README.md

metadata

license: apache-2.0

Huggingface format for Mobius Chat 12B 128k v4

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
def generate_prompt(instruction, input=""):
    instruction = instruction.strip().replace('\r\n','\n').replace('\n\n','\n')
    input = input.strip().replace('\r\n','\n').replace('\n\n','\n')
    if input:
        return f"""Instruction: {instruction}
Input: {input}
Response:"""
    else:
        return f"""User: {instruction}

Assistant:"""
#model = AutoModelForCausalLM.from_pretrained("TimeMobius/Mobius-Chat-12B-128k-HF", trust_remote_code=True, torch_dtype=torch.bfloat16).to(0)
model = AutoModelForCausalLM.from_pretrained("TimeMobius/Mobius-Chat-12B-128k-HF", trust_remote_code=True, torch_dtype=torch.float16).to(0)
tokenizer = AutoTokenizer.from_pretrained("TimeMobius/Mobius-Chat-12B-128k-HF", trust_remote_code=True)
text = "Write a beginning of sci-fi novel"
prompt = generate_prompt(text)
inputs = tokenizer(prompt, return_tensors="pt").to(0)
output = model.generate(inputs["input_ids"], max_new_tokens=128, do_sample=True, temperature=1.0, top_p=0.3, top_k=0, )
print(tokenizer.decode(output[0].tolist(), skip_special_tokens=True))