Instructions to use xverse/XVERSE-13B-256K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xverse/XVERSE-13B-256K with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="xverse/XVERSE-13B-256K", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("xverse/XVERSE-13B-256K", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use xverse/XVERSE-13B-256K with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "xverse/XVERSE-13B-256K" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xverse/XVERSE-13B-256K", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/xverse/XVERSE-13B-256K
- SGLang
How to use xverse/XVERSE-13B-256K 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 "xverse/XVERSE-13B-256K" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xverse/XVERSE-13B-256K", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "xverse/XVERSE-13B-256K" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xverse/XVERSE-13B-256K", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use xverse/XVERSE-13B-256K with Docker Model Runner:
docker model run hf.co/xverse/XVERSE-13B-256K
256k大概需要多少显存才可以支持?
如题
用tensorRT的话,八卡能跑256k
用tensorRT的话,八卡能跑256k
你好,请问是什么样的显卡配置,谢谢
我们用的h800或者a800,单卡80G
13b 模型需要这么大的显存吗?640GB?!我运行Vicuna 13b 16k 未量化只需要30多GB啊。
我查看了65B模型的介绍页,硬件需求如下:
XVERSE-65B Inference BF16/FP16 500GB 2*A800 80G
65B模型推理只需要2张A800,为什么13B需要更多显存呢?
13b 模型需要这么大的显存吗?640GB?!我运行Vicuna 13b 16k 未量化只需要30多GB啊。
跑16K不用那么多显存,跑256K需要8卡。因为显存随着序列长度成平方倍增长
我查看了65B模型的介绍页,硬件需求如下:
XVERSE-65B Inference BF16/FP16 500GB 2*A800 80G65B模型推理只需要2张A800,为什么13B需要更多显存呢?
跑256K需要8卡,因为显存随着序列长度成平方倍增长
我查看了65B模型的介绍页,硬件需求如下:
XVERSE-65B Inference BF16/FP16 500GB 2*A800 80G65B模型推理只需要2张A800,为什么13B需要更多显存呢?
跑256K需要8卡,因为显存随着序列长度成平方倍增长
是的,非常对