| pipeline_tag: text-generation | |
| tags: | |
| - conversational | |
| - text-generation | |
| - custom-chatbot | |
| - overfitted | |
| language: | |
| - ru | |
| - en | |
| # Overfitted Micro-LLM Chatbot | |
| This is a Qwen-2.5-0.5B-Instruct model overfitted on small-talk dataset. | |
| ## Chat Widget Configuration | |
| This model is formatted with appropriate metadata to display the **Interactive Chat Widget** on the Hugging Face model page. | |
| ### Usage | |
| ```python | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| import torch | |
| device = "mps" if torch.backends.mps.is_available() else "cuda" if torch.cuda.is_available() else "cpu" | |
| model_name = "overfitted-model" | |
| tokenizer = AutoTokenizer.from_pretrained(model_name) | |
| model = AutoModelForCausalLM.from_pretrained(model_name).to(device) | |
| ``` | |