add model
Browse files- config.json +56 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./squad_bert_base/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"device_iterations": 2,
|
| 9 |
+
"embedding_serialization_factor": 0,
|
| 10 |
+
"enable_half_first_order_momentum": true,
|
| 11 |
+
"enable_half_partials": true,
|
| 12 |
+
"executable_cache_dir": "./exe_cache",
|
| 13 |
+
"gradient_accumulation_steps": 16,
|
| 14 |
+
"gradient_checkpointing": false,
|
| 15 |
+
"hidden_act": "gelu",
|
| 16 |
+
"hidden_dropout_prob": 0.1,
|
| 17 |
+
"hidden_size": 768,
|
| 18 |
+
"inference_device_iterations": 4,
|
| 19 |
+
"inference_replication_factor": 4,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"ipus_per_replica": 4,
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"layers_per_ipu": [
|
| 25 |
+
0,
|
| 26 |
+
4,
|
| 27 |
+
4,
|
| 28 |
+
4
|
| 29 |
+
],
|
| 30 |
+
"matmul_proportion": [
|
| 31 |
+
0.25,
|
| 32 |
+
0.2,
|
| 33 |
+
0.2,
|
| 34 |
+
0.25
|
| 35 |
+
],
|
| 36 |
+
"max_position_embeddings": 512,
|
| 37 |
+
"model_type": "bert",
|
| 38 |
+
"num_attention_heads": 12,
|
| 39 |
+
"num_hidden_layers": 12,
|
| 40 |
+
"optimizer_state_offchip": false,
|
| 41 |
+
"optimum_version": "0.1.2",
|
| 42 |
+
"pad_token_id": 0,
|
| 43 |
+
"position_embedding_type": "absolute",
|
| 44 |
+
"profile_dir": null,
|
| 45 |
+
"recompute_checkpoint_every_layer": true,
|
| 46 |
+
"replicated_tensor_sharding": true,
|
| 47 |
+
"replication_factor": 4,
|
| 48 |
+
"seed": null,
|
| 49 |
+
"synthetic_data": false,
|
| 50 |
+
"torch_dtype": "float32",
|
| 51 |
+
"transformers_version": "4.17.0.dev0",
|
| 52 |
+
"type_vocab_size": 2,
|
| 53 |
+
"use_cache": true,
|
| 54 |
+
"use_popdist": false,
|
| 55 |
+
"vocab_size": 30522
|
| 56 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:843d35129d4eed8eedd0608868891d3ab6687d5e09062b4ce22666ea3d7bb76a
|
| 3 |
+
size 435653361
|