Upload folder using huggingface_hub
Browse files- checkpoint-368000/1_Pooling/config.json +5 -0
- checkpoint-368000/2_Dense/config.json +8 -0
- checkpoint-368000/2_Dense/model.safetensors +3 -0
- checkpoint-368000/3_Normalize/config.json +4 -0
- checkpoint-368000/README.md +1448 -0
- checkpoint-368000/config.json +28 -0
- checkpoint-368000/config_sentence_transformers.json +14 -0
- checkpoint-368000/model.safetensors +3 -0
- checkpoint-368000/modules.json +26 -0
- checkpoint-368000/optimizer.pt +3 -0
- checkpoint-368000/resume_check.json +1 -0
- checkpoint-368000/rng_state.pth +3 -0
- checkpoint-368000/scaler.pt +3 -0
- checkpoint-368000/scheduler.pt +3 -0
- checkpoint-368000/sentence_bert_config.json +10 -0
- checkpoint-368000/tokenizer.json +0 -0
- checkpoint-368000/tokenizer_config.json +22 -0
- checkpoint-368000/trainer_state.json +0 -0
- checkpoint-368000/training_args.bin +3 -0
checkpoint-368000/1_Pooling/config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"embedding_dimension": 512,
|
| 3 |
+
"pooling_mode": "mean",
|
| 4 |
+
"include_prompt": true
|
| 5 |
+
}
|
checkpoint-368000/2_Dense/config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"in_features": 512,
|
| 3 |
+
"out_features": 1024,
|
| 4 |
+
"bias": false,
|
| 5 |
+
"activation_function": "torch.nn.modules.linear.Identity",
|
| 6 |
+
"module_input_name": "sentence_embedding",
|
| 7 |
+
"module_output_name": "sentence_embedding"
|
| 8 |
+
}
|
checkpoint-368000/2_Dense/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a3840900f56c563e57a39255f848a4c4d5591f91597ed9d14e474cdc485f7ed
|
| 3 |
+
size 2097240
|
checkpoint-368000/3_Normalize/config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"module_input_name": "sentence_embedding",
|
| 3 |
+
"module_output_name": "sentence_embedding"
|
| 4 |
+
}
|
checkpoint-368000/README.md
ADDED
|
@@ -0,0 +1,1448 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- sentence-transformers
|
| 4 |
+
- sentence-similarity
|
| 5 |
+
- feature-extraction
|
| 6 |
+
- dense
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
- loss:EmbedDistillLoss
|
| 9 |
+
base_model: much1na/distil-cohere-v1-ckpt
|
| 10 |
+
widget:
|
| 11 |
+
- source_sentence: tty number
|
| 12 |
+
sentences:
|
| 13 |
+
- how old jojo
|
| 14 |
+
- what is nrc
|
| 15 |
+
- boulle work
|
| 16 |
+
- source_sentence: rbbb causes
|
| 17 |
+
sentences:
|
| 18 |
+
- what is gpr?
|
| 19 |
+
- ireland food
|
| 20 |
+
- define adobe
|
| 21 |
+
- source_sentence: 'List of HBO Films films This is a list of films produced and distributed
|
| 22 |
+
by HBO Films.
|
| 23 |
+
|
| 24 |
+
1980s
|
| 25 |
+
|
| 26 |
+
1990s
|
| 27 |
+
|
| 28 |
+
2000s
|
| 29 |
+
|
| 30 |
+
2010s
|
| 31 |
+
|
| 32 |
+
2020s
|
| 33 |
+
|
| 34 |
+
Upcoming
|
| 35 |
+
|
| 36 |
+
HBO Documentary Films
|
| 37 |
+
|
| 38 |
+
HBO Comedy Specials'
|
| 39 |
+
sentences:
|
| 40 |
+
- 'The Seven Basic Plots The Seven Basic Plots: Why We Tell Stories is a 2004 book
|
| 41 |
+
by Christopher Booker containing a Jung-influenced analysis of stories and their
|
| 42 |
+
psychological meaning. Booker worked on the book for 34 years.
|
| 43 |
+
|
| 44 |
+
Summary'
|
| 45 |
+
- Empire of the Sun (band) Empire of the Sun is an Australian electronic music duo
|
| 46 |
+
formed in 2007. The duo is a collaboration between Luke Steele, of alternative
|
| 47 |
+
rock band The Sleepy Jackson, and Nick Littlemore, of electronic dance band Pnau.
|
| 48 |
+
- 'Going for Gold Going for Gold is a British television game show that originally
|
| 49 |
+
aired on BBC1 between 12 October 1987 and 9 July 1996. It was revived for Channel
|
| 50 |
+
5 from 13 October 2008 to 20 March 2009.
|
| 51 |
+
|
| 52 |
+
Background'
|
| 53 |
+
- source_sentence: "Tex Stackexchange\n\nQ: LYx 2.2. (Cannot view the file pdf) I\
|
| 54 |
+
\ get this error when trying to view the file:\nThe external program pdflatex\
|
| 55 |
+
\ finished with an error ... check the logs.\n\n(I am using LyX 2.2.0 Windows\
|
| 56 |
+
\ 7) \n"
|
| 57 |
+
sentences:
|
| 58 |
+
- "Apple Stackexchange\n\nQ: Turn Wifi Off via command line I'm sharing my internet\
|
| 59 |
+
\ in work and forgot to turn it off! Does anyone know how I can do it via the\
|
| 60 |
+
\ command line? I have SSH access but thats it. D'oh. \n\nA: Try \nnetworksetup\
|
| 61 |
+
\ -setairportpower en0 off\n\n"
|
| 62 |
+
- 'Stackoverflow Stackexchange
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
Q: Convert Bitmap to File I understand that using BitmapFactory can convert a
|
| 66 |
+
File to a Bitmap, but is there any way to convert a Bitmap image to a File?
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
A: Try this:
|
| 70 |
+
|
| 71 |
+
bitmap.compress(Bitmap.CompressFormat.PNG, quality, outStream);
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
See this
|
| 75 |
+
|
| 76 |
+
'
|
| 77 |
+
- 'Stackoverflow Stackexchange
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
Q: How to run 16 bit code on 32 bit Linux? I have written a small 16-bit assembly
|
| 81 |
+
program that writes some values in some memory locations.Is there a way I can
|
| 82 |
+
test it in 32-bit protected mode on Linux?
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
A: qemu, dosbox, bochs
|
| 86 |
+
|
| 87 |
+
'
|
| 88 |
+
- source_sentence: 'Stackoverflow Stackexchange
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
Q: What is a good gitignore to use with Codeblocks C++ Projects? This is what
|
| 92 |
+
I have so far:
|
| 93 |
+
|
| 94 |
+
obj/
|
| 95 |
+
|
| 96 |
+
bin/
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
Anything else?
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
A: You can use this:
|
| 103 |
+
|
| 104 |
+
*.layout
|
| 105 |
+
|
| 106 |
+
*.depend
|
| 107 |
+
|
| 108 |
+
bin/
|
| 109 |
+
|
| 110 |
+
obj/
|
| 111 |
+
|
| 112 |
+
|
| 113 |
+
See:
|
| 114 |
+
|
| 115 |
+
https://www.gitignore.io/api/codeblocks
|
| 116 |
+
|
| 117 |
+
'
|
| 118 |
+
sentences:
|
| 119 |
+
- 'Stackoverflow Stackexchange
|
| 120 |
+
|
| 121 |
+
|
| 122 |
+
Q: Listen on a network port and save data to a text file Is there some easy way
|
| 123 |
+
in linux to listen for data on network and save them to a text file?
|
| 124 |
+
|
| 125 |
+
Thank you.
|
| 126 |
+
|
| 127 |
+
|
| 128 |
+
A: Also available is TCPDump.
|
| 129 |
+
|
| 130 |
+
sudo tcpdump -i eth0 -vvvvtttAXns 1500 ''port 10000''
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
'
|
| 134 |
+
- 'Stackoverflow Stackexchange
|
| 135 |
+
|
| 136 |
+
|
| 137 |
+
Q: Get the current date and time I want to get the current date and time.
|
| 138 |
+
|
| 139 |
+
For example:
|
| 140 |
+
|
| 141 |
+
2012/11/13 06:30:38
|
| 142 |
+
|
| 143 |
+
|
| 144 |
+
What I have tried:
|
| 145 |
+
|
| 146 |
+
Dim d As System.DateTime
|
| 147 |
+
|
| 148 |
+
MsgBox(d.Year) ''Return 1
|
| 149 |
+
|
| 150 |
+
|
| 151 |
+
|
| 152 |
+
A: use DateTime.Now
|
| 153 |
+
|
| 154 |
+
try this:
|
| 155 |
+
|
| 156 |
+
DateTime.Now.ToString("yyyy/MM/dd HH:mm:ss")
|
| 157 |
+
|
| 158 |
+
|
| 159 |
+
'
|
| 160 |
+
- 'Stackoverflow Stackexchange
|
| 161 |
+
|
| 162 |
+
|
| 163 |
+
Q: Can azure CLI get a list of all resources running in a tenant? Is there a single
|
| 164 |
+
command way to get all the resources in a tenant dumped out in JSON format, either
|
| 165 |
+
in az cli or powershell?
|
| 166 |
+
|
| 167 |
+
|
| 168 |
+
A: Azure CLI
|
| 169 |
+
|
| 170 |
+
az resource list
|
| 171 |
+
|
| 172 |
+
|
| 173 |
+
Powershell
|
| 174 |
+
|
| 175 |
+
Get-AzureRmResource
|
| 176 |
+
|
| 177 |
+
|
| 178 |
+
'
|
| 179 |
+
pipeline_tag: sentence-similarity
|
| 180 |
+
library_name: sentence-transformers
|
| 181 |
+
metrics:
|
| 182 |
+
- cosine_accuracy@1
|
| 183 |
+
- cosine_accuracy@3
|
| 184 |
+
- cosine_accuracy@5
|
| 185 |
+
- cosine_accuracy@10
|
| 186 |
+
- cosine_precision@1
|
| 187 |
+
- cosine_precision@3
|
| 188 |
+
- cosine_precision@5
|
| 189 |
+
- cosine_precision@10
|
| 190 |
+
- cosine_recall@1
|
| 191 |
+
- cosine_recall@3
|
| 192 |
+
- cosine_recall@5
|
| 193 |
+
- cosine_recall@10
|
| 194 |
+
- cosine_ndcg@10
|
| 195 |
+
- cosine_mrr@10
|
| 196 |
+
- cosine_map@100
|
| 197 |
+
model-index:
|
| 198 |
+
- name: SentenceTransformer based on much1na/distil-cohere-v1-ckpt
|
| 199 |
+
results:
|
| 200 |
+
- task:
|
| 201 |
+
type: information-retrieval
|
| 202 |
+
name: Information Retrieval
|
| 203 |
+
dataset:
|
| 204 |
+
name: NanoClimateFEVER
|
| 205 |
+
type: NanoClimateFEVER
|
| 206 |
+
metrics:
|
| 207 |
+
- type: cosine_accuracy@1
|
| 208 |
+
value: 0.3
|
| 209 |
+
name: Cosine Accuracy@1
|
| 210 |
+
- type: cosine_accuracy@3
|
| 211 |
+
value: 0.48
|
| 212 |
+
name: Cosine Accuracy@3
|
| 213 |
+
- type: cosine_accuracy@5
|
| 214 |
+
value: 0.52
|
| 215 |
+
name: Cosine Accuracy@5
|
| 216 |
+
- type: cosine_accuracy@10
|
| 217 |
+
value: 0.62
|
| 218 |
+
name: Cosine Accuracy@10
|
| 219 |
+
- type: cosine_precision@1
|
| 220 |
+
value: 0.3
|
| 221 |
+
name: Cosine Precision@1
|
| 222 |
+
- type: cosine_precision@3
|
| 223 |
+
value: 0.18666666666666665
|
| 224 |
+
name: Cosine Precision@3
|
| 225 |
+
- type: cosine_precision@5
|
| 226 |
+
value: 0.124
|
| 227 |
+
name: Cosine Precision@5
|
| 228 |
+
- type: cosine_precision@10
|
| 229 |
+
value: 0.084
|
| 230 |
+
name: Cosine Precision@10
|
| 231 |
+
- type: cosine_recall@1
|
| 232 |
+
value: 0.15333333333333332
|
| 233 |
+
name: Cosine Recall@1
|
| 234 |
+
- type: cosine_recall@3
|
| 235 |
+
value: 0.23399999999999999
|
| 236 |
+
name: Cosine Recall@3
|
| 237 |
+
- type: cosine_recall@5
|
| 238 |
+
value: 0.25233333333333335
|
| 239 |
+
name: Cosine Recall@5
|
| 240 |
+
- type: cosine_recall@10
|
| 241 |
+
value: 0.32299999999999995
|
| 242 |
+
name: Cosine Recall@10
|
| 243 |
+
- type: cosine_ndcg@10
|
| 244 |
+
value: 0.29189003667470415
|
| 245 |
+
name: Cosine Ndcg@10
|
| 246 |
+
- type: cosine_mrr@10
|
| 247 |
+
value: 0.3999126984126985
|
| 248 |
+
name: Cosine Mrr@10
|
| 249 |
+
- type: cosine_map@100
|
| 250 |
+
value: 0.2516840415391831
|
| 251 |
+
name: Cosine Map@100
|
| 252 |
+
- task:
|
| 253 |
+
type: information-retrieval
|
| 254 |
+
name: Information Retrieval
|
| 255 |
+
dataset:
|
| 256 |
+
name: NanoDBPedia
|
| 257 |
+
type: NanoDBPedia
|
| 258 |
+
metrics:
|
| 259 |
+
- type: cosine_accuracy@1
|
| 260 |
+
value: 0.74
|
| 261 |
+
name: Cosine Accuracy@1
|
| 262 |
+
- type: cosine_accuracy@3
|
| 263 |
+
value: 0.84
|
| 264 |
+
name: Cosine Accuracy@3
|
| 265 |
+
- type: cosine_accuracy@5
|
| 266 |
+
value: 0.88
|
| 267 |
+
name: Cosine Accuracy@5
|
| 268 |
+
- type: cosine_accuracy@10
|
| 269 |
+
value: 0.94
|
| 270 |
+
name: Cosine Accuracy@10
|
| 271 |
+
- type: cosine_precision@1
|
| 272 |
+
value: 0.74
|
| 273 |
+
name: Cosine Precision@1
|
| 274 |
+
- type: cosine_precision@3
|
| 275 |
+
value: 0.5466666666666666
|
| 276 |
+
name: Cosine Precision@3
|
| 277 |
+
- type: cosine_precision@5
|
| 278 |
+
value: 0.48399999999999993
|
| 279 |
+
name: Cosine Precision@5
|
| 280 |
+
- type: cosine_precision@10
|
| 281 |
+
value: 0.446
|
| 282 |
+
name: Cosine Precision@10
|
| 283 |
+
- type: cosine_recall@1
|
| 284 |
+
value: 0.07789454341315716
|
| 285 |
+
name: Cosine Recall@1
|
| 286 |
+
- type: cosine_recall@3
|
| 287 |
+
value: 0.14709388513196536
|
| 288 |
+
name: Cosine Recall@3
|
| 289 |
+
- type: cosine_recall@5
|
| 290 |
+
value: 0.1870910227526472
|
| 291 |
+
name: Cosine Recall@5
|
| 292 |
+
- type: cosine_recall@10
|
| 293 |
+
value: 0.2928987864758593
|
| 294 |
+
name: Cosine Recall@10
|
| 295 |
+
- type: cosine_ndcg@10
|
| 296 |
+
value: 0.5529033661694585
|
| 297 |
+
name: Cosine Ndcg@10
|
| 298 |
+
- type: cosine_mrr@10
|
| 299 |
+
value: 0.8068888888888889
|
| 300 |
+
name: Cosine Mrr@10
|
| 301 |
+
- type: cosine_map@100
|
| 302 |
+
value: 0.3997469829295745
|
| 303 |
+
name: Cosine Map@100
|
| 304 |
+
- task:
|
| 305 |
+
type: information-retrieval
|
| 306 |
+
name: Information Retrieval
|
| 307 |
+
dataset:
|
| 308 |
+
name: NanoFEVER
|
| 309 |
+
type: NanoFEVER
|
| 310 |
+
metrics:
|
| 311 |
+
- type: cosine_accuracy@1
|
| 312 |
+
value: 0.56
|
| 313 |
+
name: Cosine Accuracy@1
|
| 314 |
+
- type: cosine_accuracy@3
|
| 315 |
+
value: 0.72
|
| 316 |
+
name: Cosine Accuracy@3
|
| 317 |
+
- type: cosine_accuracy@5
|
| 318 |
+
value: 0.82
|
| 319 |
+
name: Cosine Accuracy@5
|
| 320 |
+
- type: cosine_accuracy@10
|
| 321 |
+
value: 0.96
|
| 322 |
+
name: Cosine Accuracy@10
|
| 323 |
+
- type: cosine_precision@1
|
| 324 |
+
value: 0.56
|
| 325 |
+
name: Cosine Precision@1
|
| 326 |
+
- type: cosine_precision@3
|
| 327 |
+
value: 0.24666666666666667
|
| 328 |
+
name: Cosine Precision@3
|
| 329 |
+
- type: cosine_precision@5
|
| 330 |
+
value: 0.16799999999999998
|
| 331 |
+
name: Cosine Precision@5
|
| 332 |
+
- type: cosine_precision@10
|
| 333 |
+
value: 0.09999999999999998
|
| 334 |
+
name: Cosine Precision@10
|
| 335 |
+
- type: cosine_recall@1
|
| 336 |
+
value: 0.53
|
| 337 |
+
name: Cosine Recall@1
|
| 338 |
+
- type: cosine_recall@3
|
| 339 |
+
value: 0.6766666666666665
|
| 340 |
+
name: Cosine Recall@3
|
| 341 |
+
- type: cosine_recall@5
|
| 342 |
+
value: 0.7766666666666666
|
| 343 |
+
name: Cosine Recall@5
|
| 344 |
+
- type: cosine_recall@10
|
| 345 |
+
value: 0.9266666666666667
|
| 346 |
+
name: Cosine Recall@10
|
| 347 |
+
- type: cosine_ndcg@10
|
| 348 |
+
value: 0.7212617467191452
|
| 349 |
+
name: Cosine Ndcg@10
|
| 350 |
+
- type: cosine_mrr@10
|
| 351 |
+
value: 0.6735555555555557
|
| 352 |
+
name: Cosine Mrr@10
|
| 353 |
+
- type: cosine_map@100
|
| 354 |
+
value: 0.651959758620174
|
| 355 |
+
name: Cosine Map@100
|
| 356 |
+
- task:
|
| 357 |
+
type: information-retrieval
|
| 358 |
+
name: Information Retrieval
|
| 359 |
+
dataset:
|
| 360 |
+
name: NanoFiQA2018
|
| 361 |
+
type: NanoFiQA2018
|
| 362 |
+
metrics:
|
| 363 |
+
- type: cosine_accuracy@1
|
| 364 |
+
value: 0.34
|
| 365 |
+
name: Cosine Accuracy@1
|
| 366 |
+
- type: cosine_accuracy@3
|
| 367 |
+
value: 0.56
|
| 368 |
+
name: Cosine Accuracy@3
|
| 369 |
+
- type: cosine_accuracy@5
|
| 370 |
+
value: 0.62
|
| 371 |
+
name: Cosine Accuracy@5
|
| 372 |
+
- type: cosine_accuracy@10
|
| 373 |
+
value: 0.72
|
| 374 |
+
name: Cosine Accuracy@10
|
| 375 |
+
- type: cosine_precision@1
|
| 376 |
+
value: 0.34
|
| 377 |
+
name: Cosine Precision@1
|
| 378 |
+
- type: cosine_precision@3
|
| 379 |
+
value: 0.24
|
| 380 |
+
name: Cosine Precision@3
|
| 381 |
+
- type: cosine_precision@5
|
| 382 |
+
value: 0.184
|
| 383 |
+
name: Cosine Precision@5
|
| 384 |
+
- type: cosine_precision@10
|
| 385 |
+
value: 0.11399999999999999
|
| 386 |
+
name: Cosine Precision@10
|
| 387 |
+
- type: cosine_recall@1
|
| 388 |
+
value: 0.19374603174603172
|
| 389 |
+
name: Cosine Recall@1
|
| 390 |
+
- type: cosine_recall@3
|
| 391 |
+
value: 0.3669365079365079
|
| 392 |
+
name: Cosine Recall@3
|
| 393 |
+
- type: cosine_recall@5
|
| 394 |
+
value: 0.464015873015873
|
| 395 |
+
name: Cosine Recall@5
|
| 396 |
+
- type: cosine_recall@10
|
| 397 |
+
value: 0.5427619047619047
|
| 398 |
+
name: Cosine Recall@10
|
| 399 |
+
- type: cosine_ndcg@10
|
| 400 |
+
value: 0.4234107861413032
|
| 401 |
+
name: Cosine Ndcg@10
|
| 402 |
+
- type: cosine_mrr@10
|
| 403 |
+
value: 0.4598809523809524
|
| 404 |
+
name: Cosine Mrr@10
|
| 405 |
+
- type: cosine_map@100
|
| 406 |
+
value: 0.3572454750315232
|
| 407 |
+
name: Cosine Map@100
|
| 408 |
+
- task:
|
| 409 |
+
type: information-retrieval
|
| 410 |
+
name: Information Retrieval
|
| 411 |
+
dataset:
|
| 412 |
+
name: NanoHotpotQA
|
| 413 |
+
type: NanoHotpotQA
|
| 414 |
+
metrics:
|
| 415 |
+
- type: cosine_accuracy@1
|
| 416 |
+
value: 0.78
|
| 417 |
+
name: Cosine Accuracy@1
|
| 418 |
+
- type: cosine_accuracy@3
|
| 419 |
+
value: 0.9
|
| 420 |
+
name: Cosine Accuracy@3
|
| 421 |
+
- type: cosine_accuracy@5
|
| 422 |
+
value: 0.92
|
| 423 |
+
name: Cosine Accuracy@5
|
| 424 |
+
- type: cosine_accuracy@10
|
| 425 |
+
value: 1.0
|
| 426 |
+
name: Cosine Accuracy@10
|
| 427 |
+
- type: cosine_precision@1
|
| 428 |
+
value: 0.78
|
| 429 |
+
name: Cosine Precision@1
|
| 430 |
+
- type: cosine_precision@3
|
| 431 |
+
value: 0.43999999999999995
|
| 432 |
+
name: Cosine Precision@3
|
| 433 |
+
- type: cosine_precision@5
|
| 434 |
+
value: 0.284
|
| 435 |
+
name: Cosine Precision@5
|
| 436 |
+
- type: cosine_precision@10
|
| 437 |
+
value: 0.15999999999999998
|
| 438 |
+
name: Cosine Precision@10
|
| 439 |
+
- type: cosine_recall@1
|
| 440 |
+
value: 0.39
|
| 441 |
+
name: Cosine Recall@1
|
| 442 |
+
- type: cosine_recall@3
|
| 443 |
+
value: 0.66
|
| 444 |
+
name: Cosine Recall@3
|
| 445 |
+
- type: cosine_recall@5
|
| 446 |
+
value: 0.71
|
| 447 |
+
name: Cosine Recall@5
|
| 448 |
+
- type: cosine_recall@10
|
| 449 |
+
value: 0.8
|
| 450 |
+
name: Cosine Recall@10
|
| 451 |
+
- type: cosine_ndcg@10
|
| 452 |
+
value: 0.7354996123049614
|
| 453 |
+
name: Cosine Ndcg@10
|
| 454 |
+
- type: cosine_mrr@10
|
| 455 |
+
value: 0.8485238095238096
|
| 456 |
+
name: Cosine Mrr@10
|
| 457 |
+
- type: cosine_map@100
|
| 458 |
+
value: 0.6593936674010843
|
| 459 |
+
name: Cosine Map@100
|
| 460 |
+
- task:
|
| 461 |
+
type: information-retrieval
|
| 462 |
+
name: Information Retrieval
|
| 463 |
+
dataset:
|
| 464 |
+
name: NanoMSMARCO
|
| 465 |
+
type: NanoMSMARCO
|
| 466 |
+
metrics:
|
| 467 |
+
- type: cosine_accuracy@1
|
| 468 |
+
value: 0.44
|
| 469 |
+
name: Cosine Accuracy@1
|
| 470 |
+
- type: cosine_accuracy@3
|
| 471 |
+
value: 0.64
|
| 472 |
+
name: Cosine Accuracy@3
|
| 473 |
+
- type: cosine_accuracy@5
|
| 474 |
+
value: 0.7
|
| 475 |
+
name: Cosine Accuracy@5
|
| 476 |
+
- type: cosine_accuracy@10
|
| 477 |
+
value: 0.76
|
| 478 |
+
name: Cosine Accuracy@10
|
| 479 |
+
- type: cosine_precision@1
|
| 480 |
+
value: 0.44
|
| 481 |
+
name: Cosine Precision@1
|
| 482 |
+
- type: cosine_precision@3
|
| 483 |
+
value: 0.21333333333333332
|
| 484 |
+
name: Cosine Precision@3
|
| 485 |
+
- type: cosine_precision@5
|
| 486 |
+
value: 0.14
|
| 487 |
+
name: Cosine Precision@5
|
| 488 |
+
- type: cosine_precision@10
|
| 489 |
+
value: 0.07600000000000001
|
| 490 |
+
name: Cosine Precision@10
|
| 491 |
+
- type: cosine_recall@1
|
| 492 |
+
value: 0.44
|
| 493 |
+
name: Cosine Recall@1
|
| 494 |
+
- type: cosine_recall@3
|
| 495 |
+
value: 0.64
|
| 496 |
+
name: Cosine Recall@3
|
| 497 |
+
- type: cosine_recall@5
|
| 498 |
+
value: 0.7
|
| 499 |
+
name: Cosine Recall@5
|
| 500 |
+
- type: cosine_recall@10
|
| 501 |
+
value: 0.76
|
| 502 |
+
name: Cosine Recall@10
|
| 503 |
+
- type: cosine_ndcg@10
|
| 504 |
+
value: 0.6043814421453638
|
| 505 |
+
name: Cosine Ndcg@10
|
| 506 |
+
- type: cosine_mrr@10
|
| 507 |
+
value: 0.5544126984126984
|
| 508 |
+
name: Cosine Mrr@10
|
| 509 |
+
- type: cosine_map@100
|
| 510 |
+
value: 0.5676617874135179
|
| 511 |
+
name: Cosine Map@100
|
| 512 |
+
- task:
|
| 513 |
+
type: information-retrieval
|
| 514 |
+
name: Information Retrieval
|
| 515 |
+
dataset:
|
| 516 |
+
name: NanoNFCorpus
|
| 517 |
+
type: NanoNFCorpus
|
| 518 |
+
metrics:
|
| 519 |
+
- type: cosine_accuracy@1
|
| 520 |
+
value: 0.38
|
| 521 |
+
name: Cosine Accuracy@1
|
| 522 |
+
- type: cosine_accuracy@3
|
| 523 |
+
value: 0.52
|
| 524 |
+
name: Cosine Accuracy@3
|
| 525 |
+
- type: cosine_accuracy@5
|
| 526 |
+
value: 0.62
|
| 527 |
+
name: Cosine Accuracy@5
|
| 528 |
+
- type: cosine_accuracy@10
|
| 529 |
+
value: 0.72
|
| 530 |
+
name: Cosine Accuracy@10
|
| 531 |
+
- type: cosine_precision@1
|
| 532 |
+
value: 0.38
|
| 533 |
+
name: Cosine Precision@1
|
| 534 |
+
- type: cosine_precision@3
|
| 535 |
+
value: 0.3466666666666666
|
| 536 |
+
name: Cosine Precision@3
|
| 537 |
+
- type: cosine_precision@5
|
| 538 |
+
value: 0.336
|
| 539 |
+
name: Cosine Precision@5
|
| 540 |
+
- type: cosine_precision@10
|
| 541 |
+
value: 0.28800000000000003
|
| 542 |
+
name: Cosine Precision@10
|
| 543 |
+
- type: cosine_recall@1
|
| 544 |
+
value: 0.02361993221285506
|
| 545 |
+
name: Cosine Recall@1
|
| 546 |
+
- type: cosine_recall@3
|
| 547 |
+
value: 0.0550874334390053
|
| 548 |
+
name: Cosine Recall@3
|
| 549 |
+
- type: cosine_recall@5
|
| 550 |
+
value: 0.0994974298703705
|
| 551 |
+
name: Cosine Recall@5
|
| 552 |
+
- type: cosine_recall@10
|
| 553 |
+
value: 0.16071869880999604
|
| 554 |
+
name: Cosine Recall@10
|
| 555 |
+
- type: cosine_ndcg@10
|
| 556 |
+
value: 0.3357604511492006
|
| 557 |
+
name: Cosine Ndcg@10
|
| 558 |
+
- type: cosine_mrr@10
|
| 559 |
+
value: 0.4767698412698412
|
| 560 |
+
name: Cosine Mrr@10
|
| 561 |
+
- type: cosine_map@100
|
| 562 |
+
value: 0.14291785177024427
|
| 563 |
+
name: Cosine Map@100
|
| 564 |
+
- task:
|
| 565 |
+
type: information-retrieval
|
| 566 |
+
name: Information Retrieval
|
| 567 |
+
dataset:
|
| 568 |
+
name: NanoNQ
|
| 569 |
+
type: NanoNQ
|
| 570 |
+
metrics:
|
| 571 |
+
- type: cosine_accuracy@1
|
| 572 |
+
value: 0.56
|
| 573 |
+
name: Cosine Accuracy@1
|
| 574 |
+
- type: cosine_accuracy@3
|
| 575 |
+
value: 0.7
|
| 576 |
+
name: Cosine Accuracy@3
|
| 577 |
+
- type: cosine_accuracy@5
|
| 578 |
+
value: 0.78
|
| 579 |
+
name: Cosine Accuracy@5
|
| 580 |
+
- type: cosine_accuracy@10
|
| 581 |
+
value: 0.84
|
| 582 |
+
name: Cosine Accuracy@10
|
| 583 |
+
- type: cosine_precision@1
|
| 584 |
+
value: 0.56
|
| 585 |
+
name: Cosine Precision@1
|
| 586 |
+
- type: cosine_precision@3
|
| 587 |
+
value: 0.24
|
| 588 |
+
name: Cosine Precision@3
|
| 589 |
+
- type: cosine_precision@5
|
| 590 |
+
value: 0.16
|
| 591 |
+
name: Cosine Precision@5
|
| 592 |
+
- type: cosine_precision@10
|
| 593 |
+
value: 0.09
|
| 594 |
+
name: Cosine Precision@10
|
| 595 |
+
- type: cosine_recall@1
|
| 596 |
+
value: 0.53
|
| 597 |
+
name: Cosine Recall@1
|
| 598 |
+
- type: cosine_recall@3
|
| 599 |
+
value: 0.66
|
| 600 |
+
name: Cosine Recall@3
|
| 601 |
+
- type: cosine_recall@5
|
| 602 |
+
value: 0.73
|
| 603 |
+
name: Cosine Recall@5
|
| 604 |
+
- type: cosine_recall@10
|
| 605 |
+
value: 0.8
|
| 606 |
+
name: Cosine Recall@10
|
| 607 |
+
- type: cosine_ndcg@10
|
| 608 |
+
value: 0.6782676967719391
|
| 609 |
+
name: Cosine Ndcg@10
|
| 610 |
+
- type: cosine_mrr@10
|
| 611 |
+
value: 0.6575238095238095
|
| 612 |
+
name: Cosine Mrr@10
|
| 613 |
+
- type: cosine_map@100
|
| 614 |
+
value: 0.6356999690257737
|
| 615 |
+
name: Cosine Map@100
|
| 616 |
+
- task:
|
| 617 |
+
type: information-retrieval
|
| 618 |
+
name: Information Retrieval
|
| 619 |
+
dataset:
|
| 620 |
+
name: NanoQuoraRetrieval
|
| 621 |
+
type: NanoQuoraRetrieval
|
| 622 |
+
metrics:
|
| 623 |
+
- type: cosine_accuracy@1
|
| 624 |
+
value: 0.92
|
| 625 |
+
name: Cosine Accuracy@1
|
| 626 |
+
- type: cosine_accuracy@3
|
| 627 |
+
value: 0.98
|
| 628 |
+
name: Cosine Accuracy@3
|
| 629 |
+
- type: cosine_accuracy@5
|
| 630 |
+
value: 0.98
|
| 631 |
+
name: Cosine Accuracy@5
|
| 632 |
+
- type: cosine_accuracy@10
|
| 633 |
+
value: 1.0
|
| 634 |
+
name: Cosine Accuracy@10
|
| 635 |
+
- type: cosine_precision@1
|
| 636 |
+
value: 0.92
|
| 637 |
+
name: Cosine Precision@1
|
| 638 |
+
- type: cosine_precision@3
|
| 639 |
+
value: 0.3999999999999999
|
| 640 |
+
name: Cosine Precision@3
|
| 641 |
+
- type: cosine_precision@5
|
| 642 |
+
value: 0.24799999999999997
|
| 643 |
+
name: Cosine Precision@5
|
| 644 |
+
- type: cosine_precision@10
|
| 645 |
+
value: 0.13399999999999998
|
| 646 |
+
name: Cosine Precision@10
|
| 647 |
+
- type: cosine_recall@1
|
| 648 |
+
value: 0.8073333333333332
|
| 649 |
+
name: Cosine Recall@1
|
| 650 |
+
- type: cosine_recall@3
|
| 651 |
+
value: 0.9386666666666668
|
| 652 |
+
name: Cosine Recall@3
|
| 653 |
+
- type: cosine_recall@5
|
| 654 |
+
value: 0.9493333333333334
|
| 655 |
+
name: Cosine Recall@5
|
| 656 |
+
- type: cosine_recall@10
|
| 657 |
+
value: 0.9893333333333334
|
| 658 |
+
name: Cosine Recall@10
|
| 659 |
+
- type: cosine_ndcg@10
|
| 660 |
+
value: 0.9492763453627913
|
| 661 |
+
name: Cosine Ndcg@10
|
| 662 |
+
- type: cosine_mrr@10
|
| 663 |
+
value: 0.9533333333333333
|
| 664 |
+
name: Cosine Mrr@10
|
| 665 |
+
- type: cosine_map@100
|
| 666 |
+
value: 0.9267995189995191
|
| 667 |
+
name: Cosine Map@100
|
| 668 |
+
- task:
|
| 669 |
+
type: information-retrieval
|
| 670 |
+
name: Information Retrieval
|
| 671 |
+
dataset:
|
| 672 |
+
name: NanoSCIDOCS
|
| 673 |
+
type: NanoSCIDOCS
|
| 674 |
+
metrics:
|
| 675 |
+
- type: cosine_accuracy@1
|
| 676 |
+
value: 0.36
|
| 677 |
+
name: Cosine Accuracy@1
|
| 678 |
+
- type: cosine_accuracy@3
|
| 679 |
+
value: 0.6
|
| 680 |
+
name: Cosine Accuracy@3
|
| 681 |
+
- type: cosine_accuracy@5
|
| 682 |
+
value: 0.68
|
| 683 |
+
name: Cosine Accuracy@5
|
| 684 |
+
- type: cosine_accuracy@10
|
| 685 |
+
value: 0.8
|
| 686 |
+
name: Cosine Accuracy@10
|
| 687 |
+
- type: cosine_precision@1
|
| 688 |
+
value: 0.36
|
| 689 |
+
name: Cosine Precision@1
|
| 690 |
+
- type: cosine_precision@3
|
| 691 |
+
value: 0.3
|
| 692 |
+
name: Cosine Precision@3
|
| 693 |
+
- type: cosine_precision@5
|
| 694 |
+
value: 0.236
|
| 695 |
+
name: Cosine Precision@5
|
| 696 |
+
- type: cosine_precision@10
|
| 697 |
+
value: 0.16
|
| 698 |
+
name: Cosine Precision@10
|
| 699 |
+
- type: cosine_recall@1
|
| 700 |
+
value: 0.07566666666666669
|
| 701 |
+
name: Cosine Recall@1
|
| 702 |
+
- type: cosine_recall@3
|
| 703 |
+
value: 0.18566666666666662
|
| 704 |
+
name: Cosine Recall@3
|
| 705 |
+
- type: cosine_recall@5
|
| 706 |
+
value: 0.24366666666666664
|
| 707 |
+
name: Cosine Recall@5
|
| 708 |
+
- type: cosine_recall@10
|
| 709 |
+
value: 0.3306666666666666
|
| 710 |
+
name: Cosine Recall@10
|
| 711 |
+
- type: cosine_ndcg@10
|
| 712 |
+
value: 0.3193043286623152
|
| 713 |
+
name: Cosine Ndcg@10
|
| 714 |
+
- type: cosine_mrr@10
|
| 715 |
+
value: 0.4949999999999999
|
| 716 |
+
name: Cosine Mrr@10
|
| 717 |
+
- type: cosine_map@100
|
| 718 |
+
value: 0.25689128981497417
|
| 719 |
+
name: Cosine Map@100
|
| 720 |
+
- task:
|
| 721 |
+
type: information-retrieval
|
| 722 |
+
name: Information Retrieval
|
| 723 |
+
dataset:
|
| 724 |
+
name: NanoArguAna
|
| 725 |
+
type: NanoArguAna
|
| 726 |
+
metrics:
|
| 727 |
+
- type: cosine_accuracy@1
|
| 728 |
+
value: 0.16
|
| 729 |
+
name: Cosine Accuracy@1
|
| 730 |
+
- type: cosine_accuracy@3
|
| 731 |
+
value: 0.64
|
| 732 |
+
name: Cosine Accuracy@3
|
| 733 |
+
- type: cosine_accuracy@5
|
| 734 |
+
value: 0.7
|
| 735 |
+
name: Cosine Accuracy@5
|
| 736 |
+
- type: cosine_accuracy@10
|
| 737 |
+
value: 0.86
|
| 738 |
+
name: Cosine Accuracy@10
|
| 739 |
+
- type: cosine_precision@1
|
| 740 |
+
value: 0.16
|
| 741 |
+
name: Cosine Precision@1
|
| 742 |
+
- type: cosine_precision@3
|
| 743 |
+
value: 0.21333333333333335
|
| 744 |
+
name: Cosine Precision@3
|
| 745 |
+
- type: cosine_precision@5
|
| 746 |
+
value: 0.14
|
| 747 |
+
name: Cosine Precision@5
|
| 748 |
+
- type: cosine_precision@10
|
| 749 |
+
value: 0.08599999999999998
|
| 750 |
+
name: Cosine Precision@10
|
| 751 |
+
- type: cosine_recall@1
|
| 752 |
+
value: 0.16
|
| 753 |
+
name: Cosine Recall@1
|
| 754 |
+
- type: cosine_recall@3
|
| 755 |
+
value: 0.64
|
| 756 |
+
name: Cosine Recall@3
|
| 757 |
+
- type: cosine_recall@5
|
| 758 |
+
value: 0.7
|
| 759 |
+
name: Cosine Recall@5
|
| 760 |
+
- type: cosine_recall@10
|
| 761 |
+
value: 0.86
|
| 762 |
+
name: Cosine Recall@10
|
| 763 |
+
- type: cosine_ndcg@10
|
| 764 |
+
value: 0.5219432486598236
|
| 765 |
+
name: Cosine Ndcg@10
|
| 766 |
+
- type: cosine_mrr@10
|
| 767 |
+
value: 0.41343650793650794
|
| 768 |
+
name: Cosine Mrr@10
|
| 769 |
+
- type: cosine_map@100
|
| 770 |
+
value: 0.4212263014763014
|
| 771 |
+
name: Cosine Map@100
|
| 772 |
+
- task:
|
| 773 |
+
type: information-retrieval
|
| 774 |
+
name: Information Retrieval
|
| 775 |
+
dataset:
|
| 776 |
+
name: NanoSciFact
|
| 777 |
+
type: NanoSciFact
|
| 778 |
+
metrics:
|
| 779 |
+
- type: cosine_accuracy@1
|
| 780 |
+
value: 0.62
|
| 781 |
+
name: Cosine Accuracy@1
|
| 782 |
+
- type: cosine_accuracy@3
|
| 783 |
+
value: 0.74
|
| 784 |
+
name: Cosine Accuracy@3
|
| 785 |
+
- type: cosine_accuracy@5
|
| 786 |
+
value: 0.78
|
| 787 |
+
name: Cosine Accuracy@5
|
| 788 |
+
- type: cosine_accuracy@10
|
| 789 |
+
value: 0.84
|
| 790 |
+
name: Cosine Accuracy@10
|
| 791 |
+
- type: cosine_precision@1
|
| 792 |
+
value: 0.62
|
| 793 |
+
name: Cosine Precision@1
|
| 794 |
+
- type: cosine_precision@3
|
| 795 |
+
value: 0.26
|
| 796 |
+
name: Cosine Precision@3
|
| 797 |
+
- type: cosine_precision@5
|
| 798 |
+
value: 0.17599999999999993
|
| 799 |
+
name: Cosine Precision@5
|
| 800 |
+
- type: cosine_precision@10
|
| 801 |
+
value: 0.09399999999999999
|
| 802 |
+
name: Cosine Precision@10
|
| 803 |
+
- type: cosine_recall@1
|
| 804 |
+
value: 0.585
|
| 805 |
+
name: Cosine Recall@1
|
| 806 |
+
- type: cosine_recall@3
|
| 807 |
+
value: 0.72
|
| 808 |
+
name: Cosine Recall@3
|
| 809 |
+
- type: cosine_recall@5
|
| 810 |
+
value: 0.77
|
| 811 |
+
name: Cosine Recall@5
|
| 812 |
+
- type: cosine_recall@10
|
| 813 |
+
value: 0.83
|
| 814 |
+
name: Cosine Recall@10
|
| 815 |
+
- type: cosine_ndcg@10
|
| 816 |
+
value: 0.7216537280780712
|
| 817 |
+
name: Cosine Ndcg@10
|
| 818 |
+
- type: cosine_mrr@10
|
| 819 |
+
value: 0.6944444444444444
|
| 820 |
+
name: Cosine Mrr@10
|
| 821 |
+
- type: cosine_map@100
|
| 822 |
+
value: 0.6870715058750773
|
| 823 |
+
name: Cosine Map@100
|
| 824 |
+
- task:
|
| 825 |
+
type: information-retrieval
|
| 826 |
+
name: Information Retrieval
|
| 827 |
+
dataset:
|
| 828 |
+
name: NanoTouche2020
|
| 829 |
+
type: NanoTouche2020
|
| 830 |
+
metrics:
|
| 831 |
+
- type: cosine_accuracy@1
|
| 832 |
+
value: 0.6122448979591837
|
| 833 |
+
name: Cosine Accuracy@1
|
| 834 |
+
- type: cosine_accuracy@3
|
| 835 |
+
value: 0.8367346938775511
|
| 836 |
+
name: Cosine Accuracy@3
|
| 837 |
+
- type: cosine_accuracy@5
|
| 838 |
+
value: 0.9183673469387755
|
| 839 |
+
name: Cosine Accuracy@5
|
| 840 |
+
- type: cosine_accuracy@10
|
| 841 |
+
value: 0.9795918367346939
|
| 842 |
+
name: Cosine Accuracy@10
|
| 843 |
+
- type: cosine_precision@1
|
| 844 |
+
value: 0.6122448979591837
|
| 845 |
+
name: Cosine Precision@1
|
| 846 |
+
- type: cosine_precision@3
|
| 847 |
+
value: 0.5782312925170068
|
| 848 |
+
name: Cosine Precision@3
|
| 849 |
+
- type: cosine_precision@5
|
| 850 |
+
value: 0.5387755102040817
|
| 851 |
+
name: Cosine Precision@5
|
| 852 |
+
- type: cosine_precision@10
|
| 853 |
+
value: 0.47959183673469385
|
| 854 |
+
name: Cosine Precision@10
|
| 855 |
+
- type: cosine_recall@1
|
| 856 |
+
value: 0.04350189813068328
|
| 857 |
+
name: Cosine Recall@1
|
| 858 |
+
- type: cosine_recall@3
|
| 859 |
+
value: 0.12421061419636209
|
| 860 |
+
name: Cosine Recall@3
|
| 861 |
+
- type: cosine_recall@5
|
| 862 |
+
value: 0.18611320264650894
|
| 863 |
+
name: Cosine Recall@5
|
| 864 |
+
- type: cosine_recall@10
|
| 865 |
+
value: 0.3138456220969939
|
| 866 |
+
name: Cosine Recall@10
|
| 867 |
+
- type: cosine_ndcg@10
|
| 868 |
+
value: 0.5284984258757148
|
| 869 |
+
name: Cosine Ndcg@10
|
| 870 |
+
- type: cosine_mrr@10
|
| 871 |
+
value: 0.7362244897959183
|
| 872 |
+
name: Cosine Mrr@10
|
| 873 |
+
- type: cosine_map@100
|
| 874 |
+
value: 0.3950978450315826
|
| 875 |
+
name: Cosine Map@100
|
| 876 |
+
- task:
|
| 877 |
+
type: nano-beir
|
| 878 |
+
name: Nano BEIR
|
| 879 |
+
dataset:
|
| 880 |
+
name: NanoBEIR mean
|
| 881 |
+
type: NanoBEIR_mean
|
| 882 |
+
metrics:
|
| 883 |
+
- type: cosine_accuracy@1
|
| 884 |
+
value: 0.5209419152276296
|
| 885 |
+
name: Cosine Accuracy@1
|
| 886 |
+
- type: cosine_accuracy@3
|
| 887 |
+
value: 0.70436420722135
|
| 888 |
+
name: Cosine Accuracy@3
|
| 889 |
+
- type: cosine_accuracy@5
|
| 890 |
+
value: 0.7629513343799057
|
| 891 |
+
name: Cosine Accuracy@5
|
| 892 |
+
- type: cosine_accuracy@10
|
| 893 |
+
value: 0.8491993720565149
|
| 894 |
+
name: Cosine Accuracy@10
|
| 895 |
+
- type: cosine_precision@1
|
| 896 |
+
value: 0.5209419152276296
|
| 897 |
+
name: Cosine Precision@1
|
| 898 |
+
- type: cosine_precision@3
|
| 899 |
+
value: 0.3239665096807954
|
| 900 |
+
name: Cosine Precision@3
|
| 901 |
+
- type: cosine_precision@5
|
| 902 |
+
value: 0.24759811616954475
|
| 903 |
+
name: Cosine Precision@5
|
| 904 |
+
- type: cosine_precision@10
|
| 905 |
+
value: 0.17781475667189953
|
| 906 |
+
name: Cosine Precision@10
|
| 907 |
+
- type: cosine_recall@1
|
| 908 |
+
value: 0.3084689029873893
|
| 909 |
+
name: Cosine Recall@1
|
| 910 |
+
- type: cosine_recall@3
|
| 911 |
+
value: 0.4652560339002954
|
| 912 |
+
name: Cosine Recall@3
|
| 913 |
+
- type: cosine_recall@5
|
| 914 |
+
value: 0.520670579098877
|
| 915 |
+
name: Cosine Recall@5
|
| 916 |
+
- type: cosine_recall@10
|
| 917 |
+
value: 0.6099916676008785
|
| 918 |
+
name: Cosine Recall@10
|
| 919 |
+
- type: cosine_ndcg@10
|
| 920 |
+
value: 0.5680039395934455
|
| 921 |
+
name: Cosine Ndcg@10
|
| 922 |
+
- type: cosine_mrr@10
|
| 923 |
+
value: 0.6284543868829584
|
| 924 |
+
name: Cosine Mrr@10
|
| 925 |
+
- type: cosine_map@100
|
| 926 |
+
value: 0.48872276884065613
|
| 927 |
+
name: Cosine Map@100
|
| 928 |
+
---
|
| 929 |
+
|
| 930 |
+
# SentenceTransformer based on much1na/distil-cohere-v1-ckpt
|
| 931 |
+
|
| 932 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [much1na/distil-cohere-v1-ckpt](https://huggingface.co/much1na/distil-cohere-v1-ckpt) on the generator dataset. It maps inputs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more.
|
| 933 |
+
|
| 934 |
+
## Model Details
|
| 935 |
+
|
| 936 |
+
### Model Description
|
| 937 |
+
- **Model Type:** Sentence Transformer
|
| 938 |
+
- **Base model:** [much1na/distil-cohere-v1-ckpt](https://huggingface.co/much1na/distil-cohere-v1-ckpt) <!-- at revision 487bc2f59d62211641241d4ae071987194523811 -->
|
| 939 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 940 |
+
- **Output Dimensionality:** 1024 dimensions
|
| 941 |
+
- **Similarity Function:** Cosine Similarity
|
| 942 |
+
- **Supported Modality:** Text
|
| 943 |
+
- **Training Dataset:**
|
| 944 |
+
- generator
|
| 945 |
+
<!-- - **Language:** Unknown -->
|
| 946 |
+
<!-- - **License:** Unknown -->
|
| 947 |
+
|
| 948 |
+
### Model Sources
|
| 949 |
+
|
| 950 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 951 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
|
| 952 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 953 |
+
|
| 954 |
+
### Full Model Architecture
|
| 955 |
+
|
| 956 |
+
```
|
| 957 |
+
SentenceTransformer(
|
| 958 |
+
(0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
|
| 959 |
+
(1): Pooling({'embedding_dimension': 512, 'pooling_mode': 'mean', 'include_prompt': True})
|
| 960 |
+
(2): Dense({'in_features': 512, 'out_features': 1024, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'})
|
| 961 |
+
(3): Normalize({'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'})
|
| 962 |
+
)
|
| 963 |
+
```
|
| 964 |
+
|
| 965 |
+
## Usage
|
| 966 |
+
|
| 967 |
+
### Direct Usage (Sentence Transformers)
|
| 968 |
+
|
| 969 |
+
First install the Sentence Transformers library:
|
| 970 |
+
|
| 971 |
+
```bash
|
| 972 |
+
pip install -U sentence-transformers
|
| 973 |
+
```
|
| 974 |
+
Then you can load this model and run inference.
|
| 975 |
+
```python
|
| 976 |
+
from sentence_transformers import SentenceTransformer
|
| 977 |
+
|
| 978 |
+
# Download from the 🤗 Hub
|
| 979 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
| 980 |
+
# Run inference
|
| 981 |
+
queries = [
|
| 982 |
+
'Stackoverflow Stackexchange\n\nQ: What is a good gitignore to use with Codeblocks C++ Projects? This is what I have so far:\nobj/\nbin/\n\nAnything else?\n\nA: You can use this:\n*.layout\n*.depend\nbin/\nobj/\n\nSee:\nhttps://www.gitignore.io/api/codeblocks\n',
|
| 983 |
+
]
|
| 984 |
+
documents = [
|
| 985 |
+
"Stackoverflow Stackexchange\n\nQ: Listen on a network port and save data to a text file Is there some easy way in linux to listen for data on network and save them to a text file?\nThank you.\n\nA: Also available is TCPDump.\nsudo tcpdump -i eth0 -vvvvtttAXns 1500 'port 10000'\n\n",
|
| 986 |
+
'Stackoverflow Stackexchange\n\nQ: Get the current date and time I want to get the current date and time.\nFor example:\n2012/11/13 06:30:38\n\nWhat I have tried:\nDim d As System.DateTime\nMsgBox(d.Year) \'Return 1\n\n\nA: use DateTime.Now\ntry this:\nDateTime.Now.ToString("yyyy/MM/dd HH:mm:ss")\n\n',
|
| 987 |
+
]
|
| 988 |
+
query_embeddings = model.encode_query(queries)
|
| 989 |
+
document_embeddings = model.encode_document(documents)
|
| 990 |
+
print(query_embeddings.shape, document_embeddings.shape)
|
| 991 |
+
# [1, 1024] [2, 1024]
|
| 992 |
+
|
| 993 |
+
# Get the similarity scores for the embeddings
|
| 994 |
+
similarities = model.similarity(query_embeddings, document_embeddings)
|
| 995 |
+
print(similarities)
|
| 996 |
+
# tensor([[0.3207, 0.2160]])
|
| 997 |
+
```
|
| 998 |
+
<!--
|
| 999 |
+
### Direct Usage (Transformers)
|
| 1000 |
+
|
| 1001 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 1002 |
+
|
| 1003 |
+
</details>
|
| 1004 |
+
-->
|
| 1005 |
+
|
| 1006 |
+
<!--
|
| 1007 |
+
### Downstream Usage (Sentence Transformers)
|
| 1008 |
+
|
| 1009 |
+
You can finetune this model on your own dataset.
|
| 1010 |
+
|
| 1011 |
+
<details><summary>Click to expand</summary>
|
| 1012 |
+
|
| 1013 |
+
</details>
|
| 1014 |
+
-->
|
| 1015 |
+
|
| 1016 |
+
<!--
|
| 1017 |
+
### Out-of-Scope Use
|
| 1018 |
+
|
| 1019 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 1020 |
+
-->
|
| 1021 |
+
|
| 1022 |
+
## Evaluation
|
| 1023 |
+
|
| 1024 |
+
### Metrics
|
| 1025 |
+
|
| 1026 |
+
#### Information Retrieval
|
| 1027 |
+
|
| 1028 |
+
* Datasets: `NanoClimateFEVER`, `NanoDBPedia`, `NanoFEVER`, `NanoFiQA2018`, `NanoHotpotQA`, `NanoMSMARCO`, `NanoNFCorpus`, `NanoNQ`, `NanoQuoraRetrieval`, `NanoSCIDOCS`, `NanoArguAna`, `NanoSciFact` and `NanoTouche2020`
|
| 1029 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.sentence_transformer.evaluation.InformationRetrievalEvaluator)
|
| 1030 |
+
|
| 1031 |
+
| Metric | NanoClimateFEVER | NanoDBPedia | NanoFEVER | NanoFiQA2018 | NanoHotpotQA | NanoMSMARCO | NanoNFCorpus | NanoNQ | NanoQuoraRetrieval | NanoSCIDOCS | NanoArguAna | NanoSciFact | NanoTouche2020 |
|
| 1032 |
+
|:--------------------|:-----------------|:------------|:-----------|:-------------|:-------------|:------------|:-------------|:-----------|:-------------------|:------------|:------------|:------------|:---------------|
|
| 1033 |
+
| cosine_accuracy@1 | 0.3 | 0.74 | 0.56 | 0.34 | 0.78 | 0.44 | 0.38 | 0.56 | 0.92 | 0.36 | 0.16 | 0.62 | 0.6122 |
|
| 1034 |
+
| cosine_accuracy@3 | 0.48 | 0.84 | 0.72 | 0.56 | 0.9 | 0.64 | 0.52 | 0.7 | 0.98 | 0.6 | 0.64 | 0.74 | 0.8367 |
|
| 1035 |
+
| cosine_accuracy@5 | 0.52 | 0.88 | 0.82 | 0.62 | 0.92 | 0.7 | 0.62 | 0.78 | 0.98 | 0.68 | 0.7 | 0.78 | 0.9184 |
|
| 1036 |
+
| cosine_accuracy@10 | 0.62 | 0.94 | 0.96 | 0.72 | 1.0 | 0.76 | 0.72 | 0.84 | 1.0 | 0.8 | 0.86 | 0.84 | 0.9796 |
|
| 1037 |
+
| cosine_precision@1 | 0.3 | 0.74 | 0.56 | 0.34 | 0.78 | 0.44 | 0.38 | 0.56 | 0.92 | 0.36 | 0.16 | 0.62 | 0.6122 |
|
| 1038 |
+
| cosine_precision@3 | 0.1867 | 0.5467 | 0.2467 | 0.24 | 0.44 | 0.2133 | 0.3467 | 0.24 | 0.4 | 0.3 | 0.2133 | 0.26 | 0.5782 |
|
| 1039 |
+
| cosine_precision@5 | 0.124 | 0.484 | 0.168 | 0.184 | 0.284 | 0.14 | 0.336 | 0.16 | 0.248 | 0.236 | 0.14 | 0.176 | 0.5388 |
|
| 1040 |
+
| cosine_precision@10 | 0.084 | 0.446 | 0.1 | 0.114 | 0.16 | 0.076 | 0.288 | 0.09 | 0.134 | 0.16 | 0.086 | 0.094 | 0.4796 |
|
| 1041 |
+
| cosine_recall@1 | 0.1533 | 0.0779 | 0.53 | 0.1937 | 0.39 | 0.44 | 0.0236 | 0.53 | 0.8073 | 0.0757 | 0.16 | 0.585 | 0.0435 |
|
| 1042 |
+
| cosine_recall@3 | 0.234 | 0.1471 | 0.6767 | 0.3669 | 0.66 | 0.64 | 0.0551 | 0.66 | 0.9387 | 0.1857 | 0.64 | 0.72 | 0.1242 |
|
| 1043 |
+
| cosine_recall@5 | 0.2523 | 0.1871 | 0.7767 | 0.464 | 0.71 | 0.7 | 0.0995 | 0.73 | 0.9493 | 0.2437 | 0.7 | 0.77 | 0.1861 |
|
| 1044 |
+
| cosine_recall@10 | 0.323 | 0.2929 | 0.9267 | 0.5428 | 0.8 | 0.76 | 0.1607 | 0.8 | 0.9893 | 0.3307 | 0.86 | 0.83 | 0.3138 |
|
| 1045 |
+
| **cosine_ndcg@10** | **0.2919** | **0.5529** | **0.7213** | **0.4234** | **0.7355** | **0.6044** | **0.3358** | **0.6783** | **0.9493** | **0.3193** | **0.5219** | **0.7217** | **0.5285** |
|
| 1046 |
+
| cosine_mrr@10 | 0.3999 | 0.8069 | 0.6736 | 0.4599 | 0.8485 | 0.5544 | 0.4768 | 0.6575 | 0.9533 | 0.495 | 0.4134 | 0.6944 | 0.7362 |
|
| 1047 |
+
| cosine_map@100 | 0.2517 | 0.3997 | 0.652 | 0.3572 | 0.6594 | 0.5677 | 0.1429 | 0.6357 | 0.9268 | 0.2569 | 0.4212 | 0.6871 | 0.3951 |
|
| 1048 |
+
|
| 1049 |
+
#### Nano BEIR
|
| 1050 |
+
|
| 1051 |
+
* Dataset: `NanoBEIR_mean`
|
| 1052 |
+
* Evaluated with [<code>NanoBEIREvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.sentence_transformer.evaluation.NanoBEIREvaluator) with these parameters:
|
| 1053 |
+
```json
|
| 1054 |
+
{
|
| 1055 |
+
"dataset_names": [
|
| 1056 |
+
"climatefever",
|
| 1057 |
+
"dbpedia",
|
| 1058 |
+
"fever",
|
| 1059 |
+
"fiqa2018",
|
| 1060 |
+
"hotpotqa",
|
| 1061 |
+
"msmarco",
|
| 1062 |
+
"nfcorpus",
|
| 1063 |
+
"nq",
|
| 1064 |
+
"quoraretrieval",
|
| 1065 |
+
"scidocs",
|
| 1066 |
+
"arguana",
|
| 1067 |
+
"scifact",
|
| 1068 |
+
"touche2020"
|
| 1069 |
+
],
|
| 1070 |
+
"dataset_id": "sentence-transformers/NanoBEIR-en"
|
| 1071 |
+
}
|
| 1072 |
+
```
|
| 1073 |
+
|
| 1074 |
+
| Metric | Value |
|
| 1075 |
+
|:--------------------|:----------|
|
| 1076 |
+
| cosine_accuracy@1 | 0.5209 |
|
| 1077 |
+
| cosine_accuracy@3 | 0.7044 |
|
| 1078 |
+
| cosine_accuracy@5 | 0.763 |
|
| 1079 |
+
| cosine_accuracy@10 | 0.8492 |
|
| 1080 |
+
| cosine_precision@1 | 0.5209 |
|
| 1081 |
+
| cosine_precision@3 | 0.324 |
|
| 1082 |
+
| cosine_precision@5 | 0.2476 |
|
| 1083 |
+
| cosine_precision@10 | 0.1778 |
|
| 1084 |
+
| cosine_recall@1 | 0.3085 |
|
| 1085 |
+
| cosine_recall@3 | 0.4653 |
|
| 1086 |
+
| cosine_recall@5 | 0.5207 |
|
| 1087 |
+
| cosine_recall@10 | 0.61 |
|
| 1088 |
+
| **cosine_ndcg@10** | **0.568** |
|
| 1089 |
+
| cosine_mrr@10 | 0.6285 |
|
| 1090 |
+
| cosine_map@100 | 0.4887 |
|
| 1091 |
+
|
| 1092 |
+
<!--
|
| 1093 |
+
## Bias, Risks and Limitations
|
| 1094 |
+
|
| 1095 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 1096 |
+
-->
|
| 1097 |
+
|
| 1098 |
+
<!--
|
| 1099 |
+
### Recommendations
|
| 1100 |
+
|
| 1101 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 1102 |
+
-->
|
| 1103 |
+
|
| 1104 |
+
## Training Details
|
| 1105 |
+
|
| 1106 |
+
### Training Dataset
|
| 1107 |
+
|
| 1108 |
+
#### generator
|
| 1109 |
+
|
| 1110 |
+
* Dataset: generator
|
| 1111 |
+
* Columns: <code>sentence</code> and <code>label</code>
|
| 1112 |
+
* Loss: [<code>EmbedDistillLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#embeddistillloss) with these parameters:
|
| 1113 |
+
```json
|
| 1114 |
+
{
|
| 1115 |
+
"distance_metric": "cosine",
|
| 1116 |
+
"projection_dim": null
|
| 1117 |
+
}
|
| 1118 |
+
```
|
| 1119 |
+
|
| 1120 |
+
### Evaluation Datasets
|
| 1121 |
+
<details><summary>wiki</summary>
|
| 1122 |
+
|
| 1123 |
+
#### wiki
|
| 1124 |
+
|
| 1125 |
+
* Dataset: wiki
|
| 1126 |
+
* Size: 1,000 evaluation samples
|
| 1127 |
+
* Columns: <code>sentence</code> and <code>label</code>
|
| 1128 |
+
* Approximate statistics based on the first 100 samples:
|
| 1129 |
+
| | sentence | label |
|
| 1130 |
+
|:---------|:--------------------------------------------------------------------------------------|:--------------------------------------|
|
| 1131 |
+
| type | string | list |
|
| 1132 |
+
| modality | text | |
|
| 1133 |
+
| details | <ul><li>min: 103 tokens</li><li>mean: 319.54 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>size: 1024 elements</li></ul> |
|
| 1134 |
+
* Samples:
|
| 1135 |
+
| sentence | label |
|
| 1136 |
+
|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------|
|
| 1137 |
+
| <code>Panthera spelaea Paleobiology P. spelaea inhabited colder environments such as mammoth steppe and boreal forest. It was one of the keystone species of the mammoth steppe, being one of the main apex predators alongside the gray wolf, cave hyena and brown bear. Large amounts of bones belonging to P. spelaea were excavated in caves, where bones of cave hyena, cave bear and Paleolithic artefacts were also found. Some of these accumulations of cave lion bones have been attributed to hoarding of meat from cave lion carcasses by cave hyenas in caves occupied by the latter. It is unclear whether P. spelaea was social like the modern lion; some evidence indicates that it may have been solitary.<br>Isotopic analyses of bone collagen samples extracted from fossils indicate that cave bear cubs, reindeer and other cervids (deer) were prominent in the diet of cave lions. Later cave lions seem to have preyed foremost on reindeer, up to the brink of local extinction or extirpation of both species. Other ...</code> | <code>[-0.008819580078125, -0.02508544921875, 0.012176513671875, 0.07574462890625, -0.0217742919921875, ...]</code> |
|
| 1138 |
+
| <code>Elizabeth David As a teenager David enjoyed painting, and her mother thought her talent worth developing. In 1930 she was sent to Paris, where she studied painting privately and enrolled at the Sorbonne for a course in French civilisation which covered history, literature and architecture. She found her Sorbonne studies arduous and in many ways uninspiring, but they left her with a love of French literature and a fluency in the language that remained with her throughout her life. She lodged with a Parisian family, whose fanatical devotion to the pleasures of the table she portrayed to comic effect in her French Provincial Cooking (1960). Nevertheless, she acknowledged in retrospect that the experience had been the most valuable part of her time in Paris: "I realized in what way the family had fulfilled their task of instilling French culture into at least one of their British charges. Forgotten were the Sorbonne professors. ... What had stuck was the taste for a kind of food quite idea...</code> | <code>[0.0191650390625, -0.01065826416015625, 0.034210205078125, 0.039459228515625, -0.0008692741394042969, ...]</code> |
|
| 1139 |
+
| <code>Guinea-Bissau Wars were increasingly waged for the sole purpose of capturing slaves to sell to the Europeans in exchange for imported goods. They resembled man-hunts more than conflicts over territory or political power. The nobles and kings benefited, while the common people bore the brunt of the raiding and insecurity. If a noble was captured, they were likely to be released, as the captors, whoever they were, would generally accept a ransom in exchange for freeing them. The relationship between kings and European traders was a partnership, with the two regularly making deals on how the trade was to be conducted, defining who could be enslaved and who could not, and the prices of the slaves. Contemporary chroniclers questioned multiple kings on their part in the slave trade, and noted that they recognised the trade as evil but participated because otherwise the Europeans would not buy a ny other goods from them.<br>Beginning in the late 18th century, European countries gradually began s...</code> | <code>[0.0003838539123535156, -0.027008056640625, 0.032684326171875, 0.036956787109375, -0.039581298828125, ...]</code> |
|
| 1140 |
+
* Loss: [<code>EmbedDistillLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#embeddistillloss) with these parameters:
|
| 1141 |
+
```json
|
| 1142 |
+
{
|
| 1143 |
+
"distance_metric": "cosine",
|
| 1144 |
+
"projection_dim": null
|
| 1145 |
+
}
|
| 1146 |
+
```
|
| 1147 |
+
</details>
|
| 1148 |
+
<details><summary>stackexchange</summary>
|
| 1149 |
+
|
| 1150 |
+
#### stackexchange
|
| 1151 |
+
|
| 1152 |
+
* Dataset: stackexchange
|
| 1153 |
+
* Size: 1,000 evaluation samples
|
| 1154 |
+
* Columns: <code>sentence</code> and <code>label</code>
|
| 1155 |
+
* Approximate statistics based on the first 100 samples:
|
| 1156 |
+
| | sentence | label |
|
| 1157 |
+
|:---------|:-------------------------------------------------------------------------------------|:--------------------------------------|
|
| 1158 |
+
| type | string | list |
|
| 1159 |
+
| modality | text | |
|
| 1160 |
+
| details | <ul><li>min: 72 tokens</li><li>mean: 178.89 tokens</li><li>max: 443 tokens</li></ul> | <ul><li>size: 1024 elements</li></ul> |
|
| 1161 |
+
* Samples:
|
| 1162 |
+
| sentence | label |
|
| 1163 |
+
|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------|
|
| 1164 |
+
| <code>Apple Stackexchange<br><br>Q: Why does my MacBook Pro take so long to go to sleep? My MacBook Pro takes an awful long time to go to sleep when I close the lid. Considering that I generally want to close the lid and then carry it somewhere, I want it to be fully asleep so I don't have any hard drive issues. Is there anything I can do to speed up the process?<br><br>A: I recommend a nifty little utility called SmartSleep that allows you to control when the saving of your RAM contents to disk for the Safe Sleep / Hibernate feature Mac OS X has.<br>Alternatively you can disable Safe Sleep altogether by running: sudo pmset -a hibernatemode 0. To change it back to the defaults, change the value to 3.<br>0 - Old style - just goes to sleep.<br>1 - Only Hibernate<br>3 - Default - goes to sleep but writes RAM contents to disk just in case.<br>5 - Only Hibernate mode but if you use secure virtual memory.<br>7 - The Default but if you use secure virtual memory.<br><br></code> | <code>[-0.06976318359375, -0.0247039794921875, -0.0095367431640625, 0.09149169921875, -0.053619384765625, ...]</code> |
|
| 1165 |
+
| <code>Apple Stackexchange<br><br>Q: iPhone backlight blinks on then goes out. What are my options? This morning I woke up to find my iPhone dark. If I pressed the home button to turn on the screen, the backlight would flash on briefly and then die. I've turned it on and off, done a hard reboot (home+lock), and I'm in the process of trying a restore.<br>Has anyone ever seen a similar issue?<br>The phone was purchased last June with a contract from ATT from an Apple store. If I take the phone in, will they fix it or replace it?<br>What should I do next?<br><br>A: You should take your phone in. They will fix it if they can and it's cheaper for them than giving you a new.<br>If you try to fix it yourself they can put the blame on you, so don't touch the hardware. <br></code> | <code>[-0.037384033203125, 0.020355224609375, 0.0137786865234375, 0.056610107421875, -0.0280609130859375, ...]</code> |
|
| 1166 |
+
| <code>Apple Stackexchange<br><br>Q: Can I use tethering to let an iPad use an iPhone's 3G? Given an iPad that doesn't have 3G but only wifi, can I make this use the 3G connection of an iPhone 4? <br>Does this require a cable between the devices, or does it work over (bluetooth\|wifi?) ?<br><br>A: I don't believe you can do this with the stock phone, however if you decide to jailbreakyour iPhone, you could use an application like MyWi to share your iPhone's 3G connection over WiFi<br></code> | <code>[-0.01351165771484375, -0.010284423828125, -0.0264892578125, 0.046356201171875, -0.03228759765625, ...]</code> |
|
| 1167 |
+
* Loss: [<code>EmbedDistillLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#embeddistillloss) with these parameters:
|
| 1168 |
+
```json
|
| 1169 |
+
{
|
| 1170 |
+
"distance_metric": "cosine",
|
| 1171 |
+
"projection_dim": null
|
| 1172 |
+
}
|
| 1173 |
+
```
|
| 1174 |
+
</details>
|
| 1175 |
+
<details><summary>msmarco_docs</summary>
|
| 1176 |
+
|
| 1177 |
+
#### msmarco_docs
|
| 1178 |
+
|
| 1179 |
+
* Dataset: msmarco_docs
|
| 1180 |
+
* Size: 1,000 evaluation samples
|
| 1181 |
+
* Columns: <code>sentence</code> and <code>label</code>
|
| 1182 |
+
* Approximate statistics based on the first 100 samples:
|
| 1183 |
+
| | sentence | label |
|
| 1184 |
+
|:---------|:------------------------------------------------------------------------------------|:--------------------------------------|
|
| 1185 |
+
| type | string | list |
|
| 1186 |
+
| modality | text | |
|
| 1187 |
+
| details | <ul><li>min: 23 tokens</li><li>mean: 77.07 tokens</li><li>max: 227 tokens</li></ul> | <ul><li>size: 1024 elements</li></ul> |
|
| 1188 |
+
* Samples:
|
| 1189 |
+
| sentence | label |
|
| 1190 |
+
|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------|
|
| 1191 |
+
| <code>There are 25 fountains. The Stanford campus also encompasses the 70-acre, 140-retail-store Stanford Shopping Center, built in 1955, and the 700-acre, 150-company Stanford Research Park, created in 1951.</code> | <code>[-0.0478515625, 0.0002257823944091797, -0.08514404296875, -0.0233001708984375, -0.0210418701171875, ...]</code> |
|
| 1192 |
+
| <code>First, take the probiotic on an empty stomach. When the stomach is empty, it is not making much acid. You can open a capsule and mix it with a small amount of water. The stomach will empty out liquid in 15-20 minutes, but will keep food in it for 60-90 minutes.</code> | <code>[-0.033294677734375, -0.005718231201171875, -0.0265960693359375, 0.0204925537109375, -0.025390625, ...]</code> |
|
| 1193 |
+
| <code>Most of the magnesium in the body is found in the bones and inside the cells. Only a tiny amount of magnesium is normally present in the blood. Tests for other electrolytes, such as calcium, potassium, sodium, and phosphorus, may be done along with a test for magnesium.</code> | <code>[0.00592041015625, -0.0158843994140625, -0.0017023086547851562, -0.004730224609375, -0.0122222900390625, ...]</code> |
|
| 1194 |
+
* Loss: [<code>EmbedDistillLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#embeddistillloss) with these parameters:
|
| 1195 |
+
```json
|
| 1196 |
+
{
|
| 1197 |
+
"distance_metric": "cosine",
|
| 1198 |
+
"projection_dim": null
|
| 1199 |
+
}
|
| 1200 |
+
```
|
| 1201 |
+
</details>
|
| 1202 |
+
<details><summary>msmarco_queries</summary>
|
| 1203 |
+
|
| 1204 |
+
#### msmarco_queries
|
| 1205 |
+
|
| 1206 |
+
* Dataset: msmarco_queries
|
| 1207 |
+
* Size: 1,000 evaluation samples
|
| 1208 |
+
* Columns: <code>sentence</code> and <code>label</code>
|
| 1209 |
+
* Approximate statistics based on the first 100 samples:
|
| 1210 |
+
| | sentence | label |
|
| 1211 |
+
|:---------|:---------------------------------------------------------------------------------|:--------------------------------------|
|
| 1212 |
+
| type | string | list |
|
| 1213 |
+
| modality | text | |
|
| 1214 |
+
| details | <ul><li>min: 4 tokens</li><li>mean: 8.91 tokens</li><li>max: 21 tokens</li></ul> | <ul><li>size: 1024 elements</li></ul> |
|
| 1215 |
+
* Samples:
|
| 1216 |
+
| sentence | label |
|
| 1217 |
+
|:-------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------|
|
| 1218 |
+
| <code>how much per month is a lambo</code> | <code>[-0.0255889892578125, 0.018035888671875, -0.047149658203125, -0.02044677734375, 0.01209259033203125, ...]</code> |
|
| 1219 |
+
| <code>what is basic price of lincoln mkz model?</code> | <code>[-0.05865478515625, -0.0253448486328125, -0.01363372802734375, 0.037811279296875, -0.0633544921875, ...]</code> |
|
| 1220 |
+
| <code>wendco of new hampshire, llc</code> | <code>[-0.01483917236328125, -0.047821044921875, -0.0298309326171875, -0.0416259765625, -0.04754638671875, ...]</code> |
|
| 1221 |
+
* Loss: [<code>EmbedDistillLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#embeddistillloss) with these parameters:
|
| 1222 |
+
```json
|
| 1223 |
+
{
|
| 1224 |
+
"distance_metric": "cosine",
|
| 1225 |
+
"projection_dim": null
|
| 1226 |
+
}
|
| 1227 |
+
```
|
| 1228 |
+
</details>
|
| 1229 |
+
<details><summary>sphere</summary>
|
| 1230 |
+
|
| 1231 |
+
#### sphere
|
| 1232 |
+
|
| 1233 |
+
* Dataset: sphere
|
| 1234 |
+
* Size: 1,000 evaluation samples
|
| 1235 |
+
* Columns: <code>sentence</code> and <code>label</code>
|
| 1236 |
+
* Approximate statistics based on the first 100 samples:
|
| 1237 |
+
| | sentence | label |
|
| 1238 |
+
|:---------|:-------------------------------------------------------------------------------------|:--------------------------------------|
|
| 1239 |
+
| type | string | list |
|
| 1240 |
+
| modality | text | |
|
| 1241 |
+
| details | <ul><li>min: 44 tokens</li><li>mean: 140.06 tokens</li><li>max: 321 tokens</li></ul> | <ul><li>size: 1024 elements</li></ul> |
|
| 1242 |
+
* Samples:
|
| 1243 |
+
| sentence | label |
|
| 1244 |
+
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------|
|
| 1245 |
+
| <code>Ed Schultz \| Project Gutenberg Self-Publishing - eBooks \| Read eBooks online political commentator and a former sports broadcaster. He was the host of The Ed Show, a weekday news talk program on MSNBC, and The Ed Schultz Show, a talk radio show, nationally syndicated by Dial Global.[2] The radio show ended on May 23, 2014, and was replaced by a one-hour podcast.[3] Broadcasting career 2 Sportscasting 2.1 Talk radio 2.2 Television show 2.3 Ed Shultz News and Commentary 3 Schultz was born in American players of Canadian football American talk radio hosts Canadian football quarterbacks Minnesota State University Moorhead alumni North Dakota Democrats People from Detroit Lakes, Minnesota People from Norfolk,</code> | <code>[0.030853271484375, -0.039520263671875, 0.0535888671875, -0.0031871795654296875, -0.0404052734375, ...]</code> |
|
| 1246 |
+
| <code>Tattoo Criminals — Elie Wiesel Should Be Investigated for Holocaust Fraud \| National Vanguard Jew, and Jews are never investigated for anything in Germany, let alone found guilty of something. Have you ever heard of it? I did an internet search and came up with nothing. State prosecutors had demanded that the accused [Zech] be sentenced to 10 months in jail without parole because, according to DW, he seemed to be “a politically motivated criminal, who had trampled on the core values of the German constitution.” What are the “core values” of the German constitution? Consulting the German Basic Law (constitutional law), I come up with a few: Art. 3: No person shall be</code> | <code>[-0.005931854248046875, -0.01629638671875, 0.036712646484375, 0.07537841796875, -0.033294677734375, ...]</code> |
|
| 1247 |
+
| <code>J.D. v. Atlanta Public Schools: A Lesser Spirit Would Have Been Crushed Long Ago" by Pamela Wright & Peter Wright the first time since 1998 . . . The school psychologist reported that J.D. was performing at the 2nd or 3rd grade level despite being in 9th grade . . . significant variations of his test scores showed that the I.Q. score may not be an accurate reflection of J.D.'s true ability." "A different school psychologist performed an additional psychological evaluation on J.D.. . . The July 2003 evaluation confirmed that J.D. was not MID but had a specific learning disability. The tests showed that J.D. had a full scale I.Q. of 82, which was in the low average range</code> | <code>[-0.0009756088256835938, -0.0179443359375, 0.0031375885009765625, 0.041839599609375, -0.034820556640625, ...]</code> |
|
| 1248 |
+
* Loss: [<code>EmbedDistillLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#embeddistillloss) with these parameters:
|
| 1249 |
+
```json
|
| 1250 |
+
{
|
| 1251 |
+
"distance_metric": "cosine",
|
| 1252 |
+
"projection_dim": null
|
| 1253 |
+
}
|
| 1254 |
+
```
|
| 1255 |
+
</details>
|
| 1256 |
+
|
| 1257 |
+
### Training Hyperparameters
|
| 1258 |
+
#### Non-Default Hyperparameters
|
| 1259 |
+
|
| 1260 |
+
- `per_device_train_batch_size`: 64
|
| 1261 |
+
- `max_steps`: 452659
|
| 1262 |
+
- `learning_rate`: 3e-05
|
| 1263 |
+
- `lr_scheduler_type`: cosine_with_min_lr
|
| 1264 |
+
- `lr_scheduler_kwargs`: {'min_lr_rate': 0.1}
|
| 1265 |
+
- `warmup_steps`: 500
|
| 1266 |
+
- `gradient_accumulation_steps`: 2
|
| 1267 |
+
- `fp16`: True
|
| 1268 |
+
- `per_device_eval_batch_size`: 32
|
| 1269 |
+
- `ignore_data_skip`: True
|
| 1270 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': False, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 1271 |
+
- `ddp_find_unused_parameters`: True
|
| 1272 |
+
|
| 1273 |
+
#### All Hyperparameters
|
| 1274 |
+
<details><summary>Click to expand</summary>
|
| 1275 |
+
|
| 1276 |
+
- `per_device_train_batch_size`: 64
|
| 1277 |
+
- `num_train_epochs`: 3.0
|
| 1278 |
+
- `max_steps`: 452659
|
| 1279 |
+
- `learning_rate`: 3e-05
|
| 1280 |
+
- `lr_scheduler_type`: cosine_with_min_lr
|
| 1281 |
+
- `lr_scheduler_kwargs`: {'min_lr_rate': 0.1}
|
| 1282 |
+
- `warmup_steps`: 500
|
| 1283 |
+
- `optim`: adamw_torch_fused
|
| 1284 |
+
- `optim_args`: None
|
| 1285 |
+
- `weight_decay`: 0.0
|
| 1286 |
+
- `adam_beta1`: 0.9
|
| 1287 |
+
- `adam_beta2`: 0.999
|
| 1288 |
+
- `adam_epsilon`: 1e-08
|
| 1289 |
+
- `optim_target_modules`: None
|
| 1290 |
+
- `gradient_accumulation_steps`: 2
|
| 1291 |
+
- `average_tokens_across_devices`: True
|
| 1292 |
+
- `max_grad_norm`: 1.0
|
| 1293 |
+
- `label_smoothing_factor`: 0.0
|
| 1294 |
+
- `bf16`: False
|
| 1295 |
+
- `fp16`: True
|
| 1296 |
+
- `bf16_full_eval`: False
|
| 1297 |
+
- `fp16_full_eval`: False
|
| 1298 |
+
- `tf32`: None
|
| 1299 |
+
- `gradient_checkpointing`: False
|
| 1300 |
+
- `gradient_checkpointing_kwargs`: None
|
| 1301 |
+
- `torch_compile`: False
|
| 1302 |
+
- `torch_compile_backend`: None
|
| 1303 |
+
- `torch_compile_mode`: None
|
| 1304 |
+
- `use_liger_kernel`: False
|
| 1305 |
+
- `liger_kernel_config`: None
|
| 1306 |
+
- `use_cache`: False
|
| 1307 |
+
- `neftune_noise_alpha`: None
|
| 1308 |
+
- `torch_empty_cache_steps`: None
|
| 1309 |
+
- `auto_find_batch_size`: False
|
| 1310 |
+
- `log_on_each_node`: True
|
| 1311 |
+
- `logging_nan_inf_filter`: True
|
| 1312 |
+
- `include_num_input_tokens_seen`: no
|
| 1313 |
+
- `log_level`: passive
|
| 1314 |
+
- `log_level_replica`: warning
|
| 1315 |
+
- `disable_tqdm`: False
|
| 1316 |
+
- `project`: huggingface
|
| 1317 |
+
- `trackio_space_id`: None
|
| 1318 |
+
- `trackio_bucket_id`: None
|
| 1319 |
+
- `trackio_static_space_id`: None
|
| 1320 |
+
- `per_device_eval_batch_size`: 32
|
| 1321 |
+
- `prediction_loss_only`: True
|
| 1322 |
+
- `eval_on_start`: False
|
| 1323 |
+
- `eval_do_concat_batches`: True
|
| 1324 |
+
- `eval_use_gather_object`: False
|
| 1325 |
+
- `eval_accumulation_steps`: None
|
| 1326 |
+
- `include_for_metrics`: []
|
| 1327 |
+
- `batch_eval_metrics`: False
|
| 1328 |
+
- `save_only_model`: False
|
| 1329 |
+
- `save_on_each_node`: False
|
| 1330 |
+
- `enable_jit_checkpoint`: False
|
| 1331 |
+
- `push_to_hub`: False
|
| 1332 |
+
- `hub_private_repo`: None
|
| 1333 |
+
- `hub_model_id`: None
|
| 1334 |
+
- `hub_strategy`: every_save
|
| 1335 |
+
- `hub_always_push`: False
|
| 1336 |
+
- `hub_revision`: None
|
| 1337 |
+
- `load_best_model_at_end`: False
|
| 1338 |
+
- `ignore_data_skip`: True
|
| 1339 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 1340 |
+
- `full_determinism`: False
|
| 1341 |
+
- `seed`: 42
|
| 1342 |
+
- `data_seed`: None
|
| 1343 |
+
- `use_cpu`: False
|
| 1344 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': False, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 1345 |
+
- `parallelism_config`: None
|
| 1346 |
+
- `dataloader_drop_last`: False
|
| 1347 |
+
- `dataloader_num_workers`: 0
|
| 1348 |
+
- `dataloader_pin_memory`: True
|
| 1349 |
+
- `dataloader_persistent_workers`: False
|
| 1350 |
+
- `dataloader_prefetch_factor`: None
|
| 1351 |
+
- `dataloader_multiprocessing_context`: None
|
| 1352 |
+
- `dataloader_in_order`: True
|
| 1353 |
+
- `remove_unused_columns`: True
|
| 1354 |
+
- `label_names`: None
|
| 1355 |
+
- `train_sampling_strategy`: random
|
| 1356 |
+
- `length_column_name`: length
|
| 1357 |
+
- `ddp_find_unused_parameters`: True
|
| 1358 |
+
- `ddp_bucket_cap_mb`: None
|
| 1359 |
+
- `ddp_broadcast_buffers`: False
|
| 1360 |
+
- `ddp_static_graph`: None
|
| 1361 |
+
- `ddp_backend`: None
|
| 1362 |
+
- `ddp_timeout`: 1800
|
| 1363 |
+
- `fsdp`: None
|
| 1364 |
+
- `fsdp_config`: None
|
| 1365 |
+
- `deepspeed`: None
|
| 1366 |
+
- `debug`: []
|
| 1367 |
+
- `skip_memory_metrics`: True
|
| 1368 |
+
- `do_predict`: False
|
| 1369 |
+
- `resume_from_checkpoint`: None
|
| 1370 |
+
- `local_rank`: -1
|
| 1371 |
+
- `prompts`: None
|
| 1372 |
+
- `batch_sampler`: batch_sampler
|
| 1373 |
+
- `multi_dataset_batch_sampler`: proportional
|
| 1374 |
+
- `router_mapping`: {}
|
| 1375 |
+
- `learning_rate_mapping`: {}
|
| 1376 |
+
- `warmup_ratio`: None
|
| 1377 |
+
|
| 1378 |
+
</details>
|
| 1379 |
+
|
| 1380 |
+
### Training Logs
|
| 1381 |
+
|
| 1382 |
+
|
| 1383 |
+
### Training Time
|
| 1384 |
+
- **Training**: 2.7 hours
|
| 1385 |
+
|
| 1386 |
+
### Framework Versions
|
| 1387 |
+
- Python: 3.13.15
|
| 1388 |
+
- Sentence Transformers: 6.2.0
|
| 1389 |
+
- Transformers: 5.20.1
|
| 1390 |
+
- PyTorch: 2.11.0+cu130
|
| 1391 |
+
- Accelerate: 1.15.0
|
| 1392 |
+
- Datasets: 4.8.5
|
| 1393 |
+
- Tokenizers: 0.23.3
|
| 1394 |
+
|
| 1395 |
+
## Additional Resources
|
| 1396 |
+
|
| 1397 |
+
- [Training and Finetuning Embedding Models with Sentence Transformers](https://huggingface.co/blog/train-sentence-transformers): the end-to-end guide for training or finetuning Sentence Transformer models.
|
| 1398 |
+
- [Introduction to Matryoshka Embedding Models](https://huggingface.co/blog/matryoshka): variable-size embeddings that can be truncated with minimal quality loss.
|
| 1399 |
+
- [Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval](https://huggingface.co/blog/embedding-quantization): post-training compression of embedding vectors.
|
| 1400 |
+
- [Multimodal Embedding & Reranker Models with Sentence Transformers](https://huggingface.co/blog/multimodal-sentence-transformers): use text, image, audio, and video models through the same API.
|
| 1401 |
+
- [Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers](https://huggingface.co/blog/train-multimodal-sentence-transformers): train multimodal embedding models, with a Visual Document Retrieval walkthrough.
|
| 1402 |
+
|
| 1403 |
+
## Citation
|
| 1404 |
+
|
| 1405 |
+
### BibTeX
|
| 1406 |
+
|
| 1407 |
+
#### Sentence Transformers
|
| 1408 |
+
```bibtex
|
| 1409 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 1410 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 1411 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 1412 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 1413 |
+
month = "11",
|
| 1414 |
+
year = "2019",
|
| 1415 |
+
publisher = "Association for Computational Linguistics",
|
| 1416 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 1417 |
+
}
|
| 1418 |
+
```
|
| 1419 |
+
|
| 1420 |
+
#### EmbedDistillLoss
|
| 1421 |
+
```bibtex
|
| 1422 |
+
@article{kim2023embeddistill,
|
| 1423 |
+
title={EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval},
|
| 1424 |
+
author={Kim, Seungyeon and Rawat, Ankit Singh and Zaheer, Manzil and Jayasumana, Sadeep and Sadhanala, Veeranjaneyulu and Jitkrittum, Wittawat and Menon, Aditya Krishna and Fergus, Rob and Kumar, Sanjiv},
|
| 1425 |
+
year={2023},
|
| 1426 |
+
eprint={2301.12005},
|
| 1427 |
+
archivePrefix={arXiv},
|
| 1428 |
+
primaryClass={cs.IR}
|
| 1429 |
+
}
|
| 1430 |
+
```
|
| 1431 |
+
|
| 1432 |
+
<!--
|
| 1433 |
+
## Glossary
|
| 1434 |
+
|
| 1435 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 1436 |
+
-->
|
| 1437 |
+
|
| 1438 |
+
<!--
|
| 1439 |
+
## Model Card Authors
|
| 1440 |
+
|
| 1441 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 1442 |
+
-->
|
| 1443 |
+
|
| 1444 |
+
<!--
|
| 1445 |
+
## Model Card Contact
|
| 1446 |
+
|
| 1447 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 1448 |
+
-->
|
checkpoint-368000/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": null,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 512,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 2048,
|
| 16 |
+
"is_decoder": false,
|
| 17 |
+
"layer_norm_eps": 1e-12,
|
| 18 |
+
"max_position_embeddings": 512,
|
| 19 |
+
"model_type": "bert",
|
| 20 |
+
"num_attention_heads": 8,
|
| 21 |
+
"num_hidden_layers": 6,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"tie_word_embeddings": true,
|
| 24 |
+
"transformers_version": "5.20.1",
|
| 25 |
+
"type_vocab_size": 2,
|
| 26 |
+
"use_cache": false,
|
| 27 |
+
"vocab_size": 30522
|
| 28 |
+
}
|
checkpoint-368000/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"pytorch": "2.11.0+cu130",
|
| 4 |
+
"sentence_transformers": "6.2.0",
|
| 5 |
+
"transformers": "5.20.1"
|
| 6 |
+
},
|
| 7 |
+
"default_prompt_name": null,
|
| 8 |
+
"model_type": "SentenceTransformer",
|
| 9 |
+
"prompts": {
|
| 10 |
+
"document": "",
|
| 11 |
+
"query": ""
|
| 12 |
+
},
|
| 13 |
+
"similarity_fn_name": "cosine"
|
| 14 |
+
}
|
checkpoint-368000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:672470c36dfdbb766d333ee39291ae96837d355a09987658cc9e7e22c614df01
|
| 3 |
+
size 140285096
|
checkpoint-368000/modules.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.base.modules.transformer.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Dense",
|
| 18 |
+
"type": "sentence_transformers.base.modules.dense.Dense"
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"idx": 3,
|
| 22 |
+
"name": "3",
|
| 23 |
+
"path": "3_Normalize",
|
| 24 |
+
"type": "sentence_transformers.base.modules.normalize.Normalize"
|
| 25 |
+
}
|
| 26 |
+
]
|
checkpoint-368000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:661547e3fb2f188b4998bbd3cf6723ab131ed32420be316f80809751628731b3
|
| 3 |
+
size 282727883
|
checkpoint-368000/resume_check.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"plan_sha256": "8e27a3ab0e919c63ea2020b870b6d51a0b7e8947e8ecf234ba8164a11e60e8ff", "batches_per_step": 2}
|
checkpoint-368000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67c49a3e00cf605c2fe20d295881b44c67e1b97eab96f03fd4a069a36ea5a0c8
|
| 3 |
+
size 14645
|
checkpoint-368000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fa4a31c25601f32ae2765d0e837c884e153f35bd7833edc49aef49f9446c06d
|
| 3 |
+
size 1383
|
checkpoint-368000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d966a1d62443dd37c698b71455607992b1d4dd2acad3aab2bdc3de93d3c5aff4
|
| 3 |
+
size 1465
|
checkpoint-368000/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"transformer_task": "feature-extraction",
|
| 3 |
+
"modality_config": {
|
| 4 |
+
"text": {
|
| 5 |
+
"method": "forward",
|
| 6 |
+
"method_output_name": "last_hidden_state"
|
| 7 |
+
}
|
| 8 |
+
},
|
| 9 |
+
"module_output_name": "token_embeddings"
|
| 10 |
+
}
|
checkpoint-368000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-368000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"max_length": 512,
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"pad_to_multiple_of": null,
|
| 11 |
+
"pad_token": "[PAD]",
|
| 12 |
+
"pad_token_type_id": 0,
|
| 13 |
+
"padding_side": "right",
|
| 14 |
+
"sep_token": "[SEP]",
|
| 15 |
+
"stride": 0,
|
| 16 |
+
"strip_accents": null,
|
| 17 |
+
"tokenize_chinese_chars": true,
|
| 18 |
+
"tokenizer_class": "BertTokenizer",
|
| 19 |
+
"truncation_side": "right",
|
| 20 |
+
"truncation_strategy": "longest_first",
|
| 21 |
+
"unk_token": "[UNK]"
|
| 22 |
+
}
|
checkpoint-368000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-368000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e3b4a8172882851e46d1688ac8c7d6a88036a57aef91b7f79204654be4a616d
|
| 3 |
+
size 5585
|