Huihui-Step3-VL-10B-abliterated

import torch
from tqdm import tqdm

from transformers import AutoModelForCausalLM, AutoProcessor, TextStreamer
import os
import sys

NEW_MODEL_ID = "huihui-ai/Huihui-Step3-VL-10B-abliterated"
sys.path.append(NEW_MODEL_ID)

processor = AutoProcessor.from_pretrained(NEW_MODEL_ID, trust_remote_code=True)

model = AutoModelForCausalLM.from_pretrained(
    NEW_MODEL_ID,
    trust_remote_code=True,
    device_map="auto",
    torch_dtype="auto",
).eval()

image_folder_path = "png"
image_files = [f for f in os.listdir(image_folder_path) if f.endswith(".png") or f.endswith(".jpg")]

for filename in tqdm(image_files, desc="Processing Images"):
    image_path = os.path.join(image_folder_path, filename)

    print(f"\nimage_path: {image_path}")
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": f"{image_path}"},
                {"type": "text", "text": "Describe this image."}
            ],
        },
    ]

    print("Response:")

    inputs = processor.apply_chat_template(
        messages,
        tokenize=True,
        add_generation_prompt=True,
        return_dict=True,
        return_tensors="pt"
    ).to(model.device)


    generate_ids = model.generate(
        **inputs,
        max_new_tokens=10240,
        do_sample=False,
        pad_token_id=processor.tokenizer.pad_token_id,
        eos_token_id=processor.tokenizer.eos_token_id,
    )
    output_text = processor.decode(generate_ids[0, inputs["input_ids"].shape[-1] :], skip_special_tokens=True)

    print(output_text)

    txt_filename = os.path.splitext(filename)[0] + ".txt"
    txt_filepath = os.path.join(image_folder_path, txt_filename)
    with open(txt_filepath, "w", encoding="utf-8") as txt_file:
        txt_file.write(output_text[0])

from transformers import AutoModelForCausalLM, AutoProcessor, TextStreamer
import torch
import os
import signal
import time
import sys

cpu_count = os.cpu_count()
print(f"Number of CPU cores in the system: {cpu_count}")
half_cpu_count = cpu_count // 2
os.environ["MKL_NUM_THREADS"] = str(half_cpu_count)
os.environ["OMP_NUM_THREADS"] = str(half_cpu_count)
torch.set_num_threads(half_cpu_count)

print(f"PyTorch threads: {torch.get_num_threads()}")
print(f"MKL threads: {os.getenv('MKL_NUM_THREADS')}")
print(f"OMP threads: {os.getenv('OMP_NUM_THREADS')}")

# Load the model and processor
NEW_MODEL_ID = "huihui-ai/Huihui-Step3-VL-10B-abliterated"

sys.path.append(NEW_MODEL_ID)

print(f"Load Model {NEW_MODEL_ID} ... ")

model = AutoModelForCausalLM.from_pretrained(
    NEW_MODEL_ID,
    trust_remote_code=True,
    device_map="auto",
    torch_dtype="auto",
).eval()

processor = AutoProcessor.from_pretrained(NEW_MODEL_ID, trust_remote_code=True)

messages = []
skip_prompt=True
skip_special_tokens=True

class CustomTextStreamer(TextStreamer):
    def __init__(self, processor, skip_prompt=True, skip_special_tokens=True):
        super().__init__(processor, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)
        self.generated_text = ""
        self.stop_flag = False
        self.init_time = time.time()  # Record initialization time
        self.end_time = None  # To store end time
        self.first_token_time = None  # To store first token generation time
        self.think_tokens_count = 0  # To track total think tokens
        self.token_count = 0  # To track total tokens

    def on_finalized_text(self, text: str, stream_end: bool = False):
        if self.first_token_time is None and text.strip():  # Set first token time on first non-empty text
            self.first_token_time = time.time()
        self.generated_text += text

        self.token_count += 1
        if self.think_tokens_count == 0 and "</think>" in self.generated_text:
        	  self.think_tokens_count = self.token_count
        print(text, end="", flush=True)
        if stream_end:
            self.end_time = time.time()  # Record end time when streaming ends
        if self.stop_flag:
            raise StopIteration

    def stop_generation(self):
        self.stop_flag = True
        self.end_time = time.time()  # Record end time when generation is stopped

    def get_metrics(self):
        """Returns initialization time, first token time, first token latency, end time, total time, total tokens, and tokens per second."""
        if self.end_time is None:
            self.end_time = time.time()  # Set end time if not already set
        total_time = self.end_time - self.init_time  # Total time from init to end
        tokens_per_second = self.token_count / total_time if total_time > 0 else 0
        first_token_latency = (self.first_token_time - self.init_time) if self.first_token_time is not None else None
        metrics = {
            "init_time": self.init_time,
            "first_token_time": self.first_token_time,
            "first_token_latency": first_token_latency,
            "end_time": self.end_time,
            "total_time": total_time,  # Total time in seconds
            "think_tokens_count": self.think_tokens_count,
            "total_tokens": self.token_count,
            "tokens_per_second": tokens_per_second
        }
        return metrics
def generate_stream(model, processor, messages, skip_prompt, skip_special_tokens, max_new_tokens):
    toks = processor.apply_chat_template(
        messages,
        tokenize=True,
        add_generation_prompt=True,
        return_dict=True,
        return_tensors="pt",
    ).to(model.device)

    streamer = CustomTextStreamer(processor, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)

    def signal_handler(sig, frame):
        streamer.stop_generation()
        print("\n[Generation stopped by user with Ctrl+C]")

    signal.signal(signal.SIGINT, signal_handler)

    print("Response: ", end="", flush=True)
    try:
        generated_ids = model.generate(
            **toks,
            max_new_tokens=max_new_tokens,
            do_sample=False,
            pad_token_id=processor.tokenizer.pad_token_id,
            eos_token_id=processor.tokenizer.eos_token_id,
            streamer=streamer,
        )
        del generated_ids
    except StopIteration:
        print("\n[Stopped by user]")

    del toks
    torch.cuda.empty_cache()
    signal.signal(signal.SIGINT, signal.SIG_DFL)

    return streamer.generated_text, streamer.stop_flag, streamer.get_metrics()

while True:
    print(f"skip_prompt: {skip_prompt}")
    print(f"skip_special_tokens: {skip_special_tokens}")
    
    user_input = input("User: ").strip()
    if user_input.lower() == "/exit":
        print("Exiting chat.")
        break
    if user_input.lower() == "/clear":
        messages = []
        print("Chat history cleared. Starting a new conversation.")
        continue
    if user_input.lower() == "/skip_prompt":
        skip_prompt = not skip_prompt
        continue
    if user_input.lower() == "/skip_special_tokens":
        skip_special_tokens = not skip_special_tokens
        continue
    if not user_input:
        print("Input cannot be empty. Please enter something.")
        continue
    

    messages = [{"role": "user", "content": [{"type": "text", "text": user_input}]}]

    response, stop_flag, metrics = generate_stream(model, processor, messages, skip_prompt, skip_special_tokens, 65536)
    print("\n\nMetrics:")
    for key, value in metrics.items():
        print(f"  {key}: {value}")
        
    print("", flush=True)
    if stop_flag:
        continue
    messages.append({"role": "assistant", "content": response})