Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
235
jburtoft commited on
Commit
8de9e9a
•
1 Parent(s): 00e7da5

Synchronizing local compiler cache.

Browse files
Files changed (19) hide show
  1. .gitattributes +5 -0
  2. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/codellama/CodeLlama-7b-hf/a5944998455b1bdf76f5.json +1 -0
  3. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/codellama/CodeLlama-7b-hf/e3b9c0ce479aacf9b6d1.json +1 -0
  4. neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/mistral/mistralai/Mistral-7B-Instruct-v0.2/9ea0f3dbb1ea7b3d65ad.json +1 -0
  5. neuronxcc-2.12.68.0+4480452af/MODULE_14b9e7a133b5771c2a99+2c2d707e/compile_flags.txt +1 -0
  6. neuronxcc-2.12.68.0+4480452af/MODULE_14b9e7a133b5771c2a99+2c2d707e/model.hlo.pb +3 -0
  7. neuronxcc-2.12.68.0+4480452af/MODULE_14b9e7a133b5771c2a99+2c2d707e/model.neff +3 -0
  8. neuronxcc-2.12.68.0+4480452af/MODULE_178af04b5b08c3578620+2c2d707e/compile_flags.txt +1 -0
  9. neuronxcc-2.12.68.0+4480452af/MODULE_178af04b5b08c3578620+2c2d707e/model.hlo.pb +3 -0
  10. neuronxcc-2.12.68.0+4480452af/MODULE_178af04b5b08c3578620+2c2d707e/model.neff +3 -0
  11. neuronxcc-2.12.68.0+4480452af/MODULE_2bbf8ec5e16249e923c7+2c2d707e/compile_flags.txt +1 -0
  12. neuronxcc-2.12.68.0+4480452af/MODULE_2bbf8ec5e16249e923c7+2c2d707e/model.hlo.pb +3 -0
  13. neuronxcc-2.12.68.0+4480452af/MODULE_2bbf8ec5e16249e923c7+2c2d707e/model.neff +3 -0
  14. neuronxcc-2.12.68.0+4480452af/MODULE_3aa14f7f2c5ba85f8a71+2c2d707e/compile_flags.txt +1 -0
  15. neuronxcc-2.12.68.0+4480452af/MODULE_3aa14f7f2c5ba85f8a71+2c2d707e/model.hlo.pb +3 -0
  16. neuronxcc-2.12.68.0+4480452af/MODULE_3aa14f7f2c5ba85f8a71+2c2d707e/model.neff +3 -0
  17. neuronxcc-2.12.68.0+4480452af/MODULE_d508d68ca9af9d78e9ce+2c2d707e/compile_flags.txt +1 -0
  18. neuronxcc-2.12.68.0+4480452af/MODULE_d508d68ca9af9d78e9ce+2c2d707e/model.hlo.pb +3 -0
  19. neuronxcc-2.12.68.0+4480452af/MODULE_d508d68ca9af9d78e9ce+2c2d707e/model.neff +3 -0
.gitattributes CHANGED
@@ -1753,3 +1753,8 @@ neuronxcc-2.13.66.0+6dfecc895/MODULE_f412a6bebf32d04bf191+2c2d707e/model.neff fi
1753
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f7d991bf6082f2b30284+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1754
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fb6a058e29b833424101+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1755
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fd411c71433f0e6756af+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
1753
  neuronxcc-2.13.66.0+6dfecc895/MODULE_f7d991bf6082f2b30284+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1754
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fb6a058e29b833424101+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1755
  neuronxcc-2.13.66.0+6dfecc895/MODULE_fd411c71433f0e6756af+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1756
+ neuronxcc-2.12.68.0+4480452af/MODULE_14b9e7a133b5771c2a99+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1757
+ neuronxcc-2.12.68.0+4480452af/MODULE_178af04b5b08c3578620+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1758
+ neuronxcc-2.12.68.0+4480452af/MODULE_2bbf8ec5e16249e923c7+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1759
+ neuronxcc-2.12.68.0+4480452af/MODULE_3aa14f7f2c5ba85f8a71+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
1760
+ neuronxcc-2.12.68.0+4480452af/MODULE_d508d68ca9af9d78e9ce+2c2d707e/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/codellama/CodeLlama-7b-hf/a5944998455b1bdf76f5.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32016, "max_position_embeddings": 16384, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 1000000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 2, "auto_cast_type": "fp16", "sequence_length": 2048, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "codellama/CodeLlama-7b-hf", "checkpoint_revision": "7f22f0a5f7991355a2c3867923359ec4ed0b58bf"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/codellama/CodeLlama-7b-hf/e3b9c0ce479aacf9b6d1.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32016, "max_position_embeddings": 16384, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 1000000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "codellama/CodeLlama-7b-hf", "checkpoint_revision": "7f22f0a5f7991355a2c3867923359ec4ed0b58bf", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 2, "sequence_length": 2048, "task": "text-generation"}}
neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/mistral/mistralai/Mistral-7B-Instruct-v0.2/9ea0f3dbb1ea7b3d65ad.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"vocab_size": 32000, "max_position_embeddings": 32768, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "sliding_window": null, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "use_cache": true, "rope_theta": 1000000.0, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["MistralForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "mistral", "neuron": {"task": "text-generation", "batch_size": 1, "num_cores": 2, "auto_cast_type": "fp16", "sequence_length": 2048, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "mistralai/Mistral-7B-Instruct-v0.2", "checkpoint_revision": "41b61a33a2483885c981aa79e0df6b32407ed873"}}
neuronxcc-2.12.68.0+4480452af/MODULE_14b9e7a133b5771c2a99+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_14b9e7a133b5771c2a99+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900506fa63cdc146b6b41b07d0d7caf690395c4858a75d175e2d16d37b00a48e
3
+ size 306200
neuronxcc-2.12.68.0+4480452af/MODULE_14b9e7a133b5771c2a99+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ad1afd1ae6421156675916e2f177e90d953d86e21b83792ca9498bad46ba313
3
+ size 8920064
neuronxcc-2.12.68.0+4480452af/MODULE_178af04b5b08c3578620+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_178af04b5b08c3578620+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d07a70696c791387d07ddfe0dd99b09c17257b0e26720a72aa870347d487aa
3
+ size 302393
neuronxcc-2.12.68.0+4480452af/MODULE_178af04b5b08c3578620+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b516d1ae95e25973b32639ce3074c19301c65e53cd932bea65b8cbfb5f5db62
3
+ size 7896064
neuronxcc-2.12.68.0+4480452af/MODULE_2bbf8ec5e16249e923c7+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_2bbf8ec5e16249e923c7+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:483a9767c2467c855fe2756fb7aaff256777176d62c74d2f712f73e3c36064ef
3
+ size 306200
neuronxcc-2.12.68.0+4480452af/MODULE_2bbf8ec5e16249e923c7+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb43687f2cff703a92dceaeb0343c00cc8c249523678d9fe2d189231123f743
3
+ size 8449024
neuronxcc-2.12.68.0+4480452af/MODULE_3aa14f7f2c5ba85f8a71+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_3aa14f7f2c5ba85f8a71+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674373569d83dd7ca76b0ad9df8aea15c466d337eaed6b562a76aa8169c8b07e
3
+ size 306200
neuronxcc-2.12.68.0+4480452af/MODULE_3aa14f7f2c5ba85f8a71+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a74e2d1dbc32b35dccee70314ced38c03881222ed52df4c689a11d85bda7383b
3
+ size 10998784
neuronxcc-2.12.68.0+4480452af/MODULE_d508d68ca9af9d78e9ce+2c2d707e/compile_flags.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ --model-type=transformer --auto-cast=none
neuronxcc-2.12.68.0+4480452af/MODULE_d508d68ca9af9d78e9ce+2c2d707e/model.hlo.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8dd4e5e9048bec909db0d9270e6a1f63e8ffd5280dbd0ecf9f389ce181341fe
3
+ size 306200
neuronxcc-2.12.68.0+4480452af/MODULE_d508d68ca9af9d78e9ce+2c2d707e/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af1a4ef595a973d1f73f7f898e9df3fd280926cd21d88ddcfd9729b5e453eaec
3
+ size 23665664