Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
 Community
662
dacorvo HF Staff commited on
Commit
beb63cb
·
verified ·
1 Parent(s): 347cdb8

Synchronizing local compiler cache.

Browse files
Files changed (12) hide show
  1. .gitattributes +3 -0
  2. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev2/719fe7a9c6374369ebb3c8b70e3ca2e20d29e8d4c6f1965131b188cd23d90d00/e39d5faa34fb45bc2604.json +56 -0
  3. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev2/llama/TinyLlama/TinyLlama-1.1B-Chat-v1.0/e39d5faa34fb45bc2604.json +56 -0
  4. neuronxcc-2.21.33363.0+82129205/MODULE_7e267511886adabe44b8+a02c3a36/compile_flags.json +1 -0
  5. neuronxcc-2.21.33363.0+82129205/MODULE_7e267511886adabe44b8+a02c3a36/model.done +0 -0
  6. neuronxcc-2.21.33363.0+82129205/MODULE_7e267511886adabe44b8+a02c3a36/model.hlo_module.pb +3 -0
  7. neuronxcc-2.21.33363.0+82129205/MODULE_7e267511886adabe44b8+a02c3a36/model.neff +3 -0
  8. neuronxcc-2.21.33363.0+82129205/MODULE_7e267511886adabe44b8+a02c3a36/wrapped_neff.hlo +3 -0
  9. neuronxcc-2.21.33363.0+82129205/MODULE_da062f1b3996a6baa3e0+24129607/compile_flags.json +1 -0
  10. neuronxcc-2.21.33363.0+82129205/MODULE_da062f1b3996a6baa3e0+24129607/model.done +0 -0
  11. neuronxcc-2.21.33363.0+82129205/MODULE_da062f1b3996a6baa3e0+24129607/model.hlo_module.pb +3 -0
  12. neuronxcc-2.21.33363.0+82129205/MODULE_da062f1b3996a6baa3e0+24129607/model.neff +3 -0
.gitattributes CHANGED
@@ -17003,3 +17003,6 @@ neuronxcc-2.21.33363.0+82129205/MODULE_b1dd0905b0e6b3662c39+a02c3a36/model.neff
17003
  neuronxcc-2.21.33363.0+82129205/MODULE_b1dd0905b0e6b3662c39+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
17004
  neuronxcc-2.21.33363.0+82129205/MODULE_62356b84f669421024eb+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
17005
  neuronxcc-2.21.33363.0+82129205/MODULE_62356b84f669421024eb+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
17003
  neuronxcc-2.21.33363.0+82129205/MODULE_b1dd0905b0e6b3662c39+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
17004
  neuronxcc-2.21.33363.0+82129205/MODULE_62356b84f669421024eb+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
17005
  neuronxcc-2.21.33363.0+82129205/MODULE_62356b84f669421024eb+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
17006
+ neuronxcc-2.21.33363.0+82129205/MODULE_7e267511886adabe44b8+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
17007
+ neuronxcc-2.21.33363.0+82129205/MODULE_7e267511886adabe44b8+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
17008
+ neuronxcc-2.21.33363.0+82129205/MODULE_da062f1b3996a6baa3e0+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev2/719fe7a9c6374369ebb3c8b70e3ca2e20d29e8d4c6f1965131b188cd23d90d00/e39d5faa34fb45bc2604.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": "0.4.6.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+82129205/0_REGISTRY/0.4.6.dev2/llama/TinyLlama/TinyLlama-1.1B-Chat-v1.0/e39d5faa34fb45bc2604.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": "0.4.6.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_7e267511886adabe44b8+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_7e267511886adabe44b8+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_7e267511886adabe44b8+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16a280ae34e2f0c4e1fd75f89717704cb890dec2d5aa707665e4062aa9628619
3
+ size 586700
neuronxcc-2.21.33363.0+82129205/MODULE_7e267511886adabe44b8+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f34a457983c7141061eaf4adc1257a7cf8bdc4467a027eb8ce91688093fe67f
3
+ size 1854464
neuronxcc-2.21.33363.0+82129205/MODULE_7e267511886adabe44b8+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df76e324495406c8129be79c03e3626fc681ee612378e5f4c05bcc0f491e378f
3
+ size 1956451
neuronxcc-2.21.33363.0+82129205/MODULE_da062f1b3996a6baa3e0+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_da062f1b3996a6baa3e0+24129607/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_da062f1b3996a6baa3e0+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99c7d977b68be000f45a860ea4680dfcf9243d026ef2b25e8893df439c4e4010
3
+ size 501931
neuronxcc-2.21.33363.0+82129205/MODULE_da062f1b3996a6baa3e0+24129607/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:479169c3da5f55272696b1e3cd480b00329446861678aab18a60b785ae1ecff6
3
+ size 15954944