rdsm's picture

5 1 3

rdsm

rdsm

·

regismesquita

AI & ML interests

None yet

Recent Activity

new activity about 14 hours ago

Qwen/QwQ-32B:Does Macbook M1 max 64GB run this model well?

new activity about 20 hours ago

mlx-community/Kokoro-82M-4bit:Update README.md

replied to csabakecskemeti's post 13 days ago

Testing Training on AMD/ROCm the first time! I've got my hands on an AMD Instinct MI100. It's about the same price used as a V100 but on paper has more TOPS (V100 14TOPS vs MI100 23TOPS) also the HBM has faster clock so the memory bandwidth is 1.2TB/s. For quantized inference it's a beast (MI50 was also surprisingly fast) For LORA training with this quick test I could not make the bnb config works so I'm running the FT on the fill size model. Will share all the install, setup and setting I've learned in a blog post, together with the cooling shroud 3D design.

View all activity

Organizations

None yet

rdsm's activity

New activity in Qwen/QwQ-32B about 14 hours ago

Does Macbook M1 max 64GB run this model well?

#44 opened 3 days ago by

New activity in mlx-community/Kokoro-82M-4bit about 20 hours ago

Update README.md

#2 opened about 20 hours ago by

New activity in gaia-benchmark/leaderboard 16 days ago

Unable to Load GAIA benchmark leaderboard

#31 opened 17 days ago by

New activity in mlx-community/Mistral-Small-24B-Instruct-2501-8bit about 1 month ago

Tool Calling

#1 opened about 1 month ago by

New activity in mlx-community/Mistral-Small-24B-Instruct-2501-4bit about 1 month ago

No tool calling

#2 opened about 1 month ago by