Views
No views yet
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model_name = "ertghiu256/Qwen3-Hermes-4b"
4
5# load the tokenizer and the model
6tokenizer = AutoTokenizer.from_pretrained(model_name)
7model = AutoModelForCausalLM.from_pretrained(
8 model_name,
9 torch_dtype="auto",
10 device_map="auto"
11)
12
13# prepare the model input
14prompt = "Give me a short introduction to large language model."
15messages = [
16 {"role": "user", "content": prompt}
17]
18text = tokenizer.apply_chat_template(
19 messages,
20 tokenize=False,
21 add_generation_prompt=True,
22 enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
23)
24model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
25
26# conduct text completion
27generated_ids = model.generate(
28 **model_inputs,
29 max_new_tokens=32768
30)
31output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
32
33# parsing thinking content
34try:
35 # rindex finding 151668 (</think>)
36 index = len(output_ids) - output_ids[::-1].index(151668)
37except ValueError:
38 index = 0
39
40thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
41content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
42
43print("thinking content:", thinking_content)
44print("content:", content)vllm serve ertghiu256/Qwen3-Hermes-4b --enable-reasoning --reasoning-parser deepseek_r1python -m sglang.launch_server --model-path ertghiu256/Qwen3-Hermes-4b --reasoning-parser deepseek-r1llama-server --hf-repo ertghiu256/Qwen3-Hermes-4bllama-cli --hf ertghiu256/Qwen3-Hermes-4bollama run hf.co/ertghiu256/Qwen3-Hermes-4b:Q4_K_M ertghiu256/Qwen3-Hermes-4b