anfedoro/bge-m3-mlx-fp16
0.6B • Updated • 301
Andrei Fedorov
anfedoro
AI & ML interests
AI & ML enthusiast
Recent Activity
updated a model 21 days ago
anfedoro/bge-m3-mlx-fp16 published a model 21 days ago
anfedoro/bge-m3-mlx-fp16 new activity 22 days ago
mlx-community/bge-m3-mlx-8bit:Add missing BGE-M3 sparse and ColBERT projection weightsOrganizations
None yet
updated a
model 21 days ago
published a
model 21 days ago
Add missing BGE-M3 sparse and ColBERT projection weights
#1 opened 22 days ago
by anfedoro
commented on Unbelievable! Run 70B LLM Inference on a Single 4GB GPU with This NEW Technique 27 days ago
Really ? explain
amazing work!
commented on Unbelievable! Run 70B LLM Inference on a Single 4GB GPU with This NEW Technique 27 days ago
amazing work!
Really ? explain. What exactly is amazing ?
commented on Unbelievable! Run 70B LLM Inference on a Single 4GB GPU with This NEW Technique 27 days ago
what exactly is interesting ? Do you understand that this have no any practical application at all?
Did they share any tps figures ? No? why ? Because they are ridiculous there is no possibility to gain even couple of tokens per second with tiny context size... How you suppose to use this shit ?
commented on Unbelievable! Run 70B LLM Inference on a Single 4GB GPU with This NEW Technique 27 days ago
Stop posting impractical bullshit!!!
liked a
model over 1 year ago
