Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+training_progress.png filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,9 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false
+}

README.md

@@ -0,0 +1,43 @@
+---
+language: multilingual
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- multilingual
+- nutrition
+- retrieval
+base_model: intfloat/multilingual-e5-base
+---
+
+# Multilingual E5 Nutrition Fine-tuned
+
+This model is a fine-tuned version of `intfloat/multilingual-e5-base` specifically for nutrition domain retrieval.
+
+## Model Details
+
+- Base Model: intfloat/multilingual-e5-base
+- Fine-tuned on: 5228 nutrition samples
+- Best Validation Loss: 0.1619
+- Architecture: Identical to original multilingual-e5-base
+
+## Usage
+
+Use exactly like the original multilingual-e5-base:
+
+|||python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer('linhha2705/multilingual-e5-simple')
+
+# Encode queries and passages with prefixes
+query = "query: What is healthy food?"
+passage = "passage: Healthy food includes fruits and vegetables."
+
+query_embedding = model.encode(query)
+passage_embedding = model.encode(passage)
+|||
+
+## Performance
+
+Improved retrieval accuracy for nutrition domain while maintaining full compatibility with multilingual-e5-base.

best_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b4d149a5f5bfa8e7293320a3fbfabe29f68606044e63980a506bf88a9c6a0fb
+size 1112258118

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e80dc0d1a4534079748ff71bcc02d843c8d66e47b394b3a999157e7cda57e093
+size 1112241766

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_history.json

@@ -0,0 +1,47 @@
+{
+  "train_loss": [
+    0.28792375901471984,
+    0.13033246432829346,
+    0.06221783126762338,
+    0.021929033257405906,
+    0.004770400931878439,
+    0.0017868750816082523,
+    0.0002979135190175225
+  ],
+  "val_loss": [
+    0.17018283961073297,
+    0.16192842652182093,
+    0.201121645155772,
+    0.2721035196031115,
+    0.35463913597548535,
+    0.3679629527588861,
+    0.4272266317928653
+  ],
+  "train_margin": [
+    0.16570352115485346,
+    0.40442659077946275,
+    0.4701661974451948,
+    0.49166955040792193,
+    0.5045746794564234,
+    0.5201993880053275,
+    0.5165628422555966
+  ],
+  "val_margin": [
+    0.3924270189217939,
+    0.4868021993009189,
+    0.483167874449082,
+    0.49650509689600414,
+    0.4942622045979245,
+    0.5186387334616129,
+    0.5087454100601546
+  ],
+  "temperature": [
+    0.0640648826956749,
+    0.054052360355854034,
+    0.04251548647880554,
+    0.03427914157509804,
+    0.028939830139279366,
+    0.026421384885907173,
+    0.024700213223695755
+  ]
+}