Open svaverbe opened 8 months ago
I would advise using lollms (my other project) which allows you do do way more than just analyzing small pandas dataframes :) https://github.com/ParisNeo/lollms-webui
I installed the tool on windows. What language models do you recommend ? And I assume there are extensions useful for data science and processing numeric data ?
Van: Saifeddine ALOUI @.> Verzonden: donderdag 7 maart 2024 11:34 Aan: ParisNeo/gpt4pandas @.> CC: svaverbe @.>; Author @.> Onderwerp: Re: [ParisNeo/gpt4pandas] memory requirements ? (Issue #1)
I would advise using lollms (my other project) which allows you do do way more than just analyzing small pandas dataframes :) https://github.com/ParisNeo/lollms-webui
— Reply to this email directly, view it on GitHub https://github.com/ParisNeo/gpt4pandas/issues/1#issuecomment-1983218092 , or unsubscribe https://github.com/notifications/unsubscribe-auth/AF5RR45WEYL7JMCTUXMPXHLYXA7CBAVCNFSM6AAAAABEHPV5LGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTSOBTGIYTQMBZGI . You are receiving this because you authored the thread. https://github.com/notifications/beacon/AF5RR433WA2XN57KWOEICSLYXA7CBA5CNFSM6AAAAABEHPV5LGWGG33NNVSW45C7OR4XAZNMJFZXG5LFINXW23LFNZ2KUY3PNVWWK3TUL5UWJTTWGWA2Y.gif Message ID: @. @.> >
yes there are pleinty. It is a one year of hard coding. After installing the tool and selecting a binding, yo uhave the zoo with all the 4500 models in different formats. depending on your pc power you can use small to very large ones.
as of extensions, I call them eprsonalities, you can select one out of the 500 plus personas. They dontain many things that are useful for various tasks. look at data category and you'll find Data Ops pythonista. It is a persona that can process all kinds of data files, mainly excel and csv files. you can ask it to do anything you want from just what is the average of this entry to make a plot or more complex stuff about the data.
If you are interested to learn how it works: https://www.youtube.com/watch?v=v7MJy_2_Mos
And here is an example of what you cna do with tit: https://www.youtube.com/watch?v=xT_hc1nO5Pk
I received an error message while trying to send a message to the AI:
It looks like you we couldn't load the model. Here is the error message: Could not find module 'C:\lolllm\installer_files\lollms_env\Lib\site-packages\ctransformers\lib\cuda\ctransformers.dll' (or one of its dependencies). Try using the full path with constructor syntax.
Van: Saifeddine ALOUI @.> Verzonden: donderdag 7 maart 2024 13:26 Aan: ParisNeo/gpt4pandas @.> CC: svaverbe @.>; Author @.> Onderwerp: Re: [ParisNeo/gpt4pandas] memory requirements ? (Issue #1)
yes there are pleinty. It is a one year of hard coding. After installing the tool and selecting a binding, yo uhave the zoo with all the 4500 models in different formats. depending on your pc power you can use small to very large ones.
as of extensions, I call them eprsonalities, you can select one out of the 500 plus personas. They dontain many things that are useful for various tasks. look at data category and you'll find Data Ops pythonista. It is a persona that can process all kinds of data files, mainly excel and csv files. you can ask it to do anything you want from just what is the average of this entry to make a plot or more complex stuff about the data.
— Reply to this email directly, view it on GitHub https://github.com/ParisNeo/gpt4pandas/issues/1#issuecomment-1983403860 , or unsubscribe https://github.com/notifications/unsubscribe-auth/AF5RR4Y4UOPINKRMVBRJPJ3YXBMGRAVCNFSM6AAAAABEHPV5LGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTSOBTGQYDGOBWGA . You are receiving this because you authored the thread. https://github.com/notifications/beacon/AF5RR4YRY2N4VO62OJR2ECLYXBMGRA5CNFSM6AAAAABEHPV5LGWGG33NNVSW45C7OR4XAZNMJFZXG5LFINXW23LFNZ2KUY3PNVWWK3TUL5UWJTTWHBLVI.gif Message ID: @. @.> >
I tested your python code simple_example.py:
python simple_example.py File already exists in folder llama_model_load: loading model from 'models/ggml-vicuna-13b-4bit-rev1.bin' - please wait ... llama_model_load: n_vocab = 32001 llama_model_load: n_ctx = 512 llama_model_load: n_embd = 5120 llama_model_load: n_mult = 256 llama_model_load: n_head = 40 llama_model_load: n_layer = 40 llama_model_load: n_rot = 128 llama_model_load: f16 = 2 llama_model_load: n_ff = 13824 llama_model_load: n_parts = 2 llama_model_load: type = 2 llama_model_load: ggml map size = 7759.84 MB llama_model_load: ggml ctx size = 101.25 KB llama_model_load: mem required = 9807.93 MB (+ 3216.00 MB per state) llama_model_load: loading tensors from 'models/ggml-vicuna-13b-4bit-rev1.bin' llama_model_load: model size = 7759.40 MB / num tensors = 363 llama_init_from_file: kv self size = 800.00 MB Dataframe Name Age City Salary 0 Alice 25 New York 50000 1 Bob 30 Paris 60000 2 Charlie 35 London 70000 What is the average salary?
But the execution of the script seems to stall, most likely because my laptop runs out of memory. Is there a way to circumvent memory issues ?
dr. Siegfried Vanaverbeke siegfriedvanaverbeke@gmail.com