Llama2-Code-Interpreter

Llama2-Code-Interpreter copied to clipboard

My graphics card has insufficient memory. Can I use memory and graphics memory to run it? My computer: - Window 10 - GTX 1063 - DDR4 24G Run error message:...

Jackxwb

RUN: python chatbot.py --path Seungyoun/codellama-7b-instruct-pad ERROR: PermissionError: [Errno 13] Permission denied

1

Winhalls

Hi, Does this repo support tabular data as input, such as csv or xlsx file, and perform data analysis on those file?

Tizzzzy

willshion

运行python3 chatbot.py --path Seungyoun/codellama-7b-instruct-pad报错

1

requests.exceptions.SSLError: (MaxRetryError("HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /Seungyoun/codellama-7b-instruct-pad/resolve/main/tokenizer.model (Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:997)')))"), '(Request ID: 9eb34357-ae1e-42ef-9983-61926a9e5c8d)')

heyuwei1018

I would recommend broadening your project to be more flexible, like AutoGen but for open-source models, because Autogen currently only supports OpenAI. I think your library would be very popular....

Tylersuard

google.protobuf.message.DecodeError: Error parsing message with type 'sentencepiece.ModelProto'

1165787081

local variable 'sentencepiece_model_pb2' referenced before assignment

2

python：3.8.10 GPU：RTX 4090 24GB OS：Ubuntu 18.04 

Roych13

I get the following errors when trying to install the requirements.txt. error: subprocess-exited-with-error × Getting requirements to build wheel did not run successfully. │ exit code: 1 ╰─> [20 lines...

JimmyDub010

NameError: name 'llama_ci_path' is not defined ? python chatbot.py --path Seungyoun/codellama-7b-instruct-pad

BishAU