Synchronizing local compiler cache.
Browse files- .gitattributes +2 -0
- neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/mistral/HuggingFaceH4/zephyr-7b-beta/a3def2b08381a583fdae.json +36 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_52f77cf05a48696d505f+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_52f77cf05a48696d505f+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_52f77cf05a48696d505f+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_52f77cf05a48696d505f+613edded/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_7e8a971b679cd1f1877b+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_7e8a971b679cd1f1877b+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_7e8a971b679cd1f1877b+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_7e8a971b679cd1f1877b+613edded/model.neff +3 -0
.gitattributes
CHANGED
|
@@ -7713,3 +7713,5 @@ neuronxcc-2.17.194.0+d312836f/MODULE_c299f9936437dd67f341+613edded/model.neff fi
|
|
| 7713 |
neuronxcc-2.17.194.0+d312836f/MODULE_ff8fad012e7766ca23ef+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7714 |
neuronxcc-2.17.194.0+d312836f/MODULE_4caf7deb700973d9f449+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7715 |
neuronxcc-2.17.194.0+d312836f/MODULE_a6b635cb5d8d2a5539a7+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 7713 |
neuronxcc-2.17.194.0+d312836f/MODULE_ff8fad012e7766ca23ef+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7714 |
neuronxcc-2.17.194.0+d312836f/MODULE_4caf7deb700973d9f449+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7715 |
neuronxcc-2.17.194.0+d312836f/MODULE_a6b635cb5d8d2a5539a7+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7716 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_52f77cf05a48696d505f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7717 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_7e8a971b679cd1f1877b+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/mistral/HuggingFaceH4/zephyr-7b-beta/a3def2b08381a583fdae.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "HuggingFaceH4/zephyr-7b-beta",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"MistralForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 32768,
|
| 15 |
+
"model_type": "mistral",
|
| 16 |
+
"neuron": {
|
| 17 |
+
"auto_cast_type": "bf16",
|
| 18 |
+
"batch_size": 4,
|
| 19 |
+
"checkpoint_id": "HuggingFaceH4/zephyr-7b-beta",
|
| 20 |
+
"checkpoint_revision": "892b3d7a7b1cf10c7a701c60881cd93df615734c",
|
| 21 |
+
"compiler_type": "neuronx-cc",
|
| 22 |
+
"compiler_version": "2.17.194.0+d312836f",
|
| 23 |
+
"num_cores": 2,
|
| 24 |
+
"sequence_length": 4096,
|
| 25 |
+
"task": "text-generation"
|
| 26 |
+
},
|
| 27 |
+
"num_attention_heads": 32,
|
| 28 |
+
"num_hidden_layers": 32,
|
| 29 |
+
"num_key_value_heads": 8,
|
| 30 |
+
"rms_norm_eps": 1e-05,
|
| 31 |
+
"rope_theta": 10000.0,
|
| 32 |
+
"sliding_window": 4096,
|
| 33 |
+
"tie_word_embeddings": false,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 32000
|
| 36 |
+
}
|
neuronxcc-2.17.194.0+d312836f/MODULE_52f77cf05a48696d505f+613edded/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
|
neuronxcc-2.17.194.0+d312836f/MODULE_52f77cf05a48696d505f+613edded/model.done
ADDED
|
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_52f77cf05a48696d505f+613edded/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa64e2242882ebae41eba74c882325cb659c171fa0b7be8d757340cc5ce9cc41
|
| 3 |
+
size 363541
|
neuronxcc-2.17.194.0+d312836f/MODULE_52f77cf05a48696d505f+613edded/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a08b05ae157129f4af3436f7eb419b06dda29048a2aaf80938e4217ca44a7b8e
|
| 3 |
+
size 9227264
|
neuronxcc-2.17.194.0+d312836f/MODULE_7e8a971b679cd1f1877b+613edded/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
|
neuronxcc-2.17.194.0+d312836f/MODULE_7e8a971b679cd1f1877b+613edded/model.done
ADDED
|
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_7e8a971b679cd1f1877b+613edded/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85d0b26290611750475222ffe3d4af958525a29574c9be47a3f92b6e3fb8168c
|
| 3 |
+
size 537196468
|
neuronxcc-2.17.194.0+d312836f/MODULE_7e8a971b679cd1f1877b+613edded/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:693cd7dd5d19a3f4d9e4635b3680ee6cf1a32e226f5194432b9a84789b76c2b5
|
| 3 |
+
size 6779904
|