Synchronizing local compiler cache.
Browse files- .gitattributes +2 -0
- neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/granite/ibm-granite/granite-3.1-8b-instruct/21fede0703904ef6a5cc.json +41 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_068ef074748718999f13+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_068ef074748718999f13+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_068ef074748718999f13+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_068ef074748718999f13+613edded/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_b03a85564a20a74980e5+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_b03a85564a20a74980e5+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_b03a85564a20a74980e5+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_b03a85564a20a74980e5+613edded/model.neff +3 -0
.gitattributes
CHANGED
|
@@ -7725,3 +7725,5 @@ neuronxcc-2.17.194.0+d312836f/MODULE_23c20ba5fd4672262b4f+613edded/model.neff fi
|
|
| 7725 |
neuronxcc-2.17.194.0+d312836f/MODULE_2f7a5096c6360565985d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7726 |
neuronxcc-2.17.194.0+d312836f/MODULE_3c81d5bfa3880165b963+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7727 |
neuronxcc-2.17.194.0+d312836f/MODULE_cb3ceed5baf6cff96237+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 7725 |
neuronxcc-2.17.194.0+d312836f/MODULE_2f7a5096c6360565985d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7726 |
neuronxcc-2.17.194.0+d312836f/MODULE_3c81d5bfa3880165b963+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7727 |
neuronxcc-2.17.194.0+d312836f/MODULE_cb3ceed5baf6cff96237+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7728 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_068ef074748718999f13+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7729 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_b03a85564a20a74980e5+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev2/inference/granite/ibm-granite/granite-3.1-8b-instruct/21fede0703904ef6a5cc.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "ibm-granite/granite-3.1-8b-instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GraniteForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.1,
|
| 10 |
+
"attention_multiplier": 0.0078125,
|
| 11 |
+
"embedding_multiplier": 12.0,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 4096,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 12800,
|
| 16 |
+
"logits_scaling": 16.0,
|
| 17 |
+
"max_position_embeddings": 131072,
|
| 18 |
+
"mlp_bias": false,
|
| 19 |
+
"model_type": "granite",
|
| 20 |
+
"neuron": {
|
| 21 |
+
"auto_cast_type": "bf16",
|
| 22 |
+
"batch_size": 1,
|
| 23 |
+
"checkpoint_id": "ibm-granite/granite-3.1-8b-instruct",
|
| 24 |
+
"checkpoint_revision": "3f05a1d007b2484bbf17593efe110bd5b9d67655",
|
| 25 |
+
"compiler_type": "neuronx-cc",
|
| 26 |
+
"compiler_version": "2.17.194.0+d312836f",
|
| 27 |
+
"num_cores": 8,
|
| 28 |
+
"sequence_length": 4096,
|
| 29 |
+
"task": "text-generation"
|
| 30 |
+
},
|
| 31 |
+
"num_attention_heads": 32,
|
| 32 |
+
"num_hidden_layers": 40,
|
| 33 |
+
"num_key_value_heads": 8,
|
| 34 |
+
"residual_multiplier": 0.22,
|
| 35 |
+
"rms_norm_eps": 1e-05,
|
| 36 |
+
"rope_scaling": null,
|
| 37 |
+
"rope_theta": 10000000.0,
|
| 38 |
+
"tie_word_embeddings": true,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 49155
|
| 41 |
+
}
|
neuronxcc-2.17.194.0+d312836f/MODULE_068ef074748718999f13+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_068ef074748718999f13+613edded/model.done
ADDED
|
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_068ef074748718999f13+613edded/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4db209a482bf47e85f6fdaa653cf490bf3a08f633d3245452208b53c34d2036
|
| 3 |
+
size 427799
|
neuronxcc-2.17.194.0+d312836f/MODULE_068ef074748718999f13+613edded/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2e8a4cf31f45f72a21fab17c8d231cf790365a07862dad04c70c12c0113d789
|
| 3 |
+
size 3144704
|
neuronxcc-2.17.194.0+d312836f/MODULE_b03a85564a20a74980e5+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_b03a85564a20a74980e5+613edded/model.done
ADDED
|
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_b03a85564a20a74980e5+613edded/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f02ede0b7bf25bc34f29c6fc0419ad46285bec11c97e1a0cd06e7d24a0997d4a
|
| 3 |
+
size 539864
|
neuronxcc-2.17.194.0+d312836f/MODULE_b03a85564a20a74980e5+613edded/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:beebae36ba6983d2bd123856fd3768d98fa85c6169e965fd29fcff2288bd520d
|
| 3 |
+
size 2018304
|