Vojtech Cekal's picture

26 18

Vojtech Cekal

cekal

·

vojtechcekal

AI & ML interests

In love with machine learning.

Recent Activity

new activity about 1 month ago

microsoft/OmniParser-v2.0:Error when running with transformers.

liked a dataset about 2 months ago

allenai/WildChat

liked a dataset about 2 months ago

P1ayer-1/chatgpt-conversations-chatlogs.net

View all activity

Organizations

cekal's activity

New activity in microsoft/OmniParser-v2.0 about 1 month ago

Error when running with transformers.

#2 opened about 1 month ago by

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 about 1 year ago

Different answer after each request

#130 opened about 1 year ago by

New activity in mistralai/Mistral-7B-v0.1 about 1 year ago

Mistral 7B produces different results when we hit via postman api

#124 opened about 1 year ago by

New activity in 152334H/miqu-1-70b-sf about 1 year ago

Discussion Thread - Let's Get To Know the (Allegedly) Leaked "mistral-medium" better!

#4 opened about 1 year ago by

New activity in microsoft/phi-2 about 1 year ago

How to fine-tune this? + Training code

#19 opened over 1 year ago by

Responses by phi-2 are off, it's depressed and insults me for no reason whatsover?

#61 opened about 1 year ago by

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 about 1 year ago

How to use system prompt?

#69 opened about 1 year ago by

Is there any simple way to solve the problem of redundant output

#68 opened about 1 year ago by

How many GPUs do we need to run this out of box?

#63 opened about 1 year ago by

New activity in mistralai/Mixtral-8x7B-v0.1 over 1 year ago

WARNING:root:Some parameters are on the meta device device because they were offloaded to the cpu.

#25 opened over 1 year ago by

New activity in cognitivecomputations/dolphin-2.5-mixtral-8x7b over 1 year ago

FINE TUNING with PEFT MIXTRAL

#17 opened over 1 year ago by

New activity in mistralai/Mistral-7B-v0.1 over 1 year ago

PEFT based Fine Tuned model hallucinates values from the fine tuning training data while inferencing.

#111 opened over 1 year ago by

New activity in mistralai/Mixtral-8x7B-v0.1 over 1 year ago

Delete model-00010-of-00019.safetensors

#21 opened over 1 year ago by

New activity in jan-hq/trinity-v1 over 1 year ago

Freaking outstanding! GPT-4 confirms

#1 opened over 1 year ago by

New activity in mistralai/Mixtral-8x7B-v0.1 over 1 year ago

bonjour

#20 opened over 1 year ago by

New activity in cekal/mpt-7b-peft-compatible almost 2 years ago

PEFT Finetuning Code Please

#3 opened almost 2 years ago by

New activity in tiiuae/falcon-7b almost 2 years ago

Support for LoRA?

#3 opened almost 2 years ago by

New activity in project-baize/baize-v2-7b almost 2 years ago

Which dataset was used to train this model?

#1 opened almost 2 years ago by

New activity in tiiuae/falcon-7b almost 2 years ago

Hallucinates too much

#6 opened almost 2 years ago by

New activity in cekal/mpt-7b-peft-compatible almost 2 years ago

Customize README

#1 opened almost 2 years ago by