Upload 4 files
Browse files- config.json +2 -2
- model.onnx +2 -2
- ort_config.json +1 -3
config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "/data/models/bge-m3-onnx-o4",
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"bos_token_id": 0,
|
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"pad_token_id": 1,
|
| 22 |
"position_embedding_type": "absolute",
|
| 23 |
"torch_dtype": "float32",
|
| 24 |
-
"transformers_version": "4.
|
| 25 |
"type_vocab_size": 1,
|
| 26 |
"use_cache": true,
|
| 27 |
"vocab_size": 250002
|
|
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "/data/models/bge-m3-onnx-o4",
|
| 3 |
"architectures": [
|
| 4 |
+
"BGEM3InferenceModel"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"bos_token_id": 0,
|
|
|
|
| 21 |
"pad_token_id": 1,
|
| 22 |
"position_embedding_type": "absolute",
|
| 23 |
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.46.3",
|
| 25 |
"type_vocab_size": 1,
|
| 26 |
"use_cache": true,
|
| 27 |
"vocab_size": 250002
|
model.onnx
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 sha256:978c4f95cfbfa29afb0cf2fe5b249a456154a6d9ff5bf93beeb369ec07fcfa3f
|
| 3 |
+
size 352864
|
ort_config.json
CHANGED
|
@@ -25,15 +25,13 @@
|
|
| 25 |
"enable_transformers_specific_optimizations": true,
|
| 26 |
"fp16": true,
|
| 27 |
"no_attention_mask": false,
|
| 28 |
-
"optimization_level":
|
| 29 |
"optimize_for_gpu": true,
|
| 30 |
"optimize_with_onnxruntime_only": null,
|
| 31 |
"use_mask_index": false,
|
| 32 |
"use_multi_head_attention": false,
|
| 33 |
"use_raw_attention_mask": false
|
| 34 |
},
|
| 35 |
-
"optimum_version": "1.17.0",
|
| 36 |
"quantization": {},
|
| 37 |
-
"transformers_version": "4.47.1",
|
| 38 |
"use_external_data_format": true
|
| 39 |
}
|
|
|
|
| 25 |
"enable_transformers_specific_optimizations": true,
|
| 26 |
"fp16": true,
|
| 27 |
"no_attention_mask": false,
|
| 28 |
+
"optimization_level": 99,
|
| 29 |
"optimize_for_gpu": true,
|
| 30 |
"optimize_with_onnxruntime_only": null,
|
| 31 |
"use_mask_index": false,
|
| 32 |
"use_multi_head_attention": false,
|
| 33 |
"use_raw_attention_mask": false
|
| 34 |
},
|
|
|
|
| 35 |
"quantization": {},
|
|
|
|
| 36 |
"use_external_data_format": true
|
| 37 |
}
|