Upload folder using huggingface_hub
Browse files- config.json +16 -10
- model.neuron +2 -2
- tokenizer_config.json +1 -0
config.json
CHANGED
|
@@ -1,10 +1,12 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"_name_or_path": "BAAI/bge-base-en-v1.5",
|
| 3 |
"architectures": [
|
| 4 |
"BertModel"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
|
|
|
| 8 |
"gradient_checkpointing": false,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
|
@@ -24,29 +26,33 @@
|
|
| 24 |
"auto_cast": null,
|
| 25 |
"auto_cast_type": null,
|
| 26 |
"compiler_type": "neuronx-cc",
|
| 27 |
-
"compiler_version": "2.
|
| 28 |
-
"disable_fallback": false,
|
| 29 |
-
"disable_fast_relayout": false,
|
| 30 |
"dynamic_batch_size": false,
|
|
|
|
| 31 |
"input_names": [
|
| 32 |
"input_ids",
|
| 33 |
-
"attention_mask"
|
| 34 |
-
"token_type_ids"
|
| 35 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
"output_names": [
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
],
|
| 40 |
"static_batch_size": 1,
|
| 41 |
-
"static_sequence_length": 384
|
|
|
|
| 42 |
},
|
| 43 |
"num_attention_heads": 12,
|
| 44 |
"num_hidden_layers": 12,
|
| 45 |
"pad_token_id": 0,
|
| 46 |
"position_embedding_type": "absolute",
|
| 47 |
-
"task":
|
| 48 |
"torch_dtype": "float32",
|
| 49 |
-
"
|
|
|
|
| 50 |
"type_vocab_size": 2,
|
| 51 |
"use_cache": true,
|
| 52 |
"vocab_size": 30522
|
|
|
|
| 1 |
{
|
| 2 |
+
"_attn_implementation_autoset": true,
|
| 3 |
"_name_or_path": "BAAI/bge-base-en-v1.5",
|
| 4 |
"architectures": [
|
| 5 |
"BertModel"
|
| 6 |
],
|
| 7 |
"attention_probs_dropout_prob": 0.1,
|
| 8 |
"classifier_dropout": null,
|
| 9 |
+
"export_model_type": "transformer",
|
| 10 |
"gradient_checkpointing": false,
|
| 11 |
"hidden_act": "gelu",
|
| 12 |
"hidden_dropout_prob": 0.1,
|
|
|
|
| 26 |
"auto_cast": null,
|
| 27 |
"auto_cast_type": null,
|
| 28 |
"compiler_type": "neuronx-cc",
|
| 29 |
+
"compiler_version": "2.16.372.0+4a9b2326",
|
|
|
|
|
|
|
| 30 |
"dynamic_batch_size": false,
|
| 31 |
+
"inline_weights_to_neff": false,
|
| 32 |
"input_names": [
|
| 33 |
"input_ids",
|
| 34 |
+
"attention_mask"
|
|
|
|
| 35 |
],
|
| 36 |
+
"model_type": "transformer",
|
| 37 |
+
"optlevel": "2",
|
| 38 |
+
"output_attentions": false,
|
| 39 |
+
"output_hidden_states": false,
|
| 40 |
"output_names": [
|
| 41 |
+
"token_embeddings",
|
| 42 |
+
"sentence_embedding"
|
| 43 |
],
|
| 44 |
"static_batch_size": 1,
|
| 45 |
+
"static_sequence_length": 384,
|
| 46 |
+
"tensor_parallel_size": 1
|
| 47 |
},
|
| 48 |
"num_attention_heads": 12,
|
| 49 |
"num_hidden_layers": 12,
|
| 50 |
"pad_token_id": 0,
|
| 51 |
"position_embedding_type": "absolute",
|
| 52 |
+
"task": "feature-extraction",
|
| 53 |
"torch_dtype": "float32",
|
| 54 |
+
"torchscript": true,
|
| 55 |
+
"transformers_version": "4.48.3",
|
| 56 |
"type_vocab_size": 2,
|
| 57 |
"use_cache": true,
|
| 58 |
"vocab_size": 30522
|
model.neuron
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c32bd2adef487a1a9b55995610f41144419cf1fe2e391c3b1cd3eeb7f5af9e18
|
| 3 |
+
size 436483448
|
tokenizer_config.json
CHANGED
|
@@ -45,6 +45,7 @@
|
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": true,
|
|
|
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
"model_max_length": 512,
|
| 50 |
"never_split": null,
|
|
|
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
"mask_token": "[MASK]",
|
| 50 |
"model_max_length": 512,
|
| 51 |
"never_split": null,
|