| --- |
| language: |
| - en |
|
|
| pipeline_tag: text-classification |
|
|
| tags: |
| - sentiment-analysis |
| - text-classification |
| - opinion-mining |
| - emotion-detection |
| - nlp |
| - natural-language-processing |
| - transformers |
| - peft |
| - lora |
| - adapter |
| - fine-tuning |
| - gemma |
| - gemma-2b |
| - base_model:google/gemma-2b |
| - base_model:adapter:google/gemma-2b |
|
|
| library_name: peft |
|
|
| base_model: google/gemma-2b |
|
|
| license: apache-2.0 |
|
|
| model-index: |
| - name: Sentiment Analyzer (LoRA Gemma-2B) |
| results: |
| - task: |
| type: text-classification |
| name: Sentiment Analysis |
| metrics: |
| - type: accuracy |
| value: not-reported |
| --- |
| |
| # Sentiment Analyzer (LoRA Fine-Tuned Gemma-2B) |
|
|
| ## Model Overview |
|
|
| **Sentiment Analyzer** is a **LoRA fine-tuned Gemma-2B transformer model** for **sentiment analysis and text classification** tasks. |
| It uses **PEFT (Parameter-Efficient Fine-Tuning)** to deliver strong performance while keeping memory and compute requirements low. |
|
|
| This model is well-suited for: |
| - Sentiment analysis |
| - Opinion mining |
| - Review classification |
| - Emotion-aware text generation |
| - Lightweight NLP deployments |
|
|
| --- |
|
|
| ## Tasks |
|
|
| - Text Classification |
| - Sentiment Analysis |
|
|
| --- |
|
|
| ## Model Details |
|
|
| - **Developed by:** `mysmmurf12` |
| - **Shared by:** `mysmmurf12` |
| - **Model type:** Transformer-based Language Model |
| - **Base model:** `google/gemma-2b` |
| - **Fine-tuning method:** LoRA (Low-Rank Adaptation) |
| - **Library:** PEFT + Transformers |
| - **Language:** English |
| - **License:** Apache 2.0 (inherits from base model) |
|
|
| --- |
|
|
| ## Model Sources |
|
|
| - **Hugging Face Repository:** |
| https://huggingface.co/mysmmurf12/sentiment-analyzer |
|
|
| - **Base Model:** |
| https://huggingface.co/google/gemma-2b |
|
|
| --- |
|
|
| ## Intended Uses |
|
|
| ### ✅ Direct Use |
|
|
| - Sentiment classification (positive / negative / neutral) |
| - Customer feedback and review analysis |
| - Social media sentiment monitoring |
| - Sentiment-aware chatbots |
|
|
| ### 🔁 Downstream Use |
|
|
| - Integration into RAG pipelines |
| - Domain-specific sentiment fine-tuning |
| - Deployment via APIs, Streamlit apps, or dashboards |
|
|
| ### 🚫 Out-of-Scope Use |
|
|
| - Medical, legal, or financial decision-making |
| - High-risk automated moderation |
| - Multilingual sentiment tasks (English-focused) |
|
|
| --- |
|
|
| ## Bias, Risks, and Limitations |
|
|
| - May reflect biases present in training data |
| - Less reliable on sarcasm or ambiguous language |
| - Not evaluated on standardized sentiment benchmarks |
|
|
| **Recommendation:** |
| Use human validation for high-impact applications. |
|
|
| --- |
|
|
| ## How to Use the Model |
|
|
| ### Load with Transformers + PEFT |
|
|
| ```python |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| from peft import PeftModel |
| |
| base_model = "google/gemma-2b" |
| adapter_model = "mysmmurf12/sentiment-analyzer" |
| |
| tokenizer = AutoTokenizer.from_pretrained(base_model) |
| model = AutoModelForCausalLM.from_pretrained(base_model) |
| |
| model = PeftModel.from_pretrained(model, adapter_model) |
| |
| text = "The product quality is amazing!" |
| inputs = tokenizer(text, return_tensors="pt") |
| |
| outputs = model.generate( |
| **inputs, |
| max_new_tokens=50, |
| temperature=0.7 |
| ) |
| |
| print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
| |
