Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
271
dacorvo HF staff commited on
Commit
9807cc9
•
1 Parent(s): 32561fe

Synchronizing local compiler cache.

Browse files
Files changed (26) hide show
  1. .gitattributes +6 -0
  2. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/13cbb9ec2234e7ca3c26.json +1 -0
  3. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/22d316bd8b3cdfb5514b.json +1 -0
  4. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/2e95f36ce181921d7a7b.json +1 -0
  5. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/4d28ec49befb4e87ec23.json +1 -0
  6. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/7a9166d6f50e7c014961.json +1 -0
  7. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/d3acdf9ff1795080fd1c.json +1 -0
  8. neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/ff6b3f58fac88c2f96c4.json +1 -0
  9. neuronxcc-2.13.66.0+6dfecc895/MODULE_7abaade23f23cc95d209+2c2d707e/compile_flags.txt +1 -0
  10. neuronxcc-2.13.66.0+6dfecc895/MODULE_7abaade23f23cc95d209+2c2d707e/model.hlo.pb +3 -0
  11. neuronxcc-2.13.66.0+6dfecc895/MODULE_7abaade23f23cc95d209+2c2d707e/model.neff +3 -0
  12. neuronxcc-2.13.66.0+6dfecc895/MODULE_b48f6502874ac8a8f5bb+2c2d707e/compile_flags.txt +1 -0
  13. neuronxcc-2.13.66.0+6dfecc895/MODULE_b48f6502874ac8a8f5bb+2c2d707e/model.hlo.pb +3 -0
  14. neuronxcc-2.13.66.0+6dfecc895/MODULE_b48f6502874ac8a8f5bb+2c2d707e/model.neff +3 -0
  15. neuronxcc-2.13.66.0+6dfecc895/MODULE_e3ef39f42931d27282b0+2c2d707e/compile_flags.txt +1 -0
  16. neuronxcc-2.13.66.0+6dfecc895/MODULE_e3ef39f42931d27282b0+2c2d707e/model.hlo.pb +3 -0
  17. neuronxcc-2.13.66.0+6dfecc895/MODULE_e3ef39f42931d27282b0+2c2d707e/model.neff +3 -0
  18. neuronxcc-2.13.66.0+6dfecc895/MODULE_e7dd81fdd13e1e7d9a5c+2c2d707e/compile_flags.txt +1 -0
  19. neuronxcc-2.13.66.0+6dfecc895/MODULE_e7dd81fdd13e1e7d9a5c+2c2d707e/model.hlo.pb +3 -0
  20. neuronxcc-2.13.66.0+6dfecc895/MODULE_e7dd81fdd13e1e7d9a5c+2c2d707e/model.neff +3 -0
  21. neuronxcc-2.13.66.0+6dfecc895/MODULE_f346261058789fe5d56a+2c2d707e/compile_flags.txt +1 -0
  22. neuronxcc-2.13.66.0+6dfecc895/MODULE_f346261058789fe5d56a+2c2d707e/model.hlo.pb +3 -0
  23. neuronxcc-2.13.66.0+6dfecc895/MODULE_f346261058789fe5d56a+2c2d707e/model.neff +3 -0
  24. neuronxcc-2.13.66.0+6dfecc895/MODULE_fd99f71acc89fead8df7+2c2d707e/compile_flags.txt +1 -0
  25. neuronxcc-2.13.66.0+6dfecc895/MODULE_fd99f71acc89fead8df7+2c2d707e/model.hlo.pb +3 -0
  26. neuronxcc-2.13.66.0+6dfecc895/MODULE_fd99f71acc89fead8df7+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1852,3 +1852,9 @@ neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/text_encoder_2/model.n
1852
  neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
1853
  neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
1854
  neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
1852
  neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
1853
  neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
1854
  neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
1855
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_7abaade23f23cc95d209+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1856
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_b48f6502874ac8a8f5bb+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1857
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_e3ef39f42931d27282b0+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1858
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_e7dd81fdd13e1e7d9a5c+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1859
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_f346261058789fe5d56a+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1860
+ neuronxcc-2.13.66.0+6dfecc895/MODULE_fd99f71acc89fead8df7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/13cbb9ec2234e7ca3c26.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, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 8, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "92011f62d7604e261f748ec0cfe6329f31193e33", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 4096, "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/22d316bd8b3cdfb5514b.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, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 16, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "92011f62d7604e261f748ec0cfe6329f31193e33", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 4096, "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/2e95f36ce181921d7a7b.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, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "92011f62d7604e261f748ec0cfe6329f31193e33", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 4096, "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/4d28ec49befb4e87ec23.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, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 32, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "92011f62d7604e261f748ec0cfe6329f31193e33", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 4096, "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/7a9166d6f50e7c014961.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, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 32, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "92011f62d7604e261f748ec0cfe6329f31193e33", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 8, "sequence_length": 4096, "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/d3acdf9ff1795080fd1c.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, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "92011f62d7604e261f748ec0cfe6329f31193e33", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 24, "sequence_length": 4096, "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-2.13.66.0+6dfecc895/0_REGISTRY/0.0.21.dev0/inference/llama/meta-llama/Llama-2-7b-chat-hf/ff6b3f58fac88c2f96c4.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, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 16, "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "92011f62d7604e261f748ec0cfe6329f31193e33", "compiler_type": "neuronx-cc", "compiler_version": "2.13.66.0+6dfecc895", "num_cores": 8, "sequence_length": 4096, "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-2.13.66.0+6dfecc895/MODULE_7abaade23f23cc95d209+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_7abaade23f23cc95d209+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c519ef1ec9020eb1a614ac3ee46daf0bd48e1c12b5e7c06e6973ca0a4c2eca6e
3
+ size 382458
neuronxcc-2.13.66.0+6dfecc895/MODULE_7abaade23f23cc95d209+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf78c85ab7806cc2075ff607e2b006d2191297606973107073641b32c6804b2
3
+ size 9606144
neuronxcc-2.13.66.0+6dfecc895/MODULE_b48f6502874ac8a8f5bb+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_b48f6502874ac8a8f5bb+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bac9dbd283c53aa8457f04991fee15e64947abeeb2003c564ab0a165ac11dd93
3
+ size 383482
neuronxcc-2.13.66.0+6dfecc895/MODULE_b48f6502874ac8a8f5bb+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e100a1f39124851ac66beac14774e9e19f6ae128b83cc2bf8f35193f188b07c
3
+ size 10497024
neuronxcc-2.13.66.0+6dfecc895/MODULE_e3ef39f42931d27282b0+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_e3ef39f42931d27282b0+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bde1f19c6e05aa834daca1bdf0ea93099ce38de1f3d2cfdc3a26c6880cc934bf
3
+ size 338510
neuronxcc-2.13.66.0+6dfecc895/MODULE_e3ef39f42931d27282b0+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eea54fc3b8391c171d440a67d4d3548f522b54dfa767c512aaca55510a8f4dd9
3
+ size 15770624
neuronxcc-2.13.66.0+6dfecc895/MODULE_e7dd81fdd13e1e7d9a5c+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_e7dd81fdd13e1e7d9a5c+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9623fdc379a78496152b5b560465e09de32df817b1741e55989d1f1766bc66e6
3
+ size 337486
neuronxcc-2.13.66.0+6dfecc895/MODULE_e7dd81fdd13e1e7d9a5c+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a210ffa48a264bd7529b9ab102872f51e67833c6186d62f429bedbbda3a216
3
+ size 27331584
neuronxcc-2.13.66.0+6dfecc895/MODULE_f346261058789fe5d56a+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_f346261058789fe5d56a+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:599bdbc9f4b076006b77b7e737d025f5ad596fe4e7bbacddafe164d1495cd4f3
3
+ size 337486
neuronxcc-2.13.66.0+6dfecc895/MODULE_f346261058789fe5d56a+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2167d688a780bac598db04036504f66f6102e6b551376f823abfdddb64719bfa
3
+ size 27331584
neuronxcc-2.13.66.0+6dfecc895/MODULE_fd99f71acc89fead8df7+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.13.66.0+6dfecc895/MODULE_fd99f71acc89fead8df7+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:511de3dc2c1cbcb638f4f9e1d1a8ab4cdbb627063ac6fc9df48639d9bb0f3263
3
+ size 382458
neuronxcc-2.13.66.0+6dfecc895/MODULE_fd99f71acc89fead8df7+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52a119fe64ae5207b13f02f8577981b31a9e516b708f6297fe8da717eb31797f
3
+ size 18596864