| messages = [{"role": "user", "content": prompt}] | |
| text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) | |
| model_inputs = tokenizer([text], return_tensors="pt").to(device) | |
| generated_ids = model.generate(model_inputs.input_ids, max_new_tokens=512, do_sample=True) | |
| generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)] | |
| response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] | |
| Qwen2Config | |
| [[autodoc]] Qwen2Config | |
| Qwen2Tokenizer | |
| [[autodoc]] Qwen2Tokenizer | |
| - save_vocabulary | |
| Qwen2TokenizerFast | |
| [[autodoc]] Qwen2TokenizerFast | |
| Qwen2Model | |
| [[autodoc]] Qwen2Model | |
| - forward | |
| Qwen2ForCausalLM | |
| [[autodoc]] Qwen2ForCausalLM | |
| - forward | |
| Qwen2ForSequenceClassification | |
| [[autodoc]] Qwen2ForSequenceClassification | |
| - forward |