Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
240
dacorvo HF staff commited on
Commit
65fbd2a
•
1 Parent(s): 2bc2f53

Synchronizing local compiler cache.

Browse files
Files changed (38) hide show
  1. .gitattributes +12 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/ibm/labradorite-13b/32e283828e85a2cae0e5.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/MODULE_0a6d6d62e1dc6492d7be+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.12.68.0+4480452af/MODULE_0a6d6d62e1dc6492d7be+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_0a6d6d62e1dc6492d7be+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_171d3d37929b042fea1f+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_171d3d37929b042fea1f+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_171d3d37929b042fea1f+2c2d707e/model.neff +3 -0
  9. neuronxcc-2.12.68.0+4480452af/MODULE_659897f174efb0c5f60e+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.12.68.0+4480452af/MODULE_659897f174efb0c5f60e+2c2d707e/model.hlo.pb +3 -0
  11. neuronxcc-2.12.68.0+4480452af/MODULE_659897f174efb0c5f60e+2c2d707e/model.neff +3 -0
  12. neuronxcc-2.12.68.0+4480452af/MODULE_6755f483d34c479dbd96+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.12.68.0+4480452af/MODULE_6755f483d34c479dbd96+2c2d707e/model.hlo.pb +3 -0
  14. neuronxcc-2.12.68.0+4480452af/MODULE_6755f483d34c479dbd96+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.12.68.0+4480452af/MODULE_ae0aea97c0a8b375f523+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.12.68.0+4480452af/MODULE_ae0aea97c0a8b375f523+2c2d707e/model.hlo.pb +3 -0
  17. neuronxcc-2.12.68.0+4480452af/MODULE_ae0aea97c0a8b375f523+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.12.68.0+4480452af/MODULE_b96b23974d45e3972d2e+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.12.68.0+4480452af/MODULE_b96b23974d45e3972d2e+2c2d707e/model.hlo.pb +3 -0
  20. neuronxcc-2.12.68.0+4480452af/MODULE_b96b23974d45e3972d2e+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.12.68.0+4480452af/MODULE_bb8dbcb19507b6a4d0ec+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.12.68.0+4480452af/MODULE_bb8dbcb19507b6a4d0ec+2c2d707e/model.hlo.pb +3 -0
  23. neuronxcc-2.12.68.0+4480452af/MODULE_bb8dbcb19507b6a4d0ec+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.12.68.0+4480452af/MODULE_c5a0cff1ec9fd1710be3+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.12.68.0+4480452af/MODULE_c5a0cff1ec9fd1710be3+2c2d707e/model.hlo.pb +3 -0
  26. neuronxcc-2.12.68.0+4480452af/MODULE_c5a0cff1ec9fd1710be3+2c2d707e/model.neff +3 -0
  27. neuronxcc-2.12.68.0+4480452af/MODULE_ca91a926cbdf7f298941+2c2d707e/compile_flags.txt +1 -0
  28. neuronxcc-2.12.68.0+4480452af/MODULE_ca91a926cbdf7f298941+2c2d707e/model.hlo.pb +3 -0
  29. neuronxcc-2.12.68.0+4480452af/MODULE_ca91a926cbdf7f298941+2c2d707e/model.neff +3 -0
  30. neuronxcc-2.12.68.0+4480452af/MODULE_d1d98ef823eca4d4726f+2c2d707e/compile_flags.txt +1 -0
  31. neuronxcc-2.12.68.0+4480452af/MODULE_d1d98ef823eca4d4726f+2c2d707e/model.hlo.pb +3 -0
  32. neuronxcc-2.12.68.0+4480452af/MODULE_d1d98ef823eca4d4726f+2c2d707e/model.neff +3 -0
  33. neuronxcc-2.12.68.0+4480452af/MODULE_dfbb0e7eff878641ce62+2c2d707e/compile_flags.txt +1 -0
  34. neuronxcc-2.12.68.0+4480452af/MODULE_dfbb0e7eff878641ce62+2c2d707e/model.hlo.pb +3 -0
  35. neuronxcc-2.12.68.0+4480452af/MODULE_dfbb0e7eff878641ce62+2c2d707e/model.neff +3 -0
  36. neuronxcc-2.12.68.0+4480452af/MODULE_e36fa264e1e5a562b438+2c2d707e/compile_flags.txt +1 -0
  37. neuronxcc-2.12.68.0+4480452af/MODULE_e36fa264e1e5a562b438+2c2d707e/model.hlo.pb +3 -0
  38. neuronxcc-2.12.68.0+4480452af/MODULE_e36fa264e1e5a562b438+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1492,3 +1492,15 @@ neuronxcc-2.12.68.0+4480452af/MODULE_057640e4e37cd45acc0a+2c2d707e/model.neff fi
1492
  neuronxcc-2.12.68.0+4480452af/MODULE_a4bc10f5c2b5e8833ad0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1493
  neuronxcc-2.12.68.0+4480452af/MODULE_1ed793db908baaf24353+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1494
  neuronxcc-2.12.68.0+4480452af/MODULE_65797b3dd43aaa421699+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
1492
  neuronxcc-2.12.68.0+4480452af/MODULE_a4bc10f5c2b5e8833ad0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1493
  neuronxcc-2.12.68.0+4480452af/MODULE_1ed793db908baaf24353+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1494
  neuronxcc-2.12.68.0+4480452af/MODULE_65797b3dd43aaa421699+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1495
+ neuronxcc-2.12.68.0+4480452af/MODULE_0a6d6d62e1dc6492d7be+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1496
+ neuronxcc-2.12.68.0+4480452af/MODULE_171d3d37929b042fea1f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1497
+ neuronxcc-2.12.68.0+4480452af/MODULE_659897f174efb0c5f60e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1498
+ neuronxcc-2.12.68.0+4480452af/MODULE_6755f483d34c479dbd96+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1499
+ neuronxcc-2.12.68.0+4480452af/MODULE_ae0aea97c0a8b375f523+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1500
+ neuronxcc-2.12.68.0+4480452af/MODULE_b96b23974d45e3972d2e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1501
+ neuronxcc-2.12.68.0+4480452af/MODULE_bb8dbcb19507b6a4d0ec+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1502
+ neuronxcc-2.12.68.0+4480452af/MODULE_c5a0cff1ec9fd1710be3+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1503
+ neuronxcc-2.12.68.0+4480452af/MODULE_ca91a926cbdf7f298941+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1504
+ neuronxcc-2.12.68.0+4480452af/MODULE_d1d98ef823eca4d4726f+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1505
+ neuronxcc-2.12.68.0+4480452af/MODULE_dfbb0e7eff878641ce62+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1506
+ neuronxcc-2.12.68.0+4480452af/MODULE_e36fa264e1e5a562b438+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/ibm/labradorite-13b/32e283828e85a2cae0e5.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32008, "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": "bfloat16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "pad_token_id": 32001, "eos_token_id": 2, "end_token_id": 32000, "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": "ibm/labradorite-13b", "checkpoint_revision": "26921cf1d63c9c657e8260d08eaacc14fca43da0"}}
neuronxcc-2.12.68.0+4480452af/MODULE_0a6d6d62e1dc6492d7be+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_0a6d6d62e1dc6492d7be+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee793d37c31d49eabf68b6a004b3daef1ae136eceab72bc62533285c984937b
3
+ size 372234
neuronxcc-2.12.68.0+4480452af/MODULE_0a6d6d62e1dc6492d7be+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39ede621cbff3fc11e1d18e0da8d889a0f26531ddd6d6fbdcc426bfe83adcada
3
+ size 6452224
neuronxcc-2.12.68.0+4480452af/MODULE_171d3d37929b042fea1f+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_171d3d37929b042fea1f+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88d621fef2c795aaf13eede12fe79837e639cc9b89de420066d364a43372ca88
3
+ size 367643
neuronxcc-2.12.68.0+4480452af/MODULE_171d3d37929b042fea1f+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:433e257ccec915ec8428c8ee19a80fc18e0da4cfe0ff613e40777766079f9daf
3
+ size 4609024
neuronxcc-2.12.68.0+4480452af/MODULE_659897f174efb0c5f60e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_659897f174efb0c5f60e+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d66f7e18f40682b37920e1cba0d0684bc0716251313f96dc98027f5cdd732eff
3
+ size 372234
neuronxcc-2.12.68.0+4480452af/MODULE_659897f174efb0c5f60e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb8ff217708f367c3797fcc4fddd2e037967a7a5c80f1049450820a66390cfd7
3
+ size 5458944
neuronxcc-2.12.68.0+4480452af/MODULE_6755f483d34c479dbd96+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_6755f483d34c479dbd96+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b0363ea0fde5e155ec943e72f7cf60e770c5335a221cb257a8cca8f1082315
3
+ size 372234
neuronxcc-2.12.68.0+4480452af/MODULE_6755f483d34c479dbd96+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f97cbf86ed531104c57f7fb6998b7ab6487b08f6ec9cc2b278e2b8f4ab92bd6
3
+ size 12524544
neuronxcc-2.12.68.0+4480452af/MODULE_ae0aea97c0a8b375f523+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_ae0aea97c0a8b375f523+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bd61df281a7cd292da8fcd1c6cd70ffaebf7c8b9b0e9bfb5b3e533c18853d30
3
+ size 376449
neuronxcc-2.12.68.0+4480452af/MODULE_ae0aea97c0a8b375f523+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ad279183eeedea894ffdcc3ed451bb08d105a306e50fe84e265af4c4ed2a5e
3
+ size 4353024
neuronxcc-2.12.68.0+4480452af/MODULE_b96b23974d45e3972d2e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_b96b23974d45e3972d2e+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626f1b802c2f9cda3512c1f371d84253b744a42ed151eb7ed9755b594d9dd3ff
3
+ size 376449
neuronxcc-2.12.68.0+4480452af/MODULE_b96b23974d45e3972d2e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:364d83cddc70f95e26862e9b603a4de1777701d3ac4f152bca0c3f0142014511
3
+ size 4312064
neuronxcc-2.12.68.0+4480452af/MODULE_bb8dbcb19507b6a4d0ec+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_bb8dbcb19507b6a4d0ec+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49926d1c12806081c4263acb5ad7c9013ec65ba16eb8c0ee1180e58ecf4d0ce8
3
+ size 372234
neuronxcc-2.12.68.0+4480452af/MODULE_bb8dbcb19507b6a4d0ec+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be33e5a51333ad825513fe5778d0cc22c060ff22b2751dbc8c2740ab144cb6a7
3
+ size 24095744
neuronxcc-2.12.68.0+4480452af/MODULE_c5a0cff1ec9fd1710be3+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_c5a0cff1ec9fd1710be3+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bb15513083bb55d7e81573f2ac6cfc8cdccdab75dc8b16352e5275969b013e9
3
+ size 376449
neuronxcc-2.12.68.0+4480452af/MODULE_c5a0cff1ec9fd1710be3+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79618915f7a7e05b17dcc276b0737abf13e4bc2781ebc62be10c64472b329a2
3
+ size 4475904
neuronxcc-2.12.68.0+4480452af/MODULE_ca91a926cbdf7f298941+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_ca91a926cbdf7f298941+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9b0780ae4e97eb92d6cb21ffcc63c142f22f433f5fe34dd8a048b0f4e6eff8f
3
+ size 376449
neuronxcc-2.12.68.0+4480452af/MODULE_ca91a926cbdf7f298941+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ab22214ecc258046fc7999c1539dede99c91f0dc539f00789b2db758064c88c
3
+ size 4281344
neuronxcc-2.12.68.0+4480452af/MODULE_d1d98ef823eca4d4726f+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_d1d98ef823eca4d4726f+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68553e1e680e680d2cb44b5b7f8a602eeaa064ee54388417a9848f1f680b8074
3
+ size 372234
neuronxcc-2.12.68.0+4480452af/MODULE_d1d98ef823eca4d4726f+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c29539a341e32d57974cb1e626fc375cafc57d32769d4c6ef4ee7e71b71d0f8
3
+ size 4660224
neuronxcc-2.12.68.0+4480452af/MODULE_dfbb0e7eff878641ce62+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_dfbb0e7eff878641ce62+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fac95bf7ec68515157735bcb3ccddfdb94ae9b1b617222787da9d86bb60f017f
3
+ size 376449
neuronxcc-2.12.68.0+4480452af/MODULE_dfbb0e7eff878641ce62+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ccf1839c6fdc0311b004417bb17c465ad517cea3eadddca6d08941c454b6b4
3
+ size 4660224
neuronxcc-2.12.68.0+4480452af/MODULE_e36fa264e1e5a562b438+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_e36fa264e1e5a562b438+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386ffbb47d005d42eeb60571b2c2adc3d707de8ee0d33437fabd799f47def9b1
3
+ size 376449
neuronxcc-2.12.68.0+4480452af/MODULE_e36fa264e1e5a562b438+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72744adf2b5900d691509eaebe617fd81c029706e57f540dd6bab7a2f739bd94
3
+ size 5049344