Views
No views yet
Crux-Qwen3_OpenThinking-4B is fine-tuned on the Qwen3-4B architecture, optimized for advanced open thinking, mathematical reasoning, and logical problem solving. This model is trained on the traces of sk1.1, which include 1,000 entries from the Gemini thinking trajectory, combined with fine-tuning on 100k tokens of open math reasoning data. This makes it highly effective for nuanced reasoning, educational tasks, and complex problem-solving requiring clear thought processes.
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model_name = "prithivMLmods/Crux-Qwen3_OpenThinking-4B"
4
5model = AutoModelForCausalLM.from_pretrained(
6 model_name,
7 torch_dtype="auto",
8 device_map="auto"
9)
10tokenizer = AutoTokenizer.from_pretrained(model_name)
11
12prompt = "Explain the thought process behind solving: If 5x - 3 = 2x + 12, find x."
13
14messages = [
15 {"role": "system", "content": "You are an open thinking tutor who explains reasoning clearly."},
16 {"role": "user", "content": prompt}
17]
18
19text = tokenizer.apply_chat_template(
20 messages,
21 tokenize=False,
22 add_generation_prompt=True
23)
24
25model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
26
27generated_ids = model.generate(
28 **model_inputs,
29 max_new_tokens=512
30)
31generated_ids = [
32 output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
33]
34
35response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
36print(response)