Upload 10 files

README.md

@@ -0,0 +1,119 @@
+
+# Sentence Transformer Quantized Model for Movie Recommendation on Movie-Lens-Dataset
+
+This repository hosts a quantized version of the Sentence Transformer model, fine-tuned for Movie Recommendation using the Movie Lens dataset. The model has been optimized using FP16 quantization for efficient deployment without significant accuracy loss.
+
+## Model Details
+
+- **Model Architecture:** Sentence Transformer 
+- **Task:** Movie Recommendation  
+- **Dataset:** Movie Lens Dataset
+- **Quantization:** Float16  
+- **Fine-tuning Framework:** Hugging Face Transformers  
+
+---
+
+## Installation
+
+```bash
+!pip install pandas torch sentence-transformers scikit-learn
+
+```
+
+---
+
+## Loading the Model
+
+```python
+from sentence_transformers import SentenceTransformer, InputExample, losses, util
+import torch
+
+# Load  model
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2', device=device)
+
+# pass the movie name
+recommend_by_movie_name("Toy Story")
+
+
+# Recommend Movies
+def recommend_by_movie_name(movie_name, top_k=5):
+    titles = movie_subset["title"].tolist()
+    matches = get_close_matches(movie_name, titles, n=1, cutoff=0.6)
+    
+    if not matches:
+        print(f"❌ Movie '{movie_name}' not found in dataset.")
+        return
+    
+    matched_title = matches[0]
+    movie_index = movie_subset[movie_subset["title"] == matched_title].index[0]
+    
+    query_embedding = movie_embeddings[movie_index]
+    scores = util.pytorch_cos_sim(query_embedding, movie_embeddings)[0]
+    top_results = torch.topk(scores, k=top_k + 1)
+
+    print(f"\n🎬 Recommendations for: {matched_title}")
+    for score, idx_tensor in zip(top_results[0][1:], top_results[1][1:]):  # skip itself
+        idx = idx_tensor.item()  # ✅ Convert tensor to int
+        title = movie_subset.iloc[idx]["title"]
+        print(f"  {title} (Score: {score:.4f})")
+
+```
+
+---
+
+
+---
+
+## Fine-Tuning Details
+
+### Dataset
+
+The dataset is sourced from Hugging Face’s `Movie-Lens` dataset. It contains 20,000 movies and their genres.  
+
+### Training
+
+- **Epochs:** 2  
+- **warmup_steps:**100  
+- **show_progress_bar:** True  
+- **Evaluation strategy:** `epoch`  
+
+---
+
+## Quantization
+
+Post-training quantization was applied using PyTorch’s `half()` precision (FP16) to reduce model size and inference time.
+
+---
+
+## Repository Structure
+
+```python
+.
+├── quantized-model/               # Contains the quantized model files
+│   ├── config.json
+│   ├── model.safetensors
+│   ├── tokenizer_config.json
+│   ├── modules.json
+│   └── special_tokens_map.json
+│   ├── sentence_bert_config.jason
+│   └── tokenizer.json
+│   ├── config_sentence_transformers.jason
+│   └── vocab.txt
+
+├── README.md                      # Model documentation
+```
+
+---
+
+## Limitations
+
+- The model is trained specifically for Movie Recommendation on Movies Dataset.
+- FP16 quantization may result in slight numerical instability in edge cases.
+
+
+---
+
+## Contributing
+
+Feel free to open issues or submit pull requests to improve the model or documentation.

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float16",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.51.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddfa40a11a64b4a35f1cc724b4a902f102307993ef828a2ea2483ba37b2fbb36
+size 45437760

modules.json

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

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}