CogVLM
CogVLM copied to clipboard
a state-of-the-art-level open visual language model | 多模态预训练模型
### Feature request / 功能建议 Hello, Is it possible to deploy CogVLM using Docker on OVH Cloud? I want to send requests to basic_demo/cli_demo_sat.py file Can someone please explain to...
断点继续训练如何设置
请问CogVLM大模型断点继续训练如何设置配置   args.load  谢谢
### System Info / 系統信息 版本及硬件按照指示安装 ### Who can help? / 谁可以帮助到您? @1049451037 ### Information / 问题信息 - [X] The official example scripts / 官方的示例脚本 - [ ] My own...
While CogVLM is trained, LM weights are fronzen. From my observation however, the LM weights of cogvlm are different with Vicuna Vicuna: https://huggingface.co/lmsys/vicuna-7b-v1.5/tree/main CogVLM: cogvlm-chat-v1.1 (both from HF or SAT)...
能否说明一下这些参数具体是指哪些模块:enable = ["encoder", "cross_attention", "linear_proj", 'mlp.vision', 'rotary.vision', 'eoi', 'boi', 'vit'],如果要冻结是不是仅仅在这里设置就可以了
### System Info / 系統信息 4x A800 ### Who can help? / 谁可以帮助到您? @1049451037 ### Information / 问题信息 - [X] The official example scripts / 官方的示例脚本 - [ ] My...
### System Info / 系統信息 tokenizer = LlamaTokenizer.from_pretrained('lmsys/vicuna-7b-v1.5') model = AutoModelForCausalLM.from_pretrained( 'THUDM/cogvlm-chat-hf', torch_dtype=torch.bfloat16, low_cpu_mem_usage=True, trust_remote_code=True ).to('cuda').eval() ### Who can help? / 谁可以帮助到您? _No response_ ### Information / 问题信息 - [...
Is it possible to run CogVLM with the actual openai API (`client.chat.completions.create`)? If this is not possible, how do we run CogVLM through an A100 server using the `openai demo`...
尝试让CogVLM-chat描述图像,但是返回的信息是`error`。  但是grounding模型就可以正常工作。 
### Feature request / 功能建议 The script which can transform CogAgent weights' sat version to huggingface version. ### Motivation / 动机 Many company use the huggingace transformers library, and sat...