Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
281
dacorvo HF staff commited on
Commit
31506f3
•
1 Parent(s): 40009f1

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-2-7b-hf/d1390694eb4a8f28a5fe.json +1 -0
  3. neuronxcc-2.15.128.0+56dc5a86/MODULE_1bcb1bae12fef94166bc+39f12043/compile_flags.json +1 -0
  4. neuronxcc-2.15.128.0+56dc5a86/MODULE_1bcb1bae12fef94166bc+39f12043/model.done +0 -0
  5. neuronxcc-2.15.128.0+56dc5a86/MODULE_1bcb1bae12fef94166bc+39f12043/model.hlo_module.pb +3 -0
  6. neuronxcc-2.15.128.0+56dc5a86/MODULE_1bcb1bae12fef94166bc+39f12043/model.neff +3 -0
  7. neuronxcc-2.15.128.0+56dc5a86/MODULE_2ed28cff6f3febea03ca+39f12043/compile_flags.json +1 -0
  8. neuronxcc-2.15.128.0+56dc5a86/MODULE_2ed28cff6f3febea03ca+39f12043/model.done +0 -0
  9. neuronxcc-2.15.128.0+56dc5a86/MODULE_2ed28cff6f3febea03ca+39f12043/model.hlo_module.pb +3 -0
  10. neuronxcc-2.15.128.0+56dc5a86/MODULE_2ed28cff6f3febea03ca+39f12043/model.neff +3 -0
  11. neuronxcc-2.15.128.0+56dc5a86/MODULE_5319f765df706fa2f93c+39f12043/compile_flags.json +1 -0
  12. neuronxcc-2.15.128.0+56dc5a86/MODULE_5319f765df706fa2f93c+39f12043/model.done +0 -0
  13. neuronxcc-2.15.128.0+56dc5a86/MODULE_5319f765df706fa2f93c+39f12043/model.hlo_module.pb +3 -0
  14. neuronxcc-2.15.128.0+56dc5a86/MODULE_5319f765df706fa2f93c+39f12043/model.neff +3 -0
  15. neuronxcc-2.15.128.0+56dc5a86/MODULE_5b6458ef52f0b35e3529+39f12043/compile_flags.json +1 -0
  16. neuronxcc-2.15.128.0+56dc5a86/MODULE_5b6458ef52f0b35e3529+39f12043/model.done +0 -0
  17. neuronxcc-2.15.128.0+56dc5a86/MODULE_5b6458ef52f0b35e3529+39f12043/model.hlo_module.pb +3 -0
  18. neuronxcc-2.15.128.0+56dc5a86/MODULE_5b6458ef52f0b35e3529+39f12043/model.neff +3 -0
  19. neuronxcc-2.15.128.0+56dc5a86/MODULE_8740d72c52a3102211f8+39f12043/compile_flags.json +1 -0
  20. neuronxcc-2.15.128.0+56dc5a86/MODULE_8740d72c52a3102211f8+39f12043/model.done +0 -0
  21. neuronxcc-2.15.128.0+56dc5a86/MODULE_8740d72c52a3102211f8+39f12043/model.hlo_module.pb +3 -0
  22. neuronxcc-2.15.128.0+56dc5a86/MODULE_8740d72c52a3102211f8+39f12043/model.neff +3 -0
  23. neuronxcc-2.15.128.0+56dc5a86/MODULE_97b5667b75189a07ec14+39f12043/compile_flags.json +1 -0
  24. neuronxcc-2.15.128.0+56dc5a86/MODULE_97b5667b75189a07ec14+39f12043/model.done +0 -0
  25. neuronxcc-2.15.128.0+56dc5a86/MODULE_97b5667b75189a07ec14+39f12043/model.hlo_module.pb +3 -0
  26. neuronxcc-2.15.128.0+56dc5a86/MODULE_97b5667b75189a07ec14+39f12043/model.neff +3 -0
  27. neuronxcc-2.15.128.0+56dc5a86/MODULE_c3aef552cbd11f76a966+39f12043/compile_flags.json +1 -0
  28. neuronxcc-2.15.128.0+56dc5a86/MODULE_c3aef552cbd11f76a966+39f12043/model.done +0 -0
  29. neuronxcc-2.15.128.0+56dc5a86/MODULE_c3aef552cbd11f76a966+39f12043/model.hlo_module.pb +3 -0
  30. neuronxcc-2.15.128.0+56dc5a86/MODULE_c3aef552cbd11f76a966+39f12043/model.neff +3 -0
  31. neuronxcc-2.15.128.0+56dc5a86/MODULE_ca6f2ce30d040115ac4d+39f12043/compile_flags.json +1 -0
  32. neuronxcc-2.15.128.0+56dc5a86/MODULE_ca6f2ce30d040115ac4d+39f12043/model.done +0 -0
  33. neuronxcc-2.15.128.0+56dc5a86/MODULE_ca6f2ce30d040115ac4d+39f12043/model.hlo_module.pb +3 -0
  34. neuronxcc-2.15.128.0+56dc5a86/MODULE_ca6f2ce30d040115ac4d+39f12043/model.neff +3 -0
  35. neuronxcc-2.15.128.0+56dc5a86/MODULE_d49217ce8ddca55aef51+39f12043/compile_flags.json +1 -0
  36. neuronxcc-2.15.128.0+56dc5a86/MODULE_d49217ce8ddca55aef51+39f12043/model.done +0 -0
  37. neuronxcc-2.15.128.0+56dc5a86/MODULE_d49217ce8ddca55aef51+39f12043/model.hlo_module.pb +3 -0
  38. neuronxcc-2.15.128.0+56dc5a86/MODULE_d49217ce8ddca55aef51+39f12043/model.neff +3 -0
  39. neuronxcc-2.15.128.0+56dc5a86/MODULE_ff11da2e783fee573571+39f12043/compile_flags.json +1 -0
  40. neuronxcc-2.15.128.0+56dc5a86/MODULE_ff11da2e783fee573571+39f12043/model.done +0 -0
  41. neuronxcc-2.15.128.0+56dc5a86/MODULE_ff11da2e783fee573571+39f12043/model.hlo_module.pb +3 -0
  42. neuronxcc-2.15.128.0+56dc5a86/MODULE_ff11da2e783fee573571+39f12043/model.neff +3 -0
.gitattributes CHANGED
@@ -5393,3 +5393,13 @@ neuronxcc-2.15.128.0+56dc5a86/MODULE_ebdda490678939e19229+39f12043/model.neff fi
5393
  neuronxcc-2.15.128.0+56dc5a86/MODULE_f2e3c691fdaec05bf0ee+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5394
  neuronxcc-2.15.128.0+56dc5a86/MODULE_e502e1959b03c3df69bc+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5395
  neuronxcc-2.15.128.0+56dc5a86/MODULE_fa6736ef35ec47a57315+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
5393
  neuronxcc-2.15.128.0+56dc5a86/MODULE_f2e3c691fdaec05bf0ee+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5394
  neuronxcc-2.15.128.0+56dc5a86/MODULE_e502e1959b03c3df69bc+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5395
  neuronxcc-2.15.128.0+56dc5a86/MODULE_fa6736ef35ec47a57315+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5396
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_1bcb1bae12fef94166bc+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5397
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_2ed28cff6f3febea03ca+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5398
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_5319f765df706fa2f93c+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5399
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_5b6458ef52f0b35e3529+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5400
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_8740d72c52a3102211f8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5401
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_97b5667b75189a07ec14+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5402
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_c3aef552cbd11f76a966+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5403
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_ca6f2ce30d040115ac4d+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5404
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_d49217ce8ddca55aef51+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
5405
+ neuronxcc-2.15.128.0+56dc5a86/MODULE_ff11da2e783fee573571+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-2-7b-hf/d1390694eb4a8f28a5fe.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": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-7b-hf", "checkpoint_revision": "01c7f73d771dfac7d292323805ebc428287df4f9", "compiler_type": "neuronx-cc", "compiler_version": "2.15.128.0+56dc5a86", "num_cores": 2, "sequence_length": 2048, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "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_1bcb1bae12fef94166bc+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_1bcb1bae12fef94166bc+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_1bcb1bae12fef94166bc+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d8fa12c50c81bddfe1d0c2bc20012df8cce22ed4537ad5330ac14cdb81249ab
3
+ size 308048
neuronxcc-2.15.128.0+56dc5a86/MODULE_1bcb1bae12fef94166bc+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35b8598501055474c84813a66c74a4da41e2b1058be0b1883d3b2e60148d8240
3
+ size 6892544
neuronxcc-2.15.128.0+56dc5a86/MODULE_2ed28cff6f3febea03ca+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_2ed28cff6f3febea03ca+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_2ed28cff6f3febea03ca+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74405019aabbaeccda87458873696c7a114a09eac4709ee8a8b7318dd4da3bfd
3
+ size 244385
neuronxcc-2.15.128.0+56dc5a86/MODULE_2ed28cff6f3febea03ca+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc262a75a271c40f42abb6b0721652be7cc93f6044753d7b7cc83df65fa78e7
3
+ size 10640384
neuronxcc-2.15.128.0+56dc5a86/MODULE_5319f765df706fa2f93c+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_5319f765df706fa2f93c+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_5319f765df706fa2f93c+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a8ca63203b10b3adf63212aaa1d6f74ba382d29b93e4a9be35a70ca0ce8e481
3
+ size 308048
neuronxcc-2.15.128.0+56dc5a86/MODULE_5319f765df706fa2f93c+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90bafec9ea048553aef1d6094bdc1f3589cc9e8358e277aaaae23d7073b599ab
3
+ size 6646784
neuronxcc-2.15.128.0+56dc5a86/MODULE_5b6458ef52f0b35e3529+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_5b6458ef52f0b35e3529+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_5b6458ef52f0b35e3529+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38c418836e1ee4a4de6bb9939ce2a7a690f42cc3061bff94b435c0e3c818e582
3
+ size 308048
neuronxcc-2.15.128.0+56dc5a86/MODULE_5b6458ef52f0b35e3529+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73be93d606f756a494881494637d57c6ae90860c19235e8d0deb44060884ab17
3
+ size 7414784
neuronxcc-2.15.128.0+56dc5a86/MODULE_8740d72c52a3102211f8+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_8740d72c52a3102211f8+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_8740d72c52a3102211f8+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fded41241bc8489c743cda5af7be9f0971ba341dc6c74dd695fa7f8fe86988f
3
+ size 244385
neuronxcc-2.15.128.0+56dc5a86/MODULE_8740d72c52a3102211f8+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d20a8c3d4b40d58efb3d75378804d784f0e4dc2eae554ebcee0f17351d3baeb6
3
+ size 9933824
neuronxcc-2.15.128.0+56dc5a86/MODULE_97b5667b75189a07ec14+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_97b5667b75189a07ec14+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_97b5667b75189a07ec14+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bac2b9d40503f9642cc879352b5e482249a5fb544ff44c3130bcd8bdc11ceea6
3
+ size 241026
neuronxcc-2.15.128.0+56dc5a86/MODULE_97b5667b75189a07ec14+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5e40fe9f33d650b1c42b1a20a7b0a17f576a2c46656b4fb1130dc599d0a72c5
3
+ size 7998464
neuronxcc-2.15.128.0+56dc5a86/MODULE_c3aef552cbd11f76a966+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_c3aef552cbd11f76a966+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_c3aef552cbd11f76a966+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2188a642788f6abf7705a38e647ce834c0c97e085377ab6b2f3581a4a8ffc34
3
+ size 308048
neuronxcc-2.15.128.0+56dc5a86/MODULE_c3aef552cbd11f76a966+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16f1179bf1f64ebbb73419f9d92459db8dd788beaeac6cad497b93d15a5fb006
3
+ size 6482944
neuronxcc-2.15.128.0+56dc5a86/MODULE_ca6f2ce30d040115ac4d+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_ca6f2ce30d040115ac4d+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_ca6f2ce30d040115ac4d+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d57b0544aec5b750455af2ac6f42dd13ce39a41708fcb13c6b5e6f4ffc58d1ac
3
+ size 244385
neuronxcc-2.15.128.0+56dc5a86/MODULE_ca6f2ce30d040115ac4d+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b5a52aaf872bad3dcfaf7ade781255656f581f2e8844631586378ada6a7bdc
3
+ size 21371904
neuronxcc-2.15.128.0+56dc5a86/MODULE_d49217ce8ddca55aef51+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_d49217ce8ddca55aef51+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_d49217ce8ddca55aef51+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ef76e3ec44f6b59aa65e6aa371a3922a6785ff52c41453afdb427e008ea8e7b
3
+ size 308048
neuronxcc-2.15.128.0+56dc5a86/MODULE_d49217ce8ddca55aef51+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b2f284e5fb65d612250493790e63cbb378b63948985ecbabff9e05fa79d45cd
3
+ size 6431744
neuronxcc-2.15.128.0+56dc5a86/MODULE_ff11da2e783fee573571+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_ff11da2e783fee573571+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.128.0+56dc5a86/MODULE_ff11da2e783fee573571+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e5783e752993ffbee08a62f8669a6e8111979eea0634ba6ace4232111a79283
3
+ size 244385
neuronxcc-2.15.128.0+56dc5a86/MODULE_ff11da2e783fee573571+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0956fc47e345927524a89e48ab0a9c57954daecf3b11499ade14deaf7218829f
3
+ size 8725504