Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 1.5B Qwen2 model.
Compared with the state-of-the-art opensource language models, including the previous released Qwen1.5, Qwen2 has generally surpassed most opensource models and demonstrated competitiveness against proprietary models across a series of benchmarks targeting for language understanding, language generation, multilingual capability, coding, mathematics, reasoning, etc.
Qwen2 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes.
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.
Requirements
The code of Qwen2 has been in the latest Hugging face transformers and we advise you to install
transformers>=4.37.0
, or you might encounter the following error:
KeyError: 'qwen2'
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/Qwen2-1.5B-Instruct-AWQ",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-1.5B-Instruct-AWQ")
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 inzip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
Benchmark and Speed
To compare the generation performance between bfloat16 (bf16) and quantized models such as GPTQ-Int8, GPTQ-Int4, and AWQ, please consult our
Benchmark of Quantized Models
. This benchmark provides insights into how different quantization techniques affect model performance.
For those interested in understanding the inference speed and memory consumption when deploying these models with either
transformer
or
vLLM
, we have compiled an extensive
Speed Benchmark
.
Citation
If you find our work helpful, feel free to give us a cite.
Qwen2-1.5B-Instruct-AWQ huggingface.co is an AI model on huggingface.co that provides Qwen2-1.5B-Instruct-AWQ's model effect (), which can be used instantly with this Qwen Qwen2-1.5B-Instruct-AWQ model. huggingface.co supports a free trial of the Qwen2-1.5B-Instruct-AWQ model, and also provides paid use of the Qwen2-1.5B-Instruct-AWQ. Support call Qwen2-1.5B-Instruct-AWQ model through api, including Node.js, Python, http.
Qwen2-1.5B-Instruct-AWQ huggingface.co is an online trial and call api platform, which integrates Qwen2-1.5B-Instruct-AWQ's modeling effects, including api services, and provides a free online trial of Qwen2-1.5B-Instruct-AWQ, you can try Qwen2-1.5B-Instruct-AWQ online for free by clicking the link below.
Qwen Qwen2-1.5B-Instruct-AWQ online free url in huggingface.co:
Qwen2-1.5B-Instruct-AWQ is an open source model from GitHub that offers a free installation service, and any user can find Qwen2-1.5B-Instruct-AWQ on GitHub to install. At the same time, huggingface.co provides the effect of Qwen2-1.5B-Instruct-AWQ install, users can directly use Qwen2-1.5B-Instruct-AWQ installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Qwen2-1.5B-Instruct-AWQ install url in huggingface.co: