.128.0+56dc5a86/MODULE_572e9db05447b8aa9526+39f12043/compile_flags.json +1 -0
  16. neuronxcc-2.15.128.0+56dc5a86/MODULE_572e9db05447b8aa9526+39f12043/model.done +0 -0
  17. neuronxcc-2.15.128.0+56dc5a86/MODULE_572e9db05447b8aa9526+39f12043/model.hlo_module.pb +3 -0
  18. neuronxcc-2.15.128.0+56dc5a86/MODULE_572e9db05447b8aa9526+39f12043/model.neff +3 -0
  19. neuronxcc-2.15.128.0+56dc5a86/MODULE_5ff2d90d324127fd1e46+39f12043/compile_flags.json +1 -0
  20. neuronxcc-2.15.128.0+56dc5a86/MODULE_5ff2d90d324127fd1e46+39f12043/model.done +0 -0
  21. neuronxcc-2.15.128.0+56dc5a86/MODULE_5ff2d90d324127fd1e46+39f12043/model.hlo_module.pb +3 -0
  22. neuronxcc-2.15.128.0+56dc5a86/MODULE_5ff2d90d324127fd1e46+39f12043/model.neff +3 -0
  23. neuronxcc-2.15.128.0+56dc5a86/MODULE_653735eb3b429018aab2+39f12043/compile_flags.json +1 -0
  24. neuronxcc-2.15.128.0+56dc5a86/MODULE_653735eb3b429018aab2+39f12043/model.done +0 -0
  25. neuronxcc-2.15.128.0+56dc5a86/MODULE_653735eb3b429018aab2+39f12043/model.hlo_module.pb +3 -0
  26. neuronxcc-2.15.128.0+56dc5a86/MODULE_653735eb3b429018aab2+39f12043/model.neff +3 -0
  27. neuronxcc-2.15.128.0+56dc5a86/MODULE_73bcbea1321d4f308214+39f12043/compile_flags.json +1 -0
  28. neuronxcc-2.15.128.0+56dc5a86/MODULE_73bcbea1321d4f308214+39f12043/model.done +0 -0
  29. neuronxcc-2.15.128.0+56dc5a86/MODULE_73bcbea1321d4f308214+39f12043/model.hlo_module.pb +3 -0
  30. neuronxcc-2.15.128.0+56dc5a86/MODULE_73bcbea1321d4f308214+39f12043/model.neff +3 -0
  31. neuronxcc-2.15.128.0+56dc5a86/MODULE_9638b947fc9a3205a11b+39f12043/compile_flags.json +1 -0
  32. neuronxcc-2.15.128.0+56dc5a86/MODULE_9638b947fc9a3205a11b+39f12043/model.done +0 -0
  33. neuronxcc-2.15.128.0+56dc5a86/MODULE_9638b947fc9a3205a11b+39f12043/model.hlo_module.pb +3 -0
  34. neuronxcc-2.15.128.0+56dc5a86/MODULE_9638b947fc9a3205a11b+39f12043/model.neff +3 -0
  35. neuronxcc-2.15.128.0+56dc5a86/MODULE_9e31d00ce0adfb1cf4e6+39f12043/compile_flags.json +1 -0
  36. neuronxcc-2.15.128.0+56dc5a86/MODULE_9e31d00ce0adfb1cf4e6+39f12043/model.done +0 -0
  37. neuronxcc-2.15.128.0+56dc5a86/MODULE_9e31d00ce0adfb1cf4e6+39f12043/model.hlo_module.pb +3 -0
  38. neuronxcc-2.15.128.0+56dc5a86/MODULE_9e31d00ce0adfb1cf4e6+39f12043/model.neff +3 -0
  39. neuronxcc-2.15.128.0+56dc5a86/MODULE_f07c0820470764b5a8dc+39f12043/compile_flags.json +1 -0
  40. neuronxcc-2.15.128.0+56dc5a86/MODULE_f07c0820470764b5a8dc+39f12043/model.done +0 -0
  41. neuronxcc-2.15.128.0+56dc5a86/MODULE_f07c0820470764b5a8dc+39f12043/model.hlo_module.pb +3 -0
  42. neuronxcc-2.15.128.0+56dc5a86/MODULE_f07c0820470764b5a8dc+39f12043/model.neff +3 -0
.gitattributes CHANGED
@@ -5409,3 +5409,13 @@ neuronxcc-2.15.128.0+56dc5a86/MODULE_62ada366ccf3e1af7292+39f12043/model.neff fi
5409
  neuronxcc-2.15.128.0+56dc5a86/MODULE_b4565b110ebb894b3a65+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5410
  neuronxcc-2.15.128.0+56dc5a86/MODULE_091023fc188e437f3326+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5411
  neuronxcc-2.15.128.0+56dc5a86/MODULE_9fc5ad66b5a87a122dee+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
5409
  neuronxcc-2.15.128.0+56dc5a86/MODULE_b4565b110ebb894b3a65+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5410
  neuronxcc-2.15.128.0+56dc5a86/MODULE_091023fc188e437f3326+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5411
  neuronxcc-2.15.128.0+56dc5a86/MODULE_9fc5ad66b5a87a122dee+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5412
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_142bf066a5a47eca8300+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5413
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_1ebc304f695e7b7b1e57+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5414
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_572dc16488c407ea9a3d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5415
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_572e9db05447b8aa9526+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5416
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_5ff2d90d324127fd1e46+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5417
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_653735eb3b429018aab2+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5418
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_73bcbea1321d4f308214+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5419
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_9638b947fc9a3205a11b+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5420
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_9e31d00ce0adfb1cf4e6+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5421
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_f07c0820470764b5a8dc+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.15.128.0+56dc5a86/0_REGISTRY/0.0.25.dev0/inference/llama/meta-llama/Llama-2-13b-hf/734f858405fa9bf8f065.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-13b-hf", "checkpoint_revision": "5c31dfb671ce7cfe2d7bb7c04375e44c55e815b1", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 8, "sequence_length": 2048, "task": "text-generation"}, "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 40, "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": 32000}
neuronxcc-2.15.128.0+56dc5a86/MODULE_142bf066a5a47eca8300+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_142bf066a5a47eca8300+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_142bf066a5a47eca8300+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e04987a569ba4c663a6efd196941c830ef7c2a34605c777c3a303a654e4d92b
3
+ size 385280
neuronxcc-2.15.128.0+56dc5a86/MODULE_142bf066a5a47eca8300+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adbfc8ed5de4ff6afe9ab2bd38a76bbd33d377f3ada0a2822837e23ea78ed778
3
+ size 3943424
neuronxcc-2.15.128.0+56dc5a86/MODULE_1ebc304f695e7b7b1e57+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_1ebc304f695e7b7b1e57+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_1ebc304f695e7b7b1e57+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7bd0f9486a697da30e111c0ee977c674853538a0de8379fe5c29a7a80d8ff60
3
+ size 301474
neuronxcc-2.15.128.0+56dc5a86/MODULE_1ebc304f695e7b7b1e57+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e99c379b98009ceeaddd8ce4c93831a79bb213c7cd42606d8053444309b7b97
3
+ size 4547584
neuronxcc-2.15.128.0+56dc5a86/MODULE_572dc16488c407ea9a3d+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_572dc16488c407ea9a3d+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_572dc16488c407ea9a3d+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d871b15d1dc1899f81cccedca286927b8a5f57027eacbdb36a514028dd102c
3
+ size 305665
neuronxcc-2.15.128.0+56dc5a86/MODULE_572dc16488c407ea9a3d+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef08efa48905693f0a5bbb40fbd88481b3caec8146e662fcb68ea0c74dc0d658
3
+ size 3800064
neuronxcc-2.15.128.0+56dc5a86/MODULE_572e9db05447b8aa9526+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_572e9db05447b8aa9526+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_572e9db05447b8aa9526+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c970528f038f5af2198b2c9dc50269935b0e2386310893366b1fc89e6d05799
3
+ size 305665
neuronxcc-2.15.128.0+56dc5a86/MODULE_572e9db05447b8aa9526+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e608ff196097cd66c53055515e1406a87b6dd03c2fba0d9067649ecd8e448f50
3
+ size 13026304
neuronxcc-2.15.128.0+56dc5a86/MODULE_5ff2d90d324127fd1e46+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_5ff2d90d324127fd1e46+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_5ff2d90d324127fd1e46+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb246fffa8eeed9bf1cde8a383c5907bc5686c0ab9324c61f1fb041601ac936a
3
+ size 385280
neuronxcc-2.15.128.0+56dc5a86/MODULE_5ff2d90d324127fd1e46+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cde8b4b7ce296df3e90e8278a2a8a003a53f07619fa4acc56dc57f591ea93db3
3
+ size 4445184
neuronxcc-2.15.128.0+56dc5a86/MODULE_653735eb3b429018aab2+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_653735eb3b429018aab2+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_653735eb3b429018aab2+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6efda5b5b6207093f65e5a96bedd43af83b3860b7ec07034e05a6e75ccb9cf39
3
+ size 305665
neuronxcc-2.15.128.0+56dc5a86/MODULE_653735eb3b429018aab2+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b3684d8b4555ee5415ddb0805cbd4505acbc83828a22c0b7d45953c5d2471b9
3
+ size 7025664
neuronxcc-2.15.128.0+56dc5a86/MODULE_73bcbea1321d4f308214+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_73bcbea1321d4f308214+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_73bcbea1321d4f308214+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5abd8392a67fa3f01be89f9f1d7a66b510307b8b9310823907098af24371d7b3
3
+ size 385280
neuronxcc-2.15.128.0+56dc5a86/MODULE_73bcbea1321d4f308214+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c736fa6e9abb72cc89ded2ee446e03dec6a4d89bc7b8fd6910c2c7cb5ba7efe
3
+ size 4178944
neuronxcc-2.15.128.0+56dc5a86/MODULE_9638b947fc9a3205a11b+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_9638b947fc9a3205a11b+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_9638b947fc9a3205a11b+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9d72b3d8b8304287504620b51225b7b708546d23fcd874dec9e43381b5c6fc0
3
+ size 385280
neuronxcc-2.15.128.0+56dc5a86/MODULE_9638b947fc9a3205a11b+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f167157e72992def3e914654a7b50b07fe2d4efcd00799b6d7e35b14deae6eda
3
+ size 4025344
neuronxcc-2.15.128.0+56dc5a86/MODULE_9e31d00ce0adfb1cf4e6+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_9e31d00ce0adfb1cf4e6+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_9e31d00ce0adfb1cf4e6+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8858ae0d3d8187cfc67715de8360a15d4a03e67c754a4c180f8d4b386b3a2a33
3
+ size 385280
neuronxcc-2.15.128.0+56dc5a86/MODULE_9e31d00ce0adfb1cf4e6+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6159d41fdad9dd315ab978bfe461d1d584314d249f808e9243d85b0952505ee
3
+ size 3922944
neuronxcc-2.15.128.0+56dc5a86/MODULE_f07c0820470764b5a8dc+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.128.0+56dc5a86/MODULE_f07c0820470764b5a8dc+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_f07c0820470764b5a8dc+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:276e41010ae230286f492abae5304a35cd7b350b7603af5a0bc2144a497a99ac
3
+ size 305665
neuronxcc-2.15.128.0+56dc5a86/MODULE_f07c0820470764b5a8dc+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc7a452b1f449d5173a42439bed642b96ce71fca5c2f296b921c0e96a1448ede
3
+ size 4649984