| --- |
| tags: |
| - autotrain |
| - text-generation |
| widget: |
| - text: 'Hello ' |
| license: other |
| library_name: transformers |
| pipeline_tag: text2text-generation |
| --- |
| |
| # Model Trained Using AutoTrain |
|
|
| This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain). |
| # Architecture |
|
|
| This model finetuned version of llama-2-7b |
| # Usage |
|
|
| ```python |
| |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| |
| model_path = "OmlyCheeini/Llama-Discore" |
| |
| tokenizer = AutoTokenizer.from_pretrained(model_path) |
| model = AutoModelForCausalLM.from_pretrained( |
| model_path, |
| device_map="auto", |
| torch_dtype='auto' |
| ).eval() |
| |
| # Prompt content: "hi" |
| messages = [ |
| {"role": "user", "content": "hi"} |
| ] |
| |
| input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt') |
| output_ids = model.generate(input_ids.to('cuda')) |
| response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True) |
| |
| # Model response: "Hello! How can I assist you today?" |
| print(response) |
| ``` |
