Govind Tiwari

not able to quantize after fine tuning

2

i am not able to quantize and getting this error FileNotFoundError: Could not find tokenizer.model in llama-2-7b-meditext or its parent; if it's in another directory, pass the directory as --vocab-dir...

ERROR

2

I am getting this error every time in info box but no problem during the installation [ERROR] Get target tone color error cuFFT error: CUFFT_INTERNAL_ERROR

ModuleNotFoundError

1

No module named 'crewai.agents.cache

Ollama streaming output is garbled

1

is I use local LLMs with Ollama produces outputs with words that are some times garbage. Using Ollama server outside the Chatbot-UI does not exhibit this issue.

Tokenizers issue

2

ERROR: Cannot install -r requirements.txt (line 36)

Error says Error initializing FFT: 5

Core Dump

1

INFO - Initializing model finished in 16985.25ms. INFO - Processing images ... INFO - Processing images finished in 1468.80ms. INFO - Running image 1/1 ...

Custom keymap not working

1

I cant interact with my screen through QTscrcpy normally, is there some way to enable control that I am normally

Seems not compatible with DeepSpeed