Instructions to use BAAI/Aquila2-34B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BAAI/Aquila2-34B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BAAI/Aquila2-34B", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("BAAI/Aquila2-34B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BAAI/Aquila2-34B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BAAI/Aquila2-34B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BAAI/Aquila2-34B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/BAAI/Aquila2-34B
- SGLang
How to use BAAI/Aquila2-34B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "BAAI/Aquila2-34B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BAAI/Aquila2-34B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "BAAI/Aquila2-34B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BAAI/Aquila2-34B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use BAAI/Aquila2-34B with Docker Model Runner:
docker model run hf.co/BAAI/Aquila2-34B
| license: other | |
|  | |
| <h4 align="center"> | |
| <p> | |
| <a href="https://huggingface.co/BAAI/Aquila2-34B/blob/main/README.md">English</a> | | |
| <b>简体中文</b> | | |
| <p> | |
| </h4> | |
| # 悟道·天鹰(Aquila2) | |
| 我们开源了我们的 **Aquila2** 系列,现在包括基础语言模型 **Aquila2-7B** 和 **Aquila2-34B** ,对话模型 **AquilaChat2-7B** 和 **AquilaChat2-34B**,长文本对话模型**AquilaChat2-7B-16k** 和 **AquilaChat2-34B-16k** | |
| 悟道 · 天鹰 Aquila 模型的更多细节将在官方技术报告中呈现。请关注官方渠道更新。 | |
| ## 更新/Updates 2024.6.6 | |
| 我们更新了基础语言模型 **Aquila2-34B**,该模型是基于原版模型经过继续训练得到的,和之前的模型相比,新的模型具备以下优势: | |
| * 更换了具备更大压缩率的tokenizer,不同tokenizer的压缩率对比如下面表格: | |
| | Tokenizer | Size | Zh | En | Code | Math | Average | | |
| |-----------|-------|--------------------------|--------|-------|-------|---------| | |
| | Aquila2-original | 100k | **4.70** | 4.42 | 3.20 | 3.77 | 4.02 | | |
| | Qwen1.5 | 151k | 4.27 | 4.51 | 3.62 | 3.35 | 3.94 | | |
| | Llama3 | 128k | 3.45 | **4.61** | 3.77 | **3.88** | 3.93 | | |
| | Aquila2-new | 143k | 4.60 | **4.61** | **3.78** | **3.88** | **4.22** | | |
| * 模型支持的最大处理长度从2048增加至8192 | |
| ## 快速开始使用 Aquila-34B | |
| ## 使用方式/How to use | |
| ### 1. 推理/Inference | |
| ```python | |
| import torch | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| from transformers import BitsAndBytesConfig | |
| device= "cuda:0" | |
| # 模型名称/Model Name | |
| model_name = 'BAAI/Aquila2-34B' | |
| # 加载模型以及tokenizer | |
| quantization_config=BitsAndBytesConfig( | |
| load_in_4bit=True, | |
| bnb_4bit_use_double_quant=True, | |
| bnb_4bit_quant_type="nf4", | |
| bnb_4bit_compute_dtype=torch.bfloat16, | |
| ) | |
| model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, trust_remote_code=True, | |
| # quantization_config=quantization_config # Uncomment this one for 4-bit quantization | |
| ) | |
| tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True) | |
| model.eval() | |
| model.to(device) | |
| # 对话测试样例/Example | |
| text = "生命的意义是" | |
| tokens = tokenizer.encode_plus(text)['input_ids'] | |
| tokens = torch.tensor(tokens)[None,].to(device) | |
| with torch.no_grad(): | |
| out = model.generate(tokens, do_sample=False, max_length=128, eos_token_id=tokenizer.eos_token_id)[0] | |
| out = tokenizer.decode(out.cpu().numpy().tolist()) | |
| print(out) | |
| ``` | |
| ## 证书/License | |
| `Aquila2系列开源模型使用 [智源Aquila系列模型许可协议](https://huggingface.co/BAAI/Aquila2-34B/blob/main/BAAI-Aquila-Model-License%20-Agreement.pdf) |