Instructions to use fwerkor/capai-chat-2009 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fwerkor/capai-chat-2009 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="fwerkor/capai-chat-2009", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("fwerkor/capai-chat-2009", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from fwerkor/capai-chat-2009: direct link, hf CLI and curl.
- Browser
- Download file 559 Bytes
-
https://huggingface.co/fwerkor/capai-chat-2009/resolve/main/README.md
- Command line
-
hf download hf://fwerkor/capai-chat-2009/README.md
-
curl -L -o README.md https://huggingface.co/fwerkor/capai-chat-2009/resolve/main/README.md
559 Bytes
metadata
license: apache-2.0
language:
- zh
- en
FWERKOR CapAI Chat 2009 Model
capai-chat-2009是一个开源13B对话语言模型,支持工具调用(Toolcall),支持128K上下文。
模型信息
参数集规模:13B
最大token数:128K
fp16硬件要求:显存30GB
使用方式
官方API和体验
FWERKOR团队官方提供的ai.fwerkor.com平台可进行体验和API调用。
自行部署
capai-chat-2009是一个轻量化的AI对话模型,可以在性能有限的硬件上运行,在int4量化后仍然表现良好。