This is the LLaMAfied version of Qwen1.5-0.5B-Chat model by Alibaba Cloud. The original codebase can be found at: (https://github.com/hiyouga/LLaMA-Factory/blob/main/tests/llamafy_qwen.py). I have made modifications to make it compatible with qwen1.5. This model is converted with https://github.com/Minami-su/character_AI_open/blob/main/llamafy_qwen_v2.py
Usage:
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
tokenizer = AutoTokenizer.from_pretrained("Minami-su/Qwen1.5-0.5B-Chat_llamafy")
model = AutoModelForCausalLM.from_pretrained("Minami-su/Qwen1.5-0.5B-Chat_llamafy", torch_dtype="auto", device_map="auto")
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
messages = [
{"role": "user", "content": "Who are you?"}
]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
inputs = inputs.to("cuda")
generate_ids = model.generate(inputs,max_length=2048, streamer=streamer)
Test
load in 4bit
hf-causal (pretrained=Qwen1.5-0.5B-Chat), limit: None, provide_description: False, num_fewshot: 0, batch_size: 32
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.2389|± |0.0125|
| | |acc_norm|0.2688|± |0.0130|
|truthfulqa_mc| 1|mc1 |0.2534|± |0.0152|
| | |mc2 |0.4322|± |0.0151|
|winogrande | 0|acc |0.5564|± |0.0140|
load in 4bit
hf-causal (pretrained=Qwen1.5-0.5B-Chat_llamafy), limit: None, provide_description: False, num_fewshot: 0, batch_size: 32
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|arc_challenge| 0|acc |0.2398|± |0.0125|
| | |acc_norm|0.2705|± |0.0130|
|truthfulqa_mc| 1|mc1 |0.2534|± |0.0152|
| | |mc2 |0.4322|± |0.0151|
|winogrande | 0|acc |0.5556|± |0.0140|