metadata

tags:
  - autotrain
  - text-generation
widget:
  - text: 'I love AutoTrain because '
license: other

Model Trained Using AutoTrain

This model was trained using AutoTrain. For more information, please visit AutoTrain.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "GRMenon/Mental-Mistral-7B-Instruct-AutoTrain"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    torch_dtype='auto'
).eval()

device = "cuda" if torch.cuda.is_available() else "cpu"

# Prompt content:
messages = [
    {"role": "user", "content": "Hey Connor! I have been feeling a bit down lately. I could really use some advice on how to feel better?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt').to(device)
output_ids = model.generate(input_ids=input_ids, max_new_tokens=512, do_sample=True, pad_token_id=2)
response = tokenizer.batch_decode(output_ids.detach().cpu().numpy(), skip_special_tokens = True)

# Model response: 
print(response[0])