deepseek-coder-33B-instruct 模型 DeepSeek Coder 33B 是一个代码语言模型, 基于 2 万亿数据训练而成,其中 87% 为代码, 13% 为中英文语言。模型引入 16K 窗口大小和填空任务,提供项目级别的代码补全和片段填充功能。 8K 支持该模型的服务商 deepseek-coder-33B-instruct 最大上下文长度 8K 最大输出长度 -- ...
Use FastChat to start the deepseek-coder-33b-instruct model, send a stream request and got an error response. If set stream=False, you can print a good response If change to other models, it also works with stream Start cmd: python3 -m f...
[INFO|configuration_utils.py:728] 2023-12-12 09:03:50,977 >> loading configuration file /media/models/models/deepseek-ai/deepseek-coder-33b-instruct/generation_config.json [INFO|configuration_utils.py:770] 2023-12-12 09:03:50,978 >> Generate config GenerationConfig { "bos_token_id": 32...
libc++abi: terminating due to uncaught exception of type std::out_of_range: unordered_map::at: key not found zsh: abort ./build/bin/main -m ./deepseek-coder-33b-instruct/ggml-model-Q8_0.gguf --seed