dacorvo HF Staff commited on
Commit
dbac958
·
verified ·
1 Parent(s): 35d3b35

Synchronizing local compiler cache.

Browse files
.gitattributes CHANGED
@@ -7715,3 +7715,5 @@ neuronxcc-2.17.194.0+d312836f/MODULE_4caf7deb700973d9f449+613edded/model.neff fi
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
 
 
 
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
7718
+ neuronxcc-2.17.194.0+d312836f/MODULE_8eeb8fbc4eb3349acc04+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7719
+ neuronxcc-2.17.194.0+d312836f/MODULE_fa8e5e93b134884838d5+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/9c4fc51180f9ddea7ebd.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": 4,
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": 2,
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_8eeb8fbc4eb3349acc04+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_8eeb8fbc4eb3349acc04+613edded/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_8eeb8fbc4eb3349acc04+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7df943bb7f889fc84bf253a4ab84c6e1c32255875564778baee826477a8add71
3
+ size 597520
neuronxcc-2.17.194.0+d312836f/MODULE_8eeb8fbc4eb3349acc04+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:591934180bc28df76e6474c9a402d8797def1f4bc899544b127454c11d7fc592
3
+ size 6339584
neuronxcc-2.17.194.0+d312836f/MODULE_fa8e5e93b134884838d5+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_fa8e5e93b134884838d5+613edded/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_fa8e5e93b134884838d5+613edded/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73ac916fe2e1bfd0ad76458980a7b45897d7d9481a22942186088624b541ce02
3
+ size 467931
neuronxcc-2.17.194.0+d312836f/MODULE_fa8e5e93b134884838d5+613edded/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a5f276c3dd33737b43c2ed5259a1332517dc2edf9feac067f85a44c3b076f08
3
+ size 11572224