Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
348
dacorvo HF staff commited on
Commit
9de3b7f
·
verified ·
1 Parent(s): cb9d7ec

Synchronizing local compiler cache.

Browse files
Files changed (19) hide show
  1. .gitattributes +4 -0
  2. neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.1.0.dev1/inference/llama/lmsys/vicuna-7b-v1.5/3d4b2d42a936a4ec61bf.json +1 -0
  3. neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.1.0.dev1/inference/llama/lmsys/vicuna-7b-v1.5/828bb3035f799f010672.json +1 -0
  4. neuronxcc-2.15.143.0+e39249ad/MODULE_1695330137f296fdba60+39f12043/compile_flags.json +1 -0
  5. neuronxcc-2.15.143.0+e39249ad/MODULE_1695330137f296fdba60+39f12043/model.done +0 -0
  6. neuronxcc-2.15.143.0+e39249ad/MODULE_1695330137f296fdba60+39f12043/model.hlo_module.pb +3 -0
  7. neuronxcc-2.15.143.0+e39249ad/MODULE_1695330137f296fdba60+39f12043/model.neff +3 -0
  8. neuronxcc-2.15.143.0+e39249ad/MODULE_807378dcfffa44901b59+39f12043/compile_flags.json +1 -0
  9. neuronxcc-2.15.143.0+e39249ad/MODULE_807378dcfffa44901b59+39f12043/model.done +0 -0
  10. neuronxcc-2.15.143.0+e39249ad/MODULE_807378dcfffa44901b59+39f12043/model.hlo_module.pb +3 -0
  11. neuronxcc-2.15.143.0+e39249ad/MODULE_807378dcfffa44901b59+39f12043/model.neff +3 -0
  12. neuronxcc-2.15.143.0+e39249ad/MODULE_9d7ecdc9231b4ba0c0d8+39f12043/compile_flags.json +1 -0
  13. neuronxcc-2.15.143.0+e39249ad/MODULE_9d7ecdc9231b4ba0c0d8+39f12043/model.done +0 -0
  14. neuronxcc-2.15.143.0+e39249ad/MODULE_9d7ecdc9231b4ba0c0d8+39f12043/model.hlo_module.pb +3 -0
  15. neuronxcc-2.15.143.0+e39249ad/MODULE_9d7ecdc9231b4ba0c0d8+39f12043/model.neff +3 -0
  16. neuronxcc-2.15.143.0+e39249ad/MODULE_b15e1b7eb2bfb8f6dc3e+39f12043/compile_flags.json +1 -0
  17. neuronxcc-2.15.143.0+e39249ad/MODULE_b15e1b7eb2bfb8f6dc3e+39f12043/model.done +0 -0
  18. neuronxcc-2.15.143.0+e39249ad/MODULE_b15e1b7eb2bfb8f6dc3e+39f12043/model.hlo_module.pb +3 -0
  19. neuronxcc-2.15.143.0+e39249ad/MODULE_b15e1b7eb2bfb8f6dc3e+39f12043/model.neff +3 -0
.gitattributes CHANGED
@@ -7460,3 +7460,7 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_767b99765e404104c7bb+613edded/model.neff fi
7460
  neuronxcc-2.16.372.0+4a9b2326/MODULE_f65495564d03f1c90e3a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7461
  neuronxcc-2.16.372.0+4a9b2326/MODULE_51c384f52e045bea30bd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7462
  neuronxcc-2.16.372.0+4a9b2326/MODULE_6c9037784aa88d983971+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
7460
  neuronxcc-2.16.372.0+4a9b2326/MODULE_f65495564d03f1c90e3a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7461
  neuronxcc-2.16.372.0+4a9b2326/MODULE_51c384f52e045bea30bd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7462
  neuronxcc-2.16.372.0+4a9b2326/MODULE_6c9037784aa88d983971+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7463
+ neuronxcc-2.15.143.0+e39249ad/MODULE_1695330137f296fdba60+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
7464
+ neuronxcc-2.15.143.0+e39249ad/MODULE_807378dcfffa44901b59+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
7465
+ neuronxcc-2.15.143.0+e39249ad/MODULE_9d7ecdc9231b4ba0c0d8+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
7466
+ neuronxcc-2.15.143.0+e39249ad/MODULE_b15e1b7eb2bfb8f6dc3e+39f12043/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.15.143.0+e39249ad/0_REGISTRY/0.1.0.dev1/inference/llama/lmsys/vicuna-7b-v1.5/3d4b2d42a936a4ec61bf.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": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "lmsys/vicuna-7b-v1.5", "checkpoint_revision": "3321f76e3f527bd14065daf69dad9344000a201d", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pad_token_id": 0, "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-2.15.143.0+e39249ad/0_REGISTRY/0.1.0.dev1/inference/llama/lmsys/vicuna-7b-v1.5/828bb3035f799f010672.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": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "lmsys/vicuna-7b-v1.5", "checkpoint_revision": "3321f76e3f527bd14065daf69dad9344000a201d", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 2, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pad_token_id": 0, "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-2.15.143.0+e39249ad/MODULE_1695330137f296fdba60+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.143.0+e39249ad/MODULE_1695330137f296fdba60+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.143.0+e39249ad/MODULE_1695330137f296fdba60+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd255ec8bdb6846f25c5cd89fc05954cccfec6b5c1ed43814ef6cd7a99e52a5f
3
+ size 339439
neuronxcc-2.15.143.0+e39249ad/MODULE_1695330137f296fdba60+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f0888d74390ea23cd87f464642aa1e205d5a690ed5c3259732917183cac3c5d
3
+ size 12176384
neuronxcc-2.15.143.0+e39249ad/MODULE_807378dcfffa44901b59+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.143.0+e39249ad/MODULE_807378dcfffa44901b59+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.143.0+e39249ad/MODULE_807378dcfffa44901b59+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f85f91b5a7e23df73e679c817843797fa17f2ca25f1a15255336d9ccd79569
3
+ size 308060
neuronxcc-2.15.143.0+e39249ad/MODULE_807378dcfffa44901b59+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5448df43da8672f050934d00e18b0d047d93dc9dfc6be369ddbd9e6c36debb30
3
+ size 8449024
neuronxcc-2.15.143.0+e39249ad/MODULE_9d7ecdc9231b4ba0c0d8+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.143.0+e39249ad/MODULE_9d7ecdc9231b4ba0c0d8+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.143.0+e39249ad/MODULE_9d7ecdc9231b4ba0c0d8+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b70ed2bfb087c6f10380ff37bb3e8fe2c327c0990448eba13d9001f68fafe82
3
+ size 386605
neuronxcc-2.15.143.0+e39249ad/MODULE_9d7ecdc9231b4ba0c0d8+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abdf1620c3f402eb8ab3df194fac61e4b8fc2292cd06e578b8a08a6f5a2a53b8
3
+ size 6042624
neuronxcc-2.15.143.0+e39249ad/MODULE_b15e1b7eb2bfb8f6dc3e+39f12043/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
neuronxcc-2.15.143.0+e39249ad/MODULE_b15e1b7eb2bfb8f6dc3e+39f12043/model.done ADDED
File without changes
neuronxcc-2.15.143.0+e39249ad/MODULE_b15e1b7eb2bfb8f6dc3e+39f12043/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c46f5a2f49c504927a038776062050aa848d80ba4cb81f412a4d5a2bcddaeb8b
3
+ size 432199
neuronxcc-2.15.143.0+e39249ad/MODULE_b15e1b7eb2bfb8f6dc3e+39f12043/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200d808cfd20a740b256ea74168ffb5df04923153db2f42ff26b29667b20672d
3
+ size 5929984