Upload folder using huggingface_hub

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,51 @@
+---
+language: en
+license: other
+tags:
+  - sentiment-analysis
+  - fine-tuned
+  - sentiment-classification
+  - transformers
+model_name: Fine-Tuned Sentiment Model
+model_type: Roberta
+datasets:
+  - custom-dataset
+metrics:
+  - micro precision and recall
+  - macro precision and recall
+---
+
+# Fine-Tuned Sentiment Model
+    This model is fine-tuned for Sentiment Analysis task, the model classifies a customer ticket into 5-categories of sentiments, namely:
+        - "Strong Negative"
+        - "Mild Negative"
+        - "Neutral"
+        - "Mild Positive"
+        - "Strong Positive"
+
+    *Point To Note*: The Customers are from these specific industries only:
+        - Food
+        - Cars
+        - Pet Food
+        - Furniture
+        - Beauty
+
+## Model Details
+    - **Model Architecture**: This fine-tuned model was built on a pre-trained model, "IDEA-CCNL/Erlangshen-Roberta-110M-Sentiment"
+    - **Training Dataset**: The Dataset was generated using the model, "meta-llama/Llama-3.2-1B-Instruct"
+
+## Example Usage-
+    To use this model for Sentiment Analysis:
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained("your_username/fine_tuned_sentiment_model_rt")
+model = AutoModelForSequenceClassification.from_pretrained("your_username/fine_tuned_sentiment_model_rt")
+
+# Example input
+inputs = tokenizer("The food was a bit bland, but the portion sizes were generous. I was looking forward to trying it, but it didn't quite live up to my expectations.", return_tensors='pt')
+outputs = model(**inputs)
+predicted_class = torch.argmax(outputs.logits, dim = 1).item()
+print("Predicted Sentiment:", predicted_class)

README.md

@@ -0,0 +1,51 @@
+---
+language: en
+license: other
+tags:
+  - sentiment-analysis
+  - fine-tuned
+  - sentiment-classification
+  - transformers
+model_name: Fine-Tuned Sentiment Model
+model_type: Roberta
+datasets:
+  - custom-dataset
+metrics:
+  - micro precision and recall
+  - macro precision and recall
+---
+
+# Fine-Tuned Sentiment Model
+    This model is fine-tuned for Sentiment Analysis task, the model classifies a customer ticket into 5-categories of sentiments, namely:
+        - "Strong Negative"
+        - "Mild Negative"
+        - "Neutral"
+        - "Mild Positive"
+        - "Strong Positive"
+
+    *Point To Note*: The Customers are from these specific industries only:
+        - Food
+        - Cars
+        - Pet Food
+        - Furniture
+        - Beauty
+
+## Model Details
+    - **Model Architecture**: This fine-tuned model was built on a pre-trained model, "IDEA-CCNL/Erlangshen-Roberta-110M-Sentiment"
+    - **Training Dataset**: The Dataset was generated using the model, "meta-llama/Llama-3.2-1B-Instruct"
+
+## Example Usage-
+    To use this model for Sentiment Analysis:
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained("your_username/fine_tuned_sentiment_model_rt")
+model = AutoModelForSequenceClassification.from_pretrained("your_username/fine_tuned_sentiment_model_rt")
+
+# Example input
+inputs = tokenizer("The food was a bit bland, but the portion sizes were generous. I was looking forward to trying it, but it didn't quite live up to my expectations.", return_tensors='pt')
+outputs = model(**inputs)
+predicted_class = torch.argmax(outputs.logits, dim = 1).item()
+print("Predicted Sentiment:", predicted_class)

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "IDEA-CCNL/Erlangshen-Roberta-110M-Sentiment",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Strong Negative",
+    "1": "Mild Negative",
+    "2": "Neutral",
+    "3": "Mild Positive",
+    "4": "Strong Positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Mild Negative": 1,
+    "Mild Positive": 3,
+    "Neutral": 2,
+    "Strong Negative": 0,
+    "Strong Positive": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:005b180c3b177101936e14cf8aa5ff4eebf5684da7e672cbf4b145644de6da1b
+size 409109468

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}