Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
268
dacorvo HF staff commited on
Commit
d09b7dd
•
1 Parent(s): f5aae68

Synchronizing local compiler cache.

Browse files
Files changed (38) hide show
  1. .gitattributes +12 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/meta-llama/Meta-Llama-3-8B/238a129139bee2cefd56.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/MODULE_118f7d9d1682ed69d4b8+2c2d707e/compile_flags.txt +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/MODULE_118f7d9d1682ed69d4b8+2c2d707e/model.hlo.pb +3 -0
  5. neuronxcc-2.13.66.0+6dfecc895/MODULE_118f7d9d1682ed69d4b8+2c2d707e/model.neff +3 -0
  6. neuronxcc-2.13.66.0+6dfecc895/MODULE_11e824b63900ba13b171+2c2d707e/compile_flags.txt +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/MODULE_11e824b63900ba13b171+2c2d707e/model.hlo.pb +3 -0
  8. neuronxcc-2.13.66.0+6dfecc895/MODULE_11e824b63900ba13b171+2c2d707e/model.neff +3 -0
  9. neuronxcc-2.13.66.0+6dfecc895/MODULE_37006e67d1dc776058d0+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.13.66.0+6dfecc895/MODULE_37006e67d1dc776058d0+2c2d707e/model.hlo.pb +3 -0
  11. neuronxcc-2.13.66.0+6dfecc895/MODULE_37006e67d1dc776058d0+2c2d707e/model.neff +3 -0
  12. neuronxcc-2.13.66.0+6dfecc895/MODULE_4861e4f054f5ea276204+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.13.66.0+6dfecc895/MODULE_4861e4f054f5ea276204+2c2d707e/model.hlo.pb +3 -0
  14. neuronxcc-2.13.66.0+6dfecc895/MODULE_4861e4f054f5ea276204+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.13.66.0+6dfecc895/MODULE_4a1beae2e4b222a9fa69+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.13.66.0+6dfecc895/MODULE_4a1beae2e4b222a9fa69+2c2d707e/model.hlo.pb +3 -0
  17. neuronxcc-2.13.66.0+6dfecc895/MODULE_4a1beae2e4b222a9fa69+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.13.66.0+6dfecc895/MODULE_4cff6a78801b965526e0+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.13.66.0+6dfecc895/MODULE_4cff6a78801b965526e0+2c2d707e/model.hlo.pb +3 -0
  20. neuronxcc-2.13.66.0+6dfecc895/MODULE_4cff6a78801b965526e0+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.13.66.0+6dfecc895/MODULE_6e99792a4245708b8122+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.13.66.0+6dfecc895/MODULE_6e99792a4245708b8122+2c2d707e/model.hlo.pb +3 -0
  23. neuronxcc-2.13.66.0+6dfecc895/MODULE_6e99792a4245708b8122+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.13.66.0+6dfecc895/MODULE_721ecf894ff6dfc2085e+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.13.66.0+6dfecc895/MODULE_721ecf894ff6dfc2085e+2c2d707e/model.hlo.pb +3 -0
  26. neuronxcc-2.13.66.0+6dfecc895/MODULE_721ecf894ff6dfc2085e+2c2d707e/model.neff +3 -0
  27. neuronxcc-2.13.66.0+6dfecc895/MODULE_7d7bcf26d0f01436da43+2c2d707e/compile_flags.txt +1 -0
  28. neuronxcc-2.13.66.0+6dfecc895/MODULE_7d7bcf26d0f01436da43+2c2d707e/model.hlo.pb +3 -0
  29. neuronxcc-2.13.66.0+6dfecc895/MODULE_7d7bcf26d0f01436da43+2c2d707e/model.neff +3 -0
  30. neuronxcc-2.13.66.0+6dfecc895/MODULE_b642b6a6ff8cebcaea12+2c2d707e/compile_flags.txt +1 -0
  31. neuronxcc-2.13.66.0+6dfecc895/MODULE_b642b6a6ff8cebcaea12+2c2d707e/model.hlo.pb +3 -0
  32. neuronxcc-2.13.66.0+6dfecc895/MODULE_b642b6a6ff8cebcaea12+2c2d707e/model.neff +3 -0
  33. neuronxcc-2.13.66.0+6dfecc895/MODULE_d8b0f4ebcea5ceed8187+2c2d707e/compile_flags.txt +1 -0
  34. neuronxcc-2.13.66.0+6dfecc895/MODULE_d8b0f4ebcea5ceed8187+2c2d707e/model.hlo.pb +3 -0
  35. neuronxcc-2.13.66.0+6dfecc895/MODULE_d8b0f4ebcea5ceed8187+2c2d707e/model.neff +3 -0
  36. neuronxcc-2.13.66.0+6dfecc895/MODULE_e5777b0677e49bc3dabc+2c2d707e/compile_flags.txt +1 -0
  37. neuronxcc-2.13.66.0+6dfecc895/MODULE_e5777b0677e49bc3dabc+2c2d707e/model.hlo.pb +3 -0
  38. neuronxcc-2.13.66.0+6dfecc895/MODULE_e5777b0677e49bc3dabc+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -2348,3 +2348,15 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_bd471eee64c324e4b992+2c2d707e/model.neff fi
2348
  neuronxcc-2.13.66.0+6dfecc895/MODULE_de825e9199c5dedba732+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2349
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e2194130d96a333326a2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2350
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fc66b451d019fd478fc9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
2348
  neuronxcc-2.13.66.0+6dfecc895/MODULE_de825e9199c5dedba732+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2349
  neuronxcc-2.13.66.0+6dfecc895/MODULE_e2194130d96a333326a2+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2350
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fc66b451d019fd478fc9+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2351
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_118f7d9d1682ed69d4b8+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2352
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_11e824b63900ba13b171+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2353
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_37006e67d1dc776058d0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2354
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_4861e4f054f5ea276204+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2355
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_4a1beae2e4b222a9fa69+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2356
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_4cff6a78801b965526e0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2357
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_6e99792a4245708b8122+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2358
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_721ecf894ff6dfc2085e+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2359
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_7d7bcf26d0f01436da43+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2360
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_b642b6a6ff8cebcaea12+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2361
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_d8b0f4ebcea5ceed8187+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
2362
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_e5777b0677e49bc3dabc+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21/inference/llama/meta-llama/Meta-Llama-3-8B/238a129139bee2cefd56.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "model_type": "llama", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "meta-llama/Meta-Llama-3-8B", "checkpoint_revision": "561487d18c41c76bcb5fc6cfb73a324982f04f47", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 128256}
neuronxcc-2.13.66.0+6dfecc895/MODULE_118f7d9d1682ed69d4b8+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_118f7d9d1682ed69d4b8+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5199e8b35602cd4ef105fc13c1799f12b066c510bc08b9856c54643f326ad86
3
+ size 317890
neuronxcc-2.13.66.0+6dfecc895/MODULE_118f7d9d1682ed69d4b8+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4edd9facb809068f598b85fd8b4237a148a678c1138bb2459278579e83222a6
3
+ size 7691264
neuronxcc-2.13.66.0+6dfecc895/MODULE_11e824b63900ba13b171+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_11e824b63900ba13b171+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c97bac0743275c78d1c1fbe1dda31cf781ea8f6d61c262f05b148693de512d9
3
+ size 302340
neuronxcc-2.13.66.0+6dfecc895/MODULE_11e824b63900ba13b171+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ddb85ba87c66563bb4b3278647f997311e05335b38c63a168061f44e597b8b4
3
+ size 7988224
neuronxcc-2.13.66.0+6dfecc895/MODULE_37006e67d1dc776058d0+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_37006e67d1dc776058d0+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20af8897f232abcb7b2fc726958347480d306519feefaedcfbe9a20a1ad995a1
3
+ size 317890
neuronxcc-2.13.66.0+6dfecc895/MODULE_37006e67d1dc776058d0+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97d59e695f7ded86fe97ab62ea8e727a6b033c1178e438e6b4729da0d25ceebe
3
+ size 8090624
neuronxcc-2.13.66.0+6dfecc895/MODULE_4861e4f054f5ea276204+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_4861e4f054f5ea276204+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b782b742473616f83c96a1000997f2b2832bf86a0fea89d0051982232ad8dbe
3
+ size 317890
neuronxcc-2.13.66.0+6dfecc895/MODULE_4861e4f054f5ea276204+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c53177e206fd4ed3943a1f0d455f4a01d670785b0a8a185472a15c8d1c486e
3
+ size 8428544
neuronxcc-2.13.66.0+6dfecc895/MODULE_4a1beae2e4b222a9fa69+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_4a1beae2e4b222a9fa69+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:037d1cd95a8c62a53aa47e57ea84aab8042d6d4fc74774659e33e740718c4244
3
+ size 306147
neuronxcc-2.13.66.0+6dfecc895/MODULE_4a1beae2e4b222a9fa69+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:611678f257bb2a2f86e798dd520a63b004583fa50681053c99dfef39514577a2
3
+ size 5295104
neuronxcc-2.13.66.0+6dfecc895/MODULE_4cff6a78801b965526e0+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_4cff6a78801b965526e0+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48199cfdb3e07cda1f4620b2f19aa366d7853d9fa8d2e65022c05b4755cbbc51
3
+ size 317890
neuronxcc-2.13.66.0+6dfecc895/MODULE_4cff6a78801b965526e0+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a964814ceca3ea48c943903db8f51903a1531cf2ed652f397c151fbd553a6fde
3
+ size 7875584
neuronxcc-2.13.66.0+6dfecc895/MODULE_6e99792a4245708b8122+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_6e99792a4245708b8122+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29410fc31bf1bdc3db86e5de7a9788ac1cd1a41fa711bbd46a7fa1e0c28cc81b
3
+ size 306147
neuronxcc-2.13.66.0+6dfecc895/MODULE_6e99792a4245708b8122+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e393ad44bbed3d24f37e79f1ed96125f811adb6d881c9e6e59ce3d6453dccb10
3
+ size 21883904
neuronxcc-2.13.66.0+6dfecc895/MODULE_721ecf894ff6dfc2085e+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_721ecf894ff6dfc2085e+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30712c55667cddca459f1e698cda8b88b799b57dec76e2ec88306503b6e19a0b
3
+ size 306147
neuronxcc-2.13.66.0+6dfecc895/MODULE_721ecf894ff6dfc2085e+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194a7198b5189b927c91ed1f05b7f7281e4af3d4eef52a1c4160be41d2ee25ab
3
+ size 10486784
neuronxcc-2.13.66.0+6dfecc895/MODULE_7d7bcf26d0f01436da43+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_7d7bcf26d0f01436da43+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49c4467a3ac898169bc97480d3daebc59b77605e72dbe584e82e021cb20abb5
3
+ size 306147
neuronxcc-2.13.66.0+6dfecc895/MODULE_7d7bcf26d0f01436da43+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ed54c6fa05e60c7ee23fb461322add81d502cff106c3a73658da16e38a7bfd5
3
+ size 8449024
neuronxcc-2.13.66.0+6dfecc895/MODULE_b642b6a6ff8cebcaea12+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_b642b6a6ff8cebcaea12+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e451862cc3dc3a31abae782e430acb4f1e03cd3d73a34d4e6d939a41920e57
3
+ size 306147
neuronxcc-2.13.66.0+6dfecc895/MODULE_b642b6a6ff8cebcaea12+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3988dba91b3f2f2860957f2ddd515cc85f1e6528bf3e151947d93a16ec196031
3
+ size 9094144
neuronxcc-2.13.66.0+6dfecc895/MODULE_d8b0f4ebcea5ceed8187+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_d8b0f4ebcea5ceed8187+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a94de8f73a7bd08a19af89e479ee1924abc8a1e301f55aadaa78d6e4e7d51887
3
+ size 317890
neuronxcc-2.13.66.0+6dfecc895/MODULE_d8b0f4ebcea5ceed8187+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d14483df301cde1691b58e02f02f530f88d21e2900a15c427e84b7681d3ae77c
3
+ size 7814144
neuronxcc-2.13.66.0+6dfecc895/MODULE_e5777b0677e49bc3dabc+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_e5777b0677e49bc3dabc+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5e20016c66d0a01da970021aeedfb6320067e1d63a2284b55bc88e570a50b08
3
+ size 317890
neuronxcc-2.13.66.0+6dfecc895/MODULE_e5777b0677e49bc3dabc+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5a4f22c9f9a31adba808ed3ccf7e3d1d6ff5ab40fe14566899db7d03382d402
3
+ size 7773184