Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
 Community
optimum-internal-testing-user commited on
Commit
fc73b24
·
verified ·
1 Parent(s): 0e19766

Synchronizing local compiler cache.

Browse files
Files changed (7) hide show
  1. neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/b7ad8e4280fe3bda1fab.json +64 -0
  2. neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7/llama/unsloth/Llama-3.2-1B-Instruct/b7ad8e4280fe3bda1fab.json +64 -0
  3. neuronxcc-2.26.6360.0+6f180f47/MODULE_cef50dd7a142db2bfa48+84337dd9/model.hlo_module.pb +1 -1
  4. neuronxcc-2.26.6360.0+6f180f47/MODULE_cef50dd7a142db2bfa48+84337dd9/model.neff +1 -1
  5. neuronxcc-2.26.6360.0+6f180f47/MODULE_cef50dd7a142db2bfa48+84337dd9/wrapped_neff.hlo +1 -1
  6. neuronxcc-2.26.6360.0+6f180f47/MODULE_dc04527b827075028b3a+519f203d/model.hlo_module.pb +1 -1
  7. neuronxcc-2.26.6360.0+6f180f47/MODULE_dc04527b827075028b3a+519f203d/model.neff +1 -1
neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/b7ad8e4280fe3bda1fab.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "unsloth/Llama-3.2-1B-Instruct",
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": 8192,
16
+ "max_position_embeddings": 131072,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "neuron": {
20
+ "_serialized_key": "NxDNeuronConfig",
21
+ "batch_size": 4,
22
+ "capacity_factor": null,
23
+ "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
24
+ "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
25
+ "continuous_batching": true,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 2,
30
+ "max_batch_size": 4,
31
+ "max_context_length": 1024,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 1024,
34
+ "neuronxcc_version": "2.26.6360.0+6f180f47",
35
+ "on_device_sampling": true,
36
+ "optimum_neuron_version": "0.4.7",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "prefill_chunk_size": 0,
40
+ "sequence_length": 1024,
41
+ "speculation_length": 0,
42
+ "start_rank_id": 0,
43
+ "target": "trn1",
44
+ "torch_dtype": "bfloat16",
45
+ "tp_degree": 2
46
+ },
47
+ "num_attention_heads": 32,
48
+ "num_hidden_layers": 16,
49
+ "num_key_value_heads": 8,
50
+ "pretraining_tp": 1,
51
+ "rms_norm_eps": 1e-05,
52
+ "rope_scaling": {
53
+ "factor": 32.0,
54
+ "high_freq_factor": 4.0,
55
+ "low_freq_factor": 1.0,
56
+ "original_max_position_embeddings": 8192,
57
+ "rope_type": "llama3"
58
+ },
59
+ "rope_theta": 500000.0,
60
+ "tie_word_embeddings": true,
61
+ "unsloth_fixed": true,
62
+ "use_cache": true,
63
+ "vocab_size": 128256
64
+ }
neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7/llama/unsloth/Llama-3.2-1B-Instruct/b7ad8e4280fe3bda1fab.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "unsloth/Llama-3.2-1B-Instruct",
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": 8192,
16
+ "max_position_embeddings": 131072,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "neuron": {
20
+ "_serialized_key": "NxDNeuronConfig",
21
+ "batch_size": 4,
22
+ "capacity_factor": null,
23
+ "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
24
+ "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
25
+ "continuous_batching": true,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 2,
30
+ "max_batch_size": 4,
31
+ "max_context_length": 1024,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 1024,
34
+ "neuronxcc_version": "2.26.6360.0+6f180f47",
35
+ "on_device_sampling": true,
36
+ "optimum_neuron_version": "0.4.7",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "prefill_chunk_size": 0,
40
+ "sequence_length": 1024,
41
+ "speculation_length": 0,
42
+ "start_rank_id": 0,
43
+ "target": "trn1",
44
+ "torch_dtype": "bfloat16",
45
+ "tp_degree": 2
46
+ },
47
+ "num_attention_heads": 32,
48
+ "num_hidden_layers": 16,
49
+ "num_key_value_heads": 8,
50
+ "pretraining_tp": 1,
51
+ "rms_norm_eps": 1e-05,
52
+ "rope_scaling": {
53
+ "factor": 32.0,
54
+ "high_freq_factor": 4.0,
55
+ "low_freq_factor": 1.0,
56
+ "original_max_position_embeddings": 8192,
57
+ "rope_type": "llama3"
58
+ },
59
+ "rope_theta": 500000.0,
60
+ "tie_word_embeddings": true,
61
+ "unsloth_fixed": true,
62
+ "use_cache": true,
63
+ "vocab_size": 128256
64
+ }
neuronxcc-2.26.6360.0+6f180f47/MODULE_cef50dd7a142db2bfa48+84337dd9/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae56de24d1e76448c0ead07c7991c936c76a8dc69040e83fb6213c5f11008655
3
  size 413132
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e81a6bb613ca6e23c5d826c31894902872d2350268eb9644edff019e9ee5a7b5
3
  size 413132
neuronxcc-2.26.6360.0+6f180f47/MODULE_cef50dd7a142db2bfa48+84337dd9/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:383a3f0a036dba2a782f45fc5ffd0b274eb4913d737be5b7e99e9f97e2adfc85
3
  size 2110464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60fc849ebed8542f68c2bc0fb3b4e7af21d22b7ff9e0af22d4c86977c2cd6be5
3
  size 2110464
neuronxcc-2.26.6360.0+6f180f47/MODULE_cef50dd7a142db2bfa48+84337dd9/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a001ce6bc081e8fc296ee1b4ae54b1affbba2466233102ba6af434d431096430
3
  size 2184663
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c775d6f64d7854903d53d94a043ca2ae523192e7d45118b956935d48ce058197
3
  size 2184663
neuronxcc-2.26.6360.0+6f180f47/MODULE_dc04527b827075028b3a+519f203d/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f5eb641efe865351984a59ec111479a2e0ebc2960d4183567fb785a64addc79
3
  size 399272
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:311741d4af048747f8bbaa8706a845db93388385160bce795c4b1cb2cc213ae7
3
  size 399272
neuronxcc-2.26.6360.0+6f180f47/MODULE_dc04527b827075028b3a+519f203d/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf81f3d00786a1466f3f3b5677b3ec6251df9efd6d061d771154616c3dbb2c92
3
  size 3062784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b34f34b9e356e9450669c356d13f8c58dd2e9a1a5eb634b28367c2c4624b96
3
  size 3062784