dacorvo HF Staff commited on
Commit
a281698
·
verified ·
1 Parent(s): e8b11fb

Synchronizing local compiler cache.

Browse files
.gitattributes CHANGED
@@ -15429,3 +15429,6 @@ neuronxcc-2.21.33363.0+82129205/MODULE_f59b0af46e506b254df0+24129607/model.neff
15429
  neuronxcc-2.21.33363.0+82129205/MODULE_4f2fadcb51cfc54f399a+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
15430
  neuronxcc-2.21.33363.0+82129205/MODULE_4f2fadcb51cfc54f399a+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
15431
  neuronxcc-2.21.33363.0+82129205/MODULE_73ebedc81bdd4f6771fc+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
15429
  neuronxcc-2.21.33363.0+82129205/MODULE_4f2fadcb51cfc54f399a+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
15430
  neuronxcc-2.21.33363.0+82129205/MODULE_4f2fadcb51cfc54f399a+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
15431
  neuronxcc-2.21.33363.0+82129205/MODULE_73ebedc81bdd4f6771fc+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
15432
+ neuronxcc-2.21.33363.0+82129205/MODULE_2d801f82244521e2a126+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
15433
+ neuronxcc-2.21.33363.0+82129205/MODULE_a68880909bf179812355+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
15434
+ neuronxcc-2.21.33363.0+82129205/MODULE_a68880909bf179812355+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/TinyLlama/TinyLlama-1.1B-Chat-v1.0/8eaae209d19ad64d6e5c.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "LlamaForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dtype": "bfloat16",
11
+ "head_dim": 64,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 5632,
16
+ "max_position_embeddings": 2048,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "neuron": {
20
+ "_serialized_key": "NxDNeuronConfig",
21
+ "batch_size": 1,
22
+ "capacity_factor": null,
23
+ "checkpoint_id": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
24
+ "checkpoint_revision": "fe8a4ea1ffedaf415f4da2f062534de366a451e6",
25
+ "continuous_batching": false,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 2,
30
+ "max_batch_size": 1,
31
+ "max_context_length": 2048,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 2048,
34
+ "neuronxcc_version": "2.21.33363.0+82129205",
35
+ "on_device_sampling": true,
36
+ "optimum_neuron_version": "0.4.4.dev2",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 2048,
40
+ "speculation_length": 0,
41
+ "start_rank_id": 0,
42
+ "target": "trn1",
43
+ "torch_dtype": "bfloat16",
44
+ "tp_degree": 2
45
+ },
46
+ "num_attention_heads": 32,
47
+ "num_hidden_layers": 22,
48
+ "num_key_value_heads": 4,
49
+ "pretraining_tp": 1,
50
+ "rms_norm_eps": 1e-05,
51
+ "rope_scaling": null,
52
+ "rope_theta": 10000.0,
53
+ "tie_word_embeddings": false,
54
+ "use_cache": true,
55
+ "vocab_size": 32000
56
+ }
neuronxcc-2.21.33363.0+82129205/MODULE_2d801f82244521e2a126+24129607/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_2d801f82244521e2a126+24129607/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_2d801f82244521e2a126+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c41535b6dcd6da367ba32b77b02e46766df9f17d9e85724ec634e0bc0f81c35
3
+ size 501931
neuronxcc-2.21.33363.0+82129205/MODULE_2d801f82244521e2a126+24129607/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f6853cc5b7bfb5f3a23cc403f80c8f734f20ef213b55562fb1cab6a5fdedd74
3
+ size 15954944
neuronxcc-2.21.33363.0+82129205/MODULE_a68880909bf179812355+a02c3a36/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_a68880909bf179812355+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_a68880909bf179812355+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6454c02512e5b70155da9285856b9f6b00ff410dff7307e5821c15562c3e303
3
+ size 563250
neuronxcc-2.21.33363.0+82129205/MODULE_a68880909bf179812355+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9863730c45d6046949574da1f0961d38ae3a03edc3897c8c764f27f6cc86e1a
3
+ size 1803264
neuronxcc-2.21.33363.0+82129205/MODULE_a68880909bf179812355+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3d0da9c2b25db5a983ff897a357ba882b52f661dff3c0c83d96113ac3e8c963
3
+ size 1905251