umarfarzan/sideeffect-algorithm-expert

1---2language: en3license: apache-2.04tags:5- social-media6- content-analysis7- deepseek8- llama9- unsloth10datasets:11- custom12metrics:13- accuracy14library_name: transformers15pipeline_tag: text-generation16widget:17- text: "Let me show you how to track your expenses with this simple spreadsheet template. First, create columns for date, category, and amount. Then, use the SUM function to automatically calculate your total spending..."18---19 20# Social Media Content Analyzer21 22This model is fine-tuned from DeepSeek-R1-Distill-Llama-8B to analyze social media content and generate:23 241. Detailed content critiques analyzing:25   - Hook effectiveness26   - Reliability factor27   - Relatability28   - Shareability292. Attention-grabbing titles optimized for TikTok, Instagram Reels, or YouTube Shorts30 31## Usage Example32 33```python34from transformers import AutoModelForCausalLM, AutoTokenizer35 36model_id = "umarfarzan/social-media-content-analyzer"37model = AutoModelForCausalLM.from_pretrained(model_id)38tokenizer = AutoTokenizer.from_pretrained(model_id)39 40def generate_content_analysis(transcript, confidence_score):41    prompt = f"""Below is a transcript from a social media video along with its confidence score.42Your task is to analyze the content and provide a detailed content critique analyzing the hook, reliability factor, relatability, and shareability.43 44### Transcript:45{transcript}46 47### Confidence Score:48{confidence_score}49 50### Content Critique:"""51 52    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")53    outputs = model.generate(54        input_ids=inputs.input_ids,55        attention_mask=inputs.attention_mask,56        max_new_tokens=1000,57        temperature=0.7,58        top_p=0.959    )60    response = tokenizer.decode(outputs[0], skip_special_tokens=True)61    return response.split("### Content Critique:")[1].strip()62 63# Example usage64transcript = "Let me show you how to track your expenses with this simple spreadsheet template..."65score = 8866critique = generate_content_analysis(transcript, score)67print(critique)68```69 70## Training71This model was fine-tuned using Unsloth on a dataset of social media content with expert annotations.72