NIkita Balakin's picture

NIkita Balakin

Kotokin

·

AI & ML interests

None yet

Recent Activity

reacted to csabakecskemeti's post with 👍 9 days ago

-UPDATED- 4bit inference is working! The blogpost is updated with code snippet and requirements.txt https://devquasar.com/uncategorized/all-about-amd-and-rocm/ -UPDATED- I've played around with an MI100 and ROCm and collected my experience in a blogpost: https://devquasar.com/uncategorized/all-about-amd-and-rocm/ Unfortunately I've could not make inference or training work with model loaded in 8bit or use BnB, but did everything else and documented my findings.

replied to csabakecskemeti's post 9 days ago

-UPDATED- 4bit inference is working! The blogpost is updated with code snippet and requirements.txt https://devquasar.com/uncategorized/all-about-amd-and-rocm/ -UPDATED- I've played around with an MI100 and ROCm and collected my experience in a blogpost: https://devquasar.com/uncategorized/all-about-amd-and-rocm/ Unfortunately I've could not make inference or training work with model loaded in 8bit or use BnB, but did everything else and documented my findings.

liked a model 17 days ago

featherless-ai/Qwerky-72B-Preview

View all activity

Organizations

None yet

Kotokin's activity

New activity in ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.3 4 months ago

The question of training the model.

#2 opened 4 months ago by

New activity in MikeRoz/mistralai_Mistral-Large-Instruct-2411-3.0bpw-h6-exl2 4 months ago

Request for a 3.5 bpw

#1 opened 4 months ago by

New activity in mistralai/Mistral-Large-Instruct-2411 4 months ago

Where config.json?

#1 opened 4 months ago by

New activity in FluffyKaeloky/Luminum-v0.1-123B 5 months ago

Release behemoth.

#4 opened 5 months ago by

New activity in sophosympatheia/New-Dawn-Llama-3.1-70B-v1.1 7 months ago

Exl2

#2 opened 7 months ago by

New activity in anthracite-org/magnum-v2-32b 7 months ago

question about the next model

#1 opened 7 months ago by

New activity in sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0 8 months ago

The question is about the next model.

#8 opened 8 months ago by

New activity in ParasiticRogue/Merged-RP-Stew-V2-34B 11 months ago

frankenmerge

#4 opened 11 months ago by

New activity in LoneStriker/M7-7b-8.0bpw-h8-exl2 11 months ago

A request for quantization.

#1 opened 11 months ago by

New activity in sophosympatheia/Midnight-Miqu-70B-v1.5 12 months ago

Quants

#2 opened 12 months ago by

New activity in sophosympatheia/Midnight-Miqu-70B-v1.0 about 1 year ago

Hi, I made gptq quant.

#3 opened about 1 year ago by

New activity in NexesQuants/Senku-70b-iMat.GGUF about 1 year ago

A request for quantization.

#1 opened about 1 year ago by

New activity in Artefact2/Cat-8x7B-GGUF about 1 year ago

A request for quantization.

#1 opened about 1 year ago by

New activity in wolfram/miquliz-120b-v2.0-GGUF about 1 year ago

iMatrix, IQ2_XS & IQ2_XXS

#2 opened about 1 year ago by

New activity in dranger003/Senku-70B-iMat.GGUF about 1 year ago

A request for quantization.

#1 opened about 1 year ago by

New activity in KnutJaegersberg/2-bit-LLMs about 1 year ago

Hi, could you please add miquliz-120b?

#4 opened about 1 year ago by

New activity in sophosympatheia/Midnight-Rose-70B-v2.0.3 about 1 year ago

quantize to 4bit

#2 opened about 1 year ago by

New activity in Kooten/MiquMaid-v1-70B-3bpw-exl2 about 1 year ago

More quant?

#1 opened about 1 year ago by

New activity in Kotokin/Mistral-7B-NSFWSTORY-lora about 1 year ago

A problem with this lore

#1 opened about 1 year ago by

New activity in sophosympatheia/Rogue-Rose-103b-v0.2 about 1 year ago

Context expansion

#6 opened about 1 year ago by