tags:
- autotrain
- text-generation-inference
- text-generation
- peft
- chatbot
- depression
- therapy
library_name: transformers
widget:
- messages:
- role: user
content: What is your favorite condiment?
license: other
Model Trained Using AutoTrain
This model was trained using AutoTrain. For more information, please visit AutoTrain.
Usage
from transformers import AutoTokenizer, pipeline import torch
model = "Rhaps360/gemma-dep-ins-ft"
tokenizer = AutoTokenizer.from_pretrained(model) pipeline = pipeline( "text-generation", model=model, model_kwargs={"torch_dtype": torch.bfloat16}, device="cuda" if(torch.cuda.is_available()) else "cpu", )
messages = [ {"role": "user", "content": "### Context: the input message goes here. ### Response: "} ] prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) outputs = pipeline( prompt, max_new_tokens=300, do_sample=True, temperature=0.2, top_k=50, top_p=0.95 ) print(outputs[0]["generated_text"][len(prompt):])