Synchronizing local compiler cache.
Browse files- neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/Qwen/Qwen2.5-0.5B/2c2550e69bd7b8401151.json +83 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/model.hlo_module.pb +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/wrapped_neff.hlo +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.hlo_module.pb +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/wrapped_neff.hlo +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.hlo_module.pb +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/wrapped_neff.hlo +1 -1
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev1/qwen2/Qwen/Qwen2.5-0.5B/2c2550e69bd7b8401151.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-0.5B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 896,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4864,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention"
|
| 39 |
+
],
|
| 40 |
+
"max_position_embeddings": 32768,
|
| 41 |
+
"max_window_layers": 24,
|
| 42 |
+
"model_type": "qwen2",
|
| 43 |
+
"neuron": {
|
| 44 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 45 |
+
"batch_size": 1,
|
| 46 |
+
"capacity_factor": null,
|
| 47 |
+
"checkpoint_id": "Qwen/Qwen2.5-0.5B",
|
| 48 |
+
"checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
|
| 49 |
+
"continuous_batching": false,
|
| 50 |
+
"ep_degree": 1,
|
| 51 |
+
"fused_qkv": false,
|
| 52 |
+
"glu_mlp": true,
|
| 53 |
+
"local_ranks_size": 2,
|
| 54 |
+
"max_batch_size": 1,
|
| 55 |
+
"max_context_length": 8192,
|
| 56 |
+
"max_topk": 256,
|
| 57 |
+
"n_active_tokens": 8192,
|
| 58 |
+
"neuronxcc_version": "2.21.33363.0+82129205",
|
| 59 |
+
"on_device_sampling": true,
|
| 60 |
+
"optimum_neuron_version": "0.4.4.dev1",
|
| 61 |
+
"output_logits": false,
|
| 62 |
+
"pp_degree": 1,
|
| 63 |
+
"sequence_length": 8192,
|
| 64 |
+
"sequence_parallel_enabled": false,
|
| 65 |
+
"speculation_length": 0,
|
| 66 |
+
"start_rank_id": 0,
|
| 67 |
+
"target": "trn1",
|
| 68 |
+
"torch_dtype": "bfloat16",
|
| 69 |
+
"tp_degree": 2
|
| 70 |
+
},
|
| 71 |
+
"num_attention_heads": 14,
|
| 72 |
+
"num_hidden_layers": 24,
|
| 73 |
+
"num_key_value_heads": 2,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_scaling": null,
|
| 76 |
+
"rope_theta": 1000000.0,
|
| 77 |
+
"sliding_window": null,
|
| 78 |
+
"tie_word_embeddings": true,
|
| 79 |
+
"use_cache": true,
|
| 80 |
+
"use_mrope": false,
|
| 81 |
+
"use_sliding_window": false,
|
| 82 |
+
"vocab_size": 151936
|
| 83 |
+
}
|
neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 596952
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6361b23631f22b3534873d4bc3fde1c4197b34dc2d5d84b8097108cc7faed45
|
| 3 |
size 596952
|
neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1936384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0be47707e53a60759826fc077df760c768f27f3699574a1ca42a2c1721ac66bc
|
| 3 |
size 1936384
|
neuronxcc-2.21.33363.0+82129205/MODULE_1934c2fc93e7793f0aef+a02c3a36/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2092575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e23e21a3d39349b0a3b066fd29eb841c6bb9dba1fde90c7a0792c5717638a18
|
| 3 |
size 2092575
|
neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 726810
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:582186d6720ce0ec6cface8ce4f88aaf732f9fb6f153b9026e4086c88b7bf975
|
| 3 |
size 726810
|
neuronxcc-2.21.33363.0+82129205/MODULE_30826b478ad3db0c312e+24129607/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 71302144
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:703e9869407930e4c758082af24dc8f38370a34a61991c8115d0135a70e5a8be
|
| 3 |
size 71302144
|
neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3073024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f6b941c15ed66c686b8acff2b452ead98bcf0a038a2569fb7a79463ea49703a
|
| 3 |
size 3073024
|
neuronxcc-2.21.33363.0+82129205/MODULE_3c75648f1b6d85bd72d5+a02c3a36/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3147125
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3251669900d2348ad53608811a4ffc8d5adb276028f5b97a24b9dcb52014473d
|
| 3 |
size 3147125
|
neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 643371
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70d262e66d2fc1d09841f5c0cf8aac87d350ff22163dee1fcb520515189c79d6
|
| 3 |
size 643371
|
neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1721344
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34b2e76b644a973caa852fbe966d2f4832aeb83f4ee6b130c4112910437adab6
|
| 3 |
size 1721344
|
neuronxcc-2.21.33363.0+82129205/MODULE_b6a329fd6d4912085786+a02c3a36/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1877650
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4928e4a9ad2a4572b8955baeacfd08de80d2a6433d1f56bff33e2d1e70be6ae8
|
| 3 |
size 1877650
|