Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
205
dacorvo HF staff commited on
Commit
41a16cc
•
1 Parent(s): fb565b4

Synchronizing local compiler cache.

Browse files
Files changed (38) hide show
  1. .gitattributes +12 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19.dev0/inference/llama/NousResearch/Llama-2-13b-chat-hf/190a7b1844748ebd6f79.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_276efc749f5da324ae22+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_276efc749f5da324ae22+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_276efc749f5da324ae22+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_3605c6371f16a1adcc32+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_3605c6371f16a1adcc32+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_3605c6371f16a1adcc32+2c2d707e/model.neff +3 -0
  9. neuronxcc-2.12.68.0+4480452af/MODULE_38467f1d12268fd8dbf9+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.12.68.0+4480452af/MODULE_38467f1d12268fd8dbf9+2c2d707e/model.hlo.pb +3 -0
  11. neuronxcc-2.12.68.0+4480452af/MODULE_38467f1d12268fd8dbf9+2c2d707e/model.neff +3 -0
  12. neuronxcc-2.12.68.0+4480452af/MODULE_438cd8062b5c42fb5257+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.12.68.0+4480452af/MODULE_438cd8062b5c42fb5257+2c2d707e/model.hlo.pb +3 -0
  14. neuronxcc-2.12.68.0+4480452af/MODULE_438cd8062b5c42fb5257+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.12.68.0+4480452af/MODULE_6c524bf84dc7abaad876+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.12.68.0+4480452af/MODULE_6c524bf84dc7abaad876+2c2d707e/model.hlo.pb +3 -0
  17. neuronxcc-2.12.68.0+4480452af/MODULE_6c524bf84dc7abaad876+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.12.68.0+4480452af/MODULE_8d399b75f06f539a3160+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.12.68.0+4480452af/MODULE_8d399b75f06f539a3160+2c2d707e/model.hlo.pb +3 -0
  20. neuronxcc-2.12.68.0+4480452af/MODULE_8d399b75f06f539a3160+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.12.68.0+4480452af/MODULE_9c0022e28ed4ea762154+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.12.68.0+4480452af/MODULE_9c0022e28ed4ea762154+2c2d707e/model.hlo.pb +3 -0
  23. neuronxcc-2.12.68.0+4480452af/MODULE_9c0022e28ed4ea762154+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.12.68.0+4480452af/MODULE_a3f018cbfdf372632114+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.12.68.0+4480452af/MODULE_a3f018cbfdf372632114+2c2d707e/model.hlo.pb +3 -0
  26. neuronxcc-2.12.68.0+4480452af/MODULE_a3f018cbfdf372632114+2c2d707e/model.neff +3 -0
  27. neuronxcc-2.12.68.0+4480452af/MODULE_b2141128e8c260905609+2c2d707e/compile_flags.txt +1 -0
  28. neuronxcc-2.12.68.0+4480452af/MODULE_b2141128e8c260905609+2c2d707e/model.hlo.pb +3 -0
  29. neuronxcc-2.12.68.0+4480452af/MODULE_b2141128e8c260905609+2c2d707e/model.neff +3 -0
  30. neuronxcc-2.12.68.0+4480452af/MODULE_c17d7032769c2f5202a8+2c2d707e/compile_flags.txt +1 -0
  31. neuronxcc-2.12.68.0+4480452af/MODULE_c17d7032769c2f5202a8+2c2d707e/model.hlo.pb +3 -0
  32. neuronxcc-2.12.68.0+4480452af/MODULE_c17d7032769c2f5202a8+2c2d707e/model.neff +3 -0
  33. neuronxcc-2.12.68.0+4480452af/MODULE_cc7c23b7d4695ed92fc9+2c2d707e/compile_flags.txt +1 -0
  34. neuronxcc-2.12.68.0+4480452af/MODULE_cc7c23b7d4695ed92fc9+2c2d707e/model.hlo.pb +3 -0
  35. neuronxcc-2.12.68.0+4480452af/MODULE_cc7c23b7d4695ed92fc9+2c2d707e/model.neff +3 -0
  36. neuronxcc-2.12.68.0+4480452af/MODULE_cd132d5ec27bc45aa15f+2c2d707e/compile_flags.txt +1 -0
  37. neuronxcc-2.12.68.0+4480452af/MODULE_cd132d5ec27bc45aa15f+2c2d707e/model.hlo.pb +3 -0
  38. neuronxcc-2.12.68.0+4480452af/MODULE_cd132d5ec27bc45aa15f+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -994,3 +994,15 @@ neuronxcc-2.12.68.0+4480452af/MODULE_688375d84026af8f7c57+2c2d707e/model.neff fi
994
  neuronxcc-2.12.68.0+4480452af/MODULE_7714327f48e85f09fd03+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
995
  neuronxcc-2.12.68.0+4480452af/MODULE_afb3b0eeaa2511ec5efd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
996
  neuronxcc-2.12.68.0+4480452af/MODULE_e053a935644ddb80b9eb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
994
  neuronxcc-2.12.68.0+4480452af/MODULE_7714327f48e85f09fd03+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
995
  neuronxcc-2.12.68.0+4480452af/MODULE_afb3b0eeaa2511ec5efd+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
996
  neuronxcc-2.12.68.0+4480452af/MODULE_e053a935644ddb80b9eb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
997
+ neuronxcc-2.12.68.0+4480452af/MODULE_276efc749f5da324ae22+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
998
+ neuronxcc-2.12.68.0+4480452af/MODULE_3605c6371f16a1adcc32+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
999
+ neuronxcc-2.12.68.0+4480452af/MODULE_38467f1d12268fd8dbf9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1000
+ neuronxcc-2.12.68.0+4480452af/MODULE_438cd8062b5c42fb5257+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1001
+ neuronxcc-2.12.68.0+4480452af/MODULE_6c524bf84dc7abaad876+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1002
+ neuronxcc-2.12.68.0+4480452af/MODULE_8d399b75f06f539a3160+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1003
+ neuronxcc-2.12.68.0+4480452af/MODULE_9c0022e28ed4ea762154+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1004
+ neuronxcc-2.12.68.0+4480452af/MODULE_a3f018cbfdf372632114+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1005
+ neuronxcc-2.12.68.0+4480452af/MODULE_b2141128e8c260905609+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1006
+ neuronxcc-2.12.68.0+4480452af/MODULE_c17d7032769c2f5202a8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1007
+ neuronxcc-2.12.68.0+4480452af/MODULE_cc7c23b7d4695ed92fc9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1008
+ neuronxcc-2.12.68.0+4480452af/MODULE_cd132d5ec27bc45aa15f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19.dev0/inference/llama/NousResearch/Llama-2-13b-chat-hf/190a7b1844748ebd6f79.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "pad_token_id": 0, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 8, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "NousResearch/Llama-2-13b-chat-hf", "checkpoint_revision": "aad3c0b2315a458d54cd9b09ddc51cf06021196f"}}
neuronxcc-2.12.68.0+4480452af/MODULE_276efc749f5da324ae22+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_276efc749f5da324ae22+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6906e06eaea76a44dfc9dd75be56656aa7cc06c1dceb18151bd3c869b5fdebea
3
+ size 376449
neuronxcc-2.12.68.0+4480452af/MODULE_276efc749f5da324ae22+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cea19427d07de7c85f662ca8d5f5ded1cb44dd7e30033171809f72a819aa086
3
+ size 4281344
neuronxcc-2.12.68.0+4480452af/MODULE_3605c6371f16a1adcc32+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_3605c6371f16a1adcc32+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb1bd420a8a92f587eb507038a6c3fa15c56fea78d61ca1a1f18a0ceade9b4cc
3
+ size 376449
neuronxcc-2.12.68.0+4480452af/MODULE_3605c6371f16a1adcc32+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349cca31cfced1e1406ca89c37d80907259c37161644a6f0fea7c4e05869fe62
3
+ size 4475904
neuronxcc-2.12.68.0+4480452af/MODULE_38467f1d12268fd8dbf9+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_38467f1d12268fd8dbf9+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bd712ba9709a7823b825562cb61e6c9103f3c2336acbd130e65dcf7ae810be5
3
+ size 376449
neuronxcc-2.12.68.0+4480452af/MODULE_38467f1d12268fd8dbf9+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8799548076109195a6c7cdecae4b0b7d6c2b068218b97917146e4ea016c7fd3a
3
+ size 4660224
neuronxcc-2.12.68.0+4480452af/MODULE_438cd8062b5c42fb5257+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_438cd8062b5c42fb5257+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7cc24da3561b0147a7db8f18e4ef31f6b12db76e903d6f8458e65837d77fa9c
3
+ size 372234
neuronxcc-2.12.68.0+4480452af/MODULE_438cd8062b5c42fb5257+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36f4d1afcc3dab5164f75aaf049f4e90201ca9350249e312def2b31a0715c546
3
+ size 5458944
neuronxcc-2.12.68.0+4480452af/MODULE_6c524bf84dc7abaad876+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_6c524bf84dc7abaad876+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900dc7e746ec75a7672439a06f9f875ef695cfd805a88aa2d675f9ec10fce188
3
+ size 372234
neuronxcc-2.12.68.0+4480452af/MODULE_6c524bf84dc7abaad876+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c79d67cd1966987c4ef823430221db26b2a079aab5d30d820b521f05d3001ffc
3
+ size 4660224
neuronxcc-2.12.68.0+4480452af/MODULE_8d399b75f06f539a3160+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_8d399b75f06f539a3160+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:442ad6f40137aed370b81ff1d9b8812b96ebd1c6adcf1c994b0ab107bcf9588b
3
+ size 372234
neuronxcc-2.12.68.0+4480452af/MODULE_8d399b75f06f539a3160+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:378cb39873db6f81d55ce3747b377480801b7c30ca36c661ff02f5191f062597
3
+ size 24075264
neuronxcc-2.12.68.0+4480452af/MODULE_9c0022e28ed4ea762154+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_9c0022e28ed4ea762154+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42c3dba7e79fd74e0eba666d135be5084113ef5422e880e7c0ff434c437cbdb9
3
+ size 372234
neuronxcc-2.12.68.0+4480452af/MODULE_9c0022e28ed4ea762154+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8268126c2cacca20389c1e56d0795f4a08a7a503bbfe85d25195998a23212647
3
+ size 6452224
neuronxcc-2.12.68.0+4480452af/MODULE_a3f018cbfdf372632114+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_a3f018cbfdf372632114+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:390a380feb4d8f0aeecb4604d13de3f5f3b0bd01ae06d7cc6475e178d07e35f2
3
+ size 367643
neuronxcc-2.12.68.0+4480452af/MODULE_a3f018cbfdf372632114+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d6a10a427b5b0832edbb9e6c23e8f157143df3d8307b07f6daa5710e23333ca
3
+ size 4609024
neuronxcc-2.12.68.0+4480452af/MODULE_b2141128e8c260905609+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_b2141128e8c260905609+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a24bc1ecfd26367e0aaec4bc616747c87f2f682cfd07302d12b1ec916767752a
3
+ size 376449
neuronxcc-2.12.68.0+4480452af/MODULE_b2141128e8c260905609+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:450c99aa8ae9ca1e53ea0a4de4810df0b945543236d04ddcadc829f4ff36035b
3
+ size 4353024
neuronxcc-2.12.68.0+4480452af/MODULE_c17d7032769c2f5202a8+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_c17d7032769c2f5202a8+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1fc6afb06d05725f3605e270a5d7e0037aa9ca12ec1af2849295c1d993ee992
3
+ size 376449
neuronxcc-2.12.68.0+4480452af/MODULE_c17d7032769c2f5202a8+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c62974df1a9b078eb7a0e42c3d6976b5f764eb194423574f3444d2f935219cb
3
+ size 5049344
neuronxcc-2.12.68.0+4480452af/MODULE_cc7c23b7d4695ed92fc9+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_cc7c23b7d4695ed92fc9+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f225f9368d1abd92e29fe9c675c2ab6a2236777b5e0b68042ea3c3b42593d539
3
+ size 372234
neuronxcc-2.12.68.0+4480452af/MODULE_cc7c23b7d4695ed92fc9+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad3c51889e10559dd2b25ee3f719f33888c9dd6af9169136be35ec4683e5bcad
3
+ size 12555264
neuronxcc-2.12.68.0+4480452af/MODULE_cd132d5ec27bc45aa15f+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_cd132d5ec27bc45aa15f+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f9f004d375a4b7f94018ef6be37b14752e1e975efe1600af6e5a644ab8d6f22
3
+ size 376449
neuronxcc-2.12.68.0+4480452af/MODULE_cd132d5ec27bc45aa15f+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b21de09b41e9b65faf731f7fd63c9fbf15876eaeac6066cfd51476128e94a99b
3
+ size 4312064