inference_example.py

import sys
import os
sys.path.append(os.path.dirname(os.path.abspath(__file__)))
from configuration_dolphin import DolphinConfig
from modeling_dolphin import DolphinForCausalLM
from transformers import (AutoTokenizer, AutoModelForCausalLM, AutoConfig)
import torch

def inference_instruct(mycontext, question, device="cuda:0"):
    import time
    MEMORY_SIZE = 32
    start_time = time.time()
    generated_token_ids = []
    prompt = f" <context>{question}"
    text_chunks = [tokenizer(chunk).input_ids for chunk in prompt.split("<context>")]
    input_ids = (
        torch.tensor(
            text_chunks[0] + [-1] * MEMORY_SIZE + text_chunks[1], dtype=torch.long
        )
        .unsqueeze(0)
        .to(device)
    )
    # to process the context
    context_tokenized = tokenizer(
        mycontext + "".join([f"[memory_{i}]" for i in range(MEMORY_SIZE)]),
        return_tensors="pt",
    )
    context_tokenized = {k: v.to(device) for k, v in context_tokenized.items()}
    context_token_count = (context_tokenized["input_ids"]).shape[1] - MEMORY_SIZE
    # We conduct a inference process
    for i in range(context_token_count):
        next_token = (
            model(
                input_ids,
                context_input_ids=context_tokenized["input_ids"],
                context_attention_mask=context_tokenized["attention_mask"],
            )
            .logits[:, -1]
            .argmax(-1)
        )
        if next_token.item() == 151643:
            break
        generated_token_ids.append(next_token.item())
        input_ids = torch.cat([input_ids, next_token.unsqueeze(1)], dim=-1)
    result = tokenizer.decode(generated_token_ids)
    print(f"Time taken: {time.time() - start_time}")
    return result


if __name__ == "__main__":
    # Register your configuration and model
    AutoConfig.register("dolphin", DolphinConfig)
    AutoModelForCausalLM.register(DolphinConfig, DolphinForCausalLM)
    device_name = "cuda:0" if torch.cuda.is_available() else "cpu"

    # Load the tokenizer and model
    tokenizer = AutoTokenizer.from_pretrained('NexaAIDev/Dolphin', trust_remote_code=True)
    model = AutoModelForCausalLM.from_pretrained('NexaAIDev/Dolphin', trust_remote_code=True, torch_dtype=torch.bfloat16, device_map=device_name)
    
    # Run inference example
    mycontext = "Nexa AI is a Cupertino-based company founded in May 2023 that researches and develops models and tools for on-device AI applications. The company is founded by Alex and Zack. The company is known for its Octopus-series models, which rival large-scale language models in capabilities such as function-calling, multimodality, and action-planning, while remaining efficient and compact for edge device deployment. Nexa AI's mission is to advance on-device AI in collaboration with the global developer community. To this end, the company has created an on-device model hub for users to find, share, and collaborate on open-source AI models optimized for edge devices, as well as an SDK for developers to run and deploy AI models locally"
    question = "Who founded Nexa AI?"
    # Pass the context and the correct device string
    result = inference_instruct(mycontext, question, device=device_name)
    print("Result:", result)