Upload 10 files

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "word_embedding_dimension": 1024,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": false,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": true,
+  "pooling_mode_lasttoken": false
+}

README.md

@@ -0,0 +1,86 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+<!--- Describe your model here -->
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 8807 with parameters:
+```
+{'batch_size': 64}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MNRLGradCache` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 1,
+    "evaluation_steps": 880,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
+    "optimizer_params": {
+        "lr": 0.00032
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 881,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: BloomModel 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': True, 'pooling_mode_lasttoken': False})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/content/drive/MyDrive/Colab Notebooks/training_nli_v2_bigscience-bloom-560m-2023-01-31_22-56-28",
+  "_name_or_path": "bigscience/bloom-560m",
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
     "BloomModel"

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.1.0",
+    "transformers": "4.26.0",
+    "pytorch": "1.13.1+cu116"
+  }
+}

eval/similarity_evaluation_sts-dev_results.csv

@@ -0,0 +1,12 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,880,0.7730739295350652,0.7715551652245848,0.7624365605656847,0.7651878832560441,0.7738056780000323,0.774765962811202,0.5945028356336506,0.6492590809354595
+0,1760,0.8097610198466907,0.8095535472857835,0.7779407251297351,0.7821391678764665,0.7852814025292081,0.7886208940685075,0.6599095249806181,0.7049593008199263
+0,2640,0.8164356057125646,0.8177035938282402,0.7881232506320947,0.7931402875681008,0.7909464094977913,0.7962929294234878,0.6667516754297772,0.6945011601599906
+0,3520,0.8205566117832566,0.8225628071417286,0.7885632899300942,0.7940019760690814,0.7922869076151767,0.7973139071773592,0.68123805521984,0.7126297224766549
+0,4400,0.8246633613832021,0.8264392528739577,0.7948662818700284,0.8014143726369413,0.7973234805681629,0.8036905183338244,0.6811352124044009,0.7124567152399768
+0,5280,0.8278716311461626,0.8303647324478112,0.7944490876909815,0.8006687190981095,0.7971389647391712,0.8036715165413686,0.6934613903591799,0.7132242068721515
+0,6160,0.8276340537967477,0.8316613080745355,0.7977532663102133,0.8050608484597804,0.7990159334028079,0.8066362694744206,0.6932521481661752,0.7126691904753873
+0,7040,0.8263521795828297,0.8311953006359153,0.7964605233737377,0.8049510761421301,0.7966868931245471,0.8057105054911681,0.6920102887738941,0.7127765108340522
+0,7920,0.8295055078059729,0.8335673218437176,0.7996090528343557,0.8082567154311249,0.7996295598380291,0.8086261196003169,0.6913420227276409,0.7132463385600031
+0,8800,0.829875943370156,0.8334915869160747,0.7966128866622307,0.8056167830066436,0.7964793849514137,0.8059608544181625,0.6961949575851428,0.7154576176641358
+0,-1,0.8298786185501829,0.8334962541790778,0.7966138355982828,0.8056186760728082,0.7964805974373733,0.80596287933059,0.6962014252435245,0.7154768650083625

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 75,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:796518d81847a3370a556a1c4bc940286069aec6dbbc8cb61deb5f696dac82f7
+size 14500694

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "bigscience/bloom-560m",
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}