Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
348
dacorvo HF staff commited on
Commit
afd0988
·
verified ·
1 Parent(s): c528319

Synchronizing local compiler cache.

Browse files
Files changed (24) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/llama/meta-llama/Llama-2-13b-hf/409469dd48ea340e2031.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_01a4748c99030fe69987+613edded/model.neff +1 -1
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_20ebc8f6bf90da880b7d+613edded/model.neff +1 -1
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_29d3ff9333796545a56f+613edded/model.neff +1 -1
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_2e9f2f3a425a7c54a43f+613edded/model.neff +1 -1
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_328290edc16f896de0f3+613edded/model.neff +1 -1
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_34d371c764b2edea8dcd+613edded/model.neff +1 -1
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_3d61798cb258025b2edc+613edded/model.neff +1 -1
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_7c7f9bc845414ce6b5a4+613edded/model.neff +1 -1
  11. neuronxcc-2.16.372.0+4a9b2326/MODULE_8bdbf5372d7324466d56+613edded/model.neff +1 -1
  12. neuronxcc-2.16.372.0+4a9b2326/MODULE_8ce80c0a7e475086c914+613edded/compile_flags.json +1 -0
  13. neuronxcc-2.16.372.0+4a9b2326/MODULE_8ce80c0a7e475086c914+613edded/model.done +0 -0
  14. neuronxcc-2.16.372.0+4a9b2326/MODULE_8ce80c0a7e475086c914+613edded/model.hlo_module.pb +3 -0
  15. neuronxcc-2.16.372.0+4a9b2326/MODULE_8ce80c0a7e475086c914+613edded/model.neff +3 -0
  16. neuronxcc-2.16.372.0+4a9b2326/MODULE_97cbcc47f9c08a6a6ba1+613edded/model.neff +1 -1
  17. neuronxcc-2.16.372.0+4a9b2326/MODULE_a5cdca7cc704970c3392+613edded/model.neff +1 -1
  18. neuronxcc-2.16.372.0+4a9b2326/MODULE_a6b635cb5d8d2a5539a7+613edded/model.neff +1 -1
  19. neuronxcc-2.16.372.0+4a9b2326/MODULE_d688e673288827d3fa0e+613edded/model.neff +1 -1
  20. neuronxcc-2.16.372.0+4a9b2326/MODULE_f992331f929adb7094fb+613edded/compile_flags.json +1 -0
  21. neuronxcc-2.16.372.0+4a9b2326/MODULE_f992331f929adb7094fb+613edded/model.done +0 -0
  22. neuronxcc-2.16.372.0+4a9b2326/MODULE_f992331f929adb7094fb+613edded/model.hlo_module.pb +3 -0
  23. neuronxcc-2.16.372.0+4a9b2326/MODULE_f992331f929adb7094fb+613edded/model.neff +3 -0
  24. neuronxcc-2.16.372.0+4a9b2326/MODULE_fac5455884c9dfdee723+613edded/model.neff +1 -1
.gitattributes CHANGED
@@ -7176,3 +7176,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_5f194d47737258040d3c+613edded/model.neff fi
7176
  neuronxcc-2.16.372.0+4a9b2326/MODULE_6c97395a3fefb42ecdbc+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7177
  neuronxcc-2.16.372.0+4a9b2326/MODULE_190feb29500cacd7e00a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7178
  neuronxcc-2.16.372.0+4a9b2326/MODULE_a639a850df3eb7f79ea2+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
7176
  neuronxcc-2.16.372.0+4a9b2326/MODULE_6c97395a3fefb42ecdbc+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7177
  neuronxcc-2.16.372.0+4a9b2326/MODULE_190feb29500cacd7e00a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7178
  neuronxcc-2.16.372.0+4a9b2326/MODULE_a639a850df3eb7f79ea2+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7179
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_8ce80c0a7e475086c914+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7180
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_f992331f929adb7094fb+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/llama/meta-llama/Llama-2-13b-hf/409469dd48ea340e2031.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "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": "2.16.372.0+4a9b2326", "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-2.16.372.0+4a9b2326/MODULE_01a4748c99030fe69987+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55d2e8728a9224ecc18fc58b22d22693f0e0ce970af23cce489d4c6f90824837
3
  size 29225984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f9728eb86bd53dda6366cf476d9d54cd143a3e4657bbcdc06cdfe93e5550c0
3
  size 29225984
neuronxcc-2.16.372.0+4a9b2326/MODULE_20ebc8f6bf90da880b7d+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03d608b98ce144070f5e4e2946fc984369052a1936dde761d20bf542ab3bacc3
3
  size 6042624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e41e85ad131c3915711d5cb89d86718a102497b315add7fe73ab56699eb2403
3
  size 6042624
neuronxcc-2.16.372.0+4a9b2326/MODULE_29d3ff9333796545a56f+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db9f2824b3b6c0caeccdf6aa1528aa0c34426f5f5985da1911312d00cc1a09af
3
  size 29225984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:144b24539b608c7ee685836807c096d70d1cdbb2ccdb229952952f56a14424c7
3
  size 29225984
neuronxcc-2.16.372.0+4a9b2326/MODULE_2e9f2f3a425a7c54a43f+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a46f32ba6a4ab96b5704851e1532257c41c21031efe298690860b34c87817cc
3
  size 29225984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0bf925a65d289b96b884d9fe192914f6783a51c6cb5f86eab96b91af290f538
3
  size 29225984
neuronxcc-2.16.372.0+4a9b2326/MODULE_328290edc16f896de0f3+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a92838cbc33a798066dd113e804c4cffdd18c13c932b970b889a2b2be09e6330
3
  size 11664384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2b5aa96226ad698dc2f0b661311988cca8a196f2cff32d3cd2958c3bf24961d
3
  size 11664384
neuronxcc-2.16.372.0+4a9b2326/MODULE_34d371c764b2edea8dcd+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55254fa7cc84ed2c53d21177d4593a3d67aee29ac21b8ea690b080b327d622d6
3
  size 7803904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ebf416056af21adc3bc3d71057c68e6353e2f8d7e384b6741366543b8ec0de
3
  size 7803904
neuronxcc-2.16.372.0+4a9b2326/MODULE_3d61798cb258025b2edc+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ee9cc60f35b7a6d07a396cdb7952d261dfb276e4bf4bab8c5ad41e7ad16b995
3
  size 5970944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e7c98cc9bf2a57760705a932a6f1c62de9f0d31c125e997d8b03d2ae2ad602a
3
  size 5970944
neuronxcc-2.16.372.0+4a9b2326/MODULE_7c7f9bc845414ce6b5a4+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc748b8c1c8ceb28130e853d22d0a845c31944e937435e745a182e268b1c3045
3
  size 6042624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63dc2a42eb970f65a692123d929236a469a216ceede8b2129df0cd2ccaca26e7
3
  size 6042624
neuronxcc-2.16.372.0+4a9b2326/MODULE_8bdbf5372d7324466d56+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d733f8c214421ce5588348bfee93afb0cfccbf74f0bc4067addf64adf97e194c
3
  size 5622784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:188e2fb757804a5a4245d67a83ed22142bdbadbb266a4ac7092b2450890e7c9b
3
  size 5622784
neuronxcc-2.16.372.0+4a9b2326/MODULE_8ce80c0a7e475086c914+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.16.372.0+4a9b2326/MODULE_8ce80c0a7e475086c914+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_8ce80c0a7e475086c914+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbc929aa648846520b3ef9b58099acc1123e9ad4d269da79f5ef70c5e02c46c5
3
+ size 385292
neuronxcc-2.16.372.0+4a9b2326/MODULE_8ce80c0a7e475086c914+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:731e78af081266b099bb17cd186e3838ae0084baa9691b3a4c586f165d986564
3
+ size 4178944
neuronxcc-2.16.372.0+4a9b2326/MODULE_97cbcc47f9c08a6a6ba1+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07115d49f8c735e2d3a8f5821aed28147cbc94d55ec104474050aa8f1f70b5f0
3
  size 3103744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24ec42b4bc330cd04fdf1eeb2458132e57d06eaec28ea5c647896319e743c4b2
3
  size 3103744
neuronxcc-2.16.372.0+4a9b2326/MODULE_a5cdca7cc704970c3392+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c81225d8efe0b00dc253bd1e46d5a1d744dd282c1b9940ab547f770078b620f0
3
  size 3922944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f41e8c070a232fba4a5063c483e2cf3a3548fbdc2b8abac302dbbe3b7a498fb
3
  size 3922944
neuronxcc-2.16.372.0+4a9b2326/MODULE_a6b635cb5d8d2a5539a7+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecc77d017d21db5fca91147fc10f6a8055b310ce2f3b0782589d1b6214408931
3
  size 3431424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df883eef6f639a1362f278ad2652899de8d1fdaaf79b52a1973dad2a98d762dd
3
  size 3431424
neuronxcc-2.16.372.0+4a9b2326/MODULE_d688e673288827d3fa0e+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:188543fdb86245c653361d1700dde1d13f8f7a343a9b118e09a6f706297398e4
3
  size 29225984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:952e21c531592d0d016e054ea9c444bfb5563f45c3a3f7487b30e1bda00dcbb5
3
  size 29225984
neuronxcc-2.16.372.0+4a9b2326/MODULE_f992331f929adb7094fb+613edded/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.16.372.0+4a9b2326/MODULE_f992331f929adb7094fb+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_f992331f929adb7094fb+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74fc068d85127548ff0b21fa2a6dd966a9aab13472ccafcf93e32f4769754c7e
3
+ size 305677
neuronxcc-2.16.372.0+4a9b2326/MODULE_f992331f929adb7094fb+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9718203414ef42ade7753d9afad03bfa323e3dac9f8dbb5267d3c0468e4c9a54
3
+ size 23706624
neuronxcc-2.16.372.0+4a9b2326/MODULE_fac5455884c9dfdee723+613edded/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82858de1f06a352a9f5c8d36841d5f72d40cfa45be4c8a499ace797c84c2c5f3
3
  size 10415104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9745b0e63860d8d1c07a88c52d0361b4e9f86c89dd586d94d7a6afd3decfb6d0
3
  size 10415104