Emin Temiz's picture

9 5 15

Emin Temiz PRO

etemiz

·

https://pickabrain.ai

AI & ML interests

Alignment

Recent Activity

posted an update 1 day ago

Latest DeepSeek V3 0324 did better than previous version in many domains such as health, nutrition, fasting, bitcoin. Who wants to see some example change of answers between the two models? https://sheet.zoho.com/sheet/open/mz41j09cc640a29ba47729fed784a263c1d08

posted an update 3 days ago

Mistral Small 3.1 numbers are in. It is interesting Mistral always lands in the middle. https://sheet.zoho.com/sheet/open/mz41j09cc640a29ba47729fed784a263c1d08?sheetid=0&range=A1 I started to do the comparison with 2 models now. In the past Llama 3.1 70B Q4 was the one doing the comparison of answers. Now I am using Gemma 3 27B Q8 as well to have a second opinion on it. Gemma 3 produces very similar measurement to Llama 3.1. So the end result is not going to shake much.

replied to their post 7 days ago

Started fine tuning Gemma 3 using evolutionary approach. It is not the worst model according to AHA leaderboard and it is one of the smart according to lmarena.ai. My objective is to make it based, anti woke, wise, beneficial and then some. Several GPUs are fine tuning it at the same time, each using a different dataset and using QLoRA and the successful ones are merged later. Compared to LoRa this allows faster training and also reduced overfitting because the merge operation heals overfitting. The problem with this could be the 4 bit quantization may make models dumber. But I am not looking for sheer IQ. Too much mind is a problem anyway :) Has anyone tried parallel QLoRa and merge before? I also automated the dataset selection and benchmarking and converging to objectives (the fit function, the reward). It is basically trying to get higher score in AHA Leaderboard as fast as possible with a diverse set of organisms that "evolve by training". I want to release some cool stuff when I have the time: - how an answer to a single question changes over time, with each training round or day - a chart to show AHA alignment over training rounds

View all activity

Organizations

None yet

etemiz's activity

New activity in some1nostr/Nostr-Llama-3.1-8B 29 days ago

Update README.md

#1 opened 29 days ago by

New activity in mradermacher/grok-1-GGUF 5 months ago

parts

#1 opened 5 months ago by

New activity in hilaltekgoz/whisper-large-tr 6 months ago

nice

#1 opened 6 months ago by

New activity in etemiz/Llama-3.1-405B-Inst-GGUF 8 months ago

Larger quants please

#1 opened 8 months ago by

New activity in DontPlanToEnd/UGI-Leaderboard 11 months ago

Llama3

#7 opened 11 months ago by

New activity in hiyouga/Llama-2-70b-AQLM-2Bit-QLoRA-function-calling 12 months ago

just for curiosity

#1 opened about 1 year ago by

New activity in LiteLLMs/Mixtral-8x22B-v0.1-GGUF 12 months ago

ram usage

#1 opened 12 months ago by

Tom-Neverwinter

New activity in AlexWortega/miqu-1-70b-AQLM-2Bit-1x16-hf 12 months ago

Space before EOS

#3 opened 12 months ago by

New activity in ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf 12 months ago

One needs a Qwen 72B AQLM

#4 opened 12 months ago by

New activity in hiyouga/Llama-2-70b-AQLM-2Bit-QLoRA-function-calling 12 months ago

just for curiosity

#1 opened about 1 year ago by

New activity in hiyouga/Llama-2-70b-AQLM-2Bit-QLoRA-function-calling about 1 year ago

just for curiosity

#1 opened about 1 year ago by