license: other
license_name: tongyi-qianwen
license_link: https://huggingface.co/Qwen/Qwen1.5-7B-Chat-GPTQ-Int4/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
tags:
- chat
Qwen1.5-7B-Chat-GPTQ-Int4
Introduction
Qwen1.5-MoE is the beta version of Qwen2-MoE, a transformer-based decoder-only language model pretrained on a large amount of data.
For more details, please refer to our blog post and GitHub repo.
Model Details
Qwen1.5-MoE is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and code. For the beta version, temporarily we did not include GQA and the mixture of SWA and full attention.
Qwen1.5-MoE employs Mixture of Experts (MoE) architecture, where the models are upcycled from dense language models. For instance, Qwen1.5-MoE-A2.7B is upcycled from Qwen-1.8B. It has 14.3B parameters in total and 2.7B activated parameters during runtime, while achieching comparable performance to Qwen1.5-7B, it only requires 20% of the training resources. We also observed that the inference speed is 1.8 times that of Qwen1.5-7B.
Training details
We pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization. However, DPO leads to improvements in human preference evaluation but degradation in benchmark evaluation. In the very near future, we will fix both problems.
Requirements
The code of Qwen1.5-MoE has been in the latest Hugging face transformers and we advise you to install transformers>=4.39.0, or you might encounter the following error:
KeyError: 'qwen2_moe'.
Quickstart
Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4")
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"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
)
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]
Tips
- If you encounter code switching or other bad cases, we advise you to use our provided hyper-parameters in
generation_config.json.