Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
451
dacorvo HF Staff commited on
Commit
460bba8
·
verified ·
1 Parent(s): 826638e

Synchronizing local compiler cache.

Browse files
Files changed (10) hide show
  1. .gitattributes +2 -0
  2. neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/mistral/HuggingFaceH4/zephyr-7b-beta/1114d34726992c649698.json +1 -0
  3. neuronxcc-2.16.372.0+4a9b2326/MODULE_d3c34e6adb65ca3901ff+613edded/compile_flags.json +1 -0
  4. neuronxcc-2.16.372.0+4a9b2326/MODULE_d3c34e6adb65ca3901ff+613edded/model.done +0 -0
  5. neuronxcc-2.16.372.0+4a9b2326/MODULE_d3c34e6adb65ca3901ff+613edded/model.hlo_module.pb +3 -0
  6. neuronxcc-2.16.372.0+4a9b2326/MODULE_d3c34e6adb65ca3901ff+613edded/model.neff +3 -0
  7. neuronxcc-2.16.372.0+4a9b2326/MODULE_d5c3e8fb7324bf43ee44+613edded/compile_flags.json +1 -0
  8. neuronxcc-2.16.372.0+4a9b2326/MODULE_d5c3e8fb7324bf43ee44+613edded/model.done +0 -0
  9. neuronxcc-2.16.372.0+4a9b2326/MODULE_d5c3e8fb7324bf43ee44+613edded/model.hlo_module.pb +3 -0
  10. neuronxcc-2.16.372.0+4a9b2326/MODULE_d5c3e8fb7324bf43ee44+613edded/model.neff +3 -0
.gitattributes CHANGED
@@ -7153,3 +7153,5 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_29d3ff9333796545a56f+613edded/model.neff fi
7153
  neuronxcc-2.16.372.0+4a9b2326/MODULE_a5cdca7cc704970c3392+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7154
  neuronxcc-2.16.372.0+4a9b2326/MODULE_3ae663b4f5ea827f9967+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7155
  neuronxcc-2.16.372.0+4a9b2326/MODULE_f691c44ee0aa862b6d62+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
7153
  neuronxcc-2.16.372.0+4a9b2326/MODULE_a5cdca7cc704970c3392+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7154
  neuronxcc-2.16.372.0+4a9b2326/MODULE_3ae663b4f5ea827f9967+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7155
  neuronxcc-2.16.372.0+4a9b2326/MODULE_f691c44ee0aa862b6d62+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7156
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_d3c34e6adb65ca3901ff+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7157
+ neuronxcc-2.16.372.0+4a9b2326/MODULE_d5c3e8fb7324bf43ee44+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev1/inference/mistral/HuggingFaceH4/zephyr-7b-beta/1114d34726992c649698.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"architectures": ["MistralForCausalLM"], "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": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "neuron": {"auto_cast_type": "bf16", "batch_size": 4, "checkpoint_id": "HuggingFaceH4/zephyr-7b-beta", "checkpoint_revision": "892b3d7a7b1cf10c7a701c60881cd93df615734c", "compiler_type": "neuronx-cc", "compiler_version": "2.16.372.0+4a9b2326", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 2, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "vocab_size": 32000}
neuronxcc-2.16.372.0+4a9b2326/MODULE_d3c34e6adb65ca3901ff+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_d3c34e6adb65ca3901ff+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_d3c34e6adb65ca3901ff+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46226105f5bf3c58662117f90979573cf37edbed7aa8bf99d0243fab4f59dfa3
3
+ size 363413
neuronxcc-2.16.372.0+4a9b2326/MODULE_d3c34e6adb65ca3901ff+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b880935f8c4b8ca631a83d27ec0faf90d0ea974e7281a963ffd35db7467e4ed
3
+ size 2694144
neuronxcc-2.16.372.0+4a9b2326/MODULE_d5c3e8fb7324bf43ee44+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_d5c3e8fb7324bf43ee44+613edded/model.done ADDED
File without changes
neuronxcc-2.16.372.0+4a9b2326/MODULE_d5c3e8fb7324bf43ee44+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dadc1a68154b7e761119d9948b2aee6da47bbc10e8ddaf38b97825185bd53e4
3
+ size 537196596
neuronxcc-2.16.372.0+4a9b2326/MODULE_d5c3e8fb7324bf43ee44+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:318b115a81c542dce6b82b887502e49e1b41dbcf409926d1a62769c29809598f
3
+ size 28017664