pseudollms

Sure, It look like this: Refused to apply inline style because it violates the following Content Security Policy directive: "style-src 'self' 'nonce-hello'". Either the 'unsafe-inline' keyword, a hash ('sha256-9OlNO0DNEeaVzHL4RZwCLsBHA8WBQ8toBp/4F5XV2nc='), or...

@abidlabs I have replicated the same error with latest gradio version: 4.22.0 ``` import gradio as gr print(gr.__file__) # Define a function to be called when the dropdown selection changes...

@pseudotensor Thanks for your quick reply. I installed gradio 3.50.2 and associated gradio_client 0.6.1. However, it is still not working. The environment details and console logs are as follows: ```...

I installed it using the **INSTALL** instructions from the [https://github.com/h2oai/h2ogpt/blob/main/docs/README_LINUX.md](url) for cuda 11.8

And when I doing it with your way i.e quick install then the following things happened 

I first ensured that the correct environment variables are set before following the manual steps. `export PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cu118 https://huggingface.github.io/autogptq-index/whl/cu118"` and then proceed with the provided manual steps. Note: Previously, the same...

Thanks for your response. I successfully integrate vllm engine using h2ogpt ecosystem. `INFO 11-09 10:14:03 llm_engine.py:72] Initializing an LLM engine with config: model='meta-llama/Llama-2-13b-chat-hf', tokenizer='hf-internal-testing/llama-tokenizer', tokenizer_mode=auto, revision=None, tokenizer_revision=None, trust_remote_code=False, dtype=torch.float16, max_seq_len=4096,...

> --local_files_only=True I tried but it didn't work for me when i hit generate.py in CPU using WizardLM-7B-uncensored-GGML.

> Please see the offline docs: https://github.com/h2oai/h2ogpt/blob/main/docs/README_offline.md > > Let me know... For offline mode in which script file I should put all these code for using WizardLM-7B-uncensored-GGML. in CPU...

Sure, I'll wait for it!