File size: 4,906 Bytes
606e387 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 |
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextStreamer
import torch
import os
import signal
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 tokenizer
NEW_MODEL_ID = "huihui-ai/Qwen3-8B-abliterated"
print(f"Load Model {NEW_MODEL_ID} ... ")
quant_config_4 = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_use_double_quant=True,
llm_int8_enable_fp32_cpu_offload=True,
)
model = AutoModelForCausalLM.from_pretrained(
NEW_MODEL_ID,
device_map="auto",
trust_remote_code=True,
#quantization_config=quant_config_4,
torch_dtype=torch.bfloat16
)
tokenizer = AutoTokenizer.from_pretrained(NEW_MODEL_ID, trust_remote_code=True)
if tokenizer.pad_token is None:
tokenizer.pad_token = tokenizer.eos_token
tokenizer.pad_token_id = tokenizer.eos_token_id
initial_messages = [{"role": "system", "content": "You are a helpful assistant."}]
messages = initial_messages.copy()
enable_thinking = True
skip_prompt=True
skip_special_tokens=True
class CustomTextStreamer(TextStreamer):
def __init__(self, tokenizer, skip_prompt=True, skip_special_tokens=True):
super().__init__(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)
self.generated_text = ""
self.stop_flag = False
def on_finalized_text(self, text: str, stream_end: bool = False):
self.generated_text += text
print(text, end="", flush=True)
if self.stop_flag:
raise StopIteration
def stop_generation(self):
self.stop_flag = True
def generate_stream(model, tokenizer, messages, enable_thinking, skip_prompt, skip_special_tokens, max_new_tokens):
input_ids = tokenizer.apply_chat_template(
messages,
tokenize=True,
enable_thinking = enable_thinking,
add_generation_prompt=True,
return_tensors="pt"
)
attention_mask = torch.ones_like(input_ids, dtype=torch.long)
tokens = input_ids.to(model.device)
attention_mask = attention_mask.to(model.device)
streamer = CustomTextStreamer(tokenizer, 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(
tokens,
attention_mask=attention_mask,
use_cache=False,
max_new_tokens=max_new_tokens,
do_sample=True,
pad_token_id=tokenizer.pad_token_id,
streamer=streamer
)
del generated_ids
except StopIteration:
print("\n[Stopped by user]")
del input_ids, attention_mask
torch.cuda.empty_cache()
signal.signal(signal.SIGINT, signal.SIG_DFL)
return streamer.generated_text, streamer.stop_flag
while True:
user_input = input("User: ").strip()
if user_input.lower() == "/exit":
print("Exiting chat.")
break
if user_input.lower() == "/clear":
messages = initial_messages.copy()
print("Chat history cleared. Starting a new conversation.")
continue
if user_input.lower() == "/no_think":
if enable_thinking:
enable_thinking = False
print("Thinking = False.")
else:
enable_thinking = True
print("Thinking = True.")
continue
if user_input.lower() == "/skip_prompt":
if skip_prompt:
skip_prompt = False
print("skip_prompt = False.")
else:
skip_prompt = True
print("skip_prompt = True.")
continue
if user_input.lower() == "/skip_special_tokens":
if skip_special_tokens:
skip_special_tokens = False
print("skip_special_tokens = False.")
else:
skip_special_tokens = True
print("skip_special_tokens = True.")
continue
if not user_input:
print("Input cannot be empty. Please enter something.")
continue
messages.append({"role": "user", "content": user_input})
response, stop_flag = generate_stream(model, tokenizer, messages, enable_thinking, skip_prompt, skip_special_tokens, 8192)
print("", flush=True)
if stop_flag:
continue
messages.append({"role": "assistant", "content": response})
|