Vojtech Cekal's picture

Building on HF

22 15

Vojtech Cekal

cekal

·

https://vojtechcekal.com

vojtechcekal

AI & ML interests

None yet

Recent Activity

liked a model 11 days ago

zai-org/GLM-OCR

liked a model 15 days ago

PaddlePaddle/PaddleOCR-VL-1.5

liked a model 15 days ago

Qwen/Qwen3-VL-8B-Instruct

View all activity

Organizations

None yet

New activity in microsoft/OmniParser-v2.0 12 months ago

Error when running with transformers.

#2 opened 12 months ago by

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 about 2 years ago

Different answer after each request

#130 opened about 2 years ago by

New activity in mistralai/Mistral-7B-v0.1 about 2 years ago

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

#124 opened about 2 years ago by

New activity in 152334H/miqu-1-70b-sf about 2 years ago

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

#4 opened about 2 years ago by

New activity in microsoft/phi-2 about 2 years ago

How to fine-tune this? + Training code

#19 opened about 2 years ago by

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

#61 opened about 2 years ago by

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 about 2 years ago

How to use system prompt?

#69 opened about 2 years ago by

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

#68 opened about 2 years ago by

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

#63 opened about 2 years ago by

New activity in mistralai/Mixtral-8x7B-v0.1 about 2 years ago

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

#25 opened about 2 years ago by deleted

New activity in dphn/dolphin-2.5-mixtral-8x7b about 2 years ago

FINE TUNING with PEFT MIXTRAL

#17 opened about 2 years ago by

New activity in mistralai/Mistral-7B-v0.1 about 2 years ago

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

#111 opened about 2 years ago by

New activity in mistralai/Mixtral-8x7B-v0.1 about 2 years ago

Delete model-00010-of-00019.safetensors

#21 opened about 2 years ago by

New activity in jan-hq/trinity-v1 about 2 years ago

Freaking outstanding! GPT-4 confirms

#1 opened about 2 years ago by

New activity in mistralai/Mixtral-8x7B-v0.1 about 2 years ago

bonjour

#20 opened about 2 years ago by

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

Support for LoRA?

#3 opened over 2 years ago by

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

Which dataset was used to train this model?

#1 opened over 2 years ago by

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

Hallucinates too much

#6 opened over 2 years ago by

Support for LoRA?

#3 opened over 2 years ago by