Anthony's picture

11

Anthony

depasquale

AI & ML interests

None yet

Recent Activity

new activity 9 days ago

meta-llama/Llama-3.1-8B-Instruct:Improve chat template for function calling

new activity 9 days ago

meta-llama/Llama-3.1-8B-Instruct:new tokenizer contains the cutoff date and today date by default

new activity 9 days ago

mlx-community/Qwen2.5-1.5B-Instruct-4bit:Fix chat template

View all activity

Organizations

depasquale's activity

New activity in meta-llama/Llama-3.1-8B-Instruct 9 days ago

Improve chat template for function calling

#170 opened 9 days ago by

new tokenizer contains the cutoff date and today date by default

#74 opened 5 months ago by

New activity in mlx-community/Qwen2.5-1.5B-Instruct-4bit 9 days ago

Fix chat template

#2 opened 9 days ago by

New activity in mlx-community/Phi-3-mini-128k-instruct-8bit 6 months ago

Update model

#1 opened 6 months ago by

New activity in mlx-community/Phi-3-mini-128k-instruct-4bit 6 months ago

Update model

#3 opened 6 months ago by

New activity in mlx-community/Phi-3-mini-4k-instruct-8bit 6 months ago

Update model

#1 opened 6 months ago by

New activity in mlx-community/Phi-3-mini-4k-instruct-4bit 6 months ago

Update model

#1 opened 6 months ago by

New activity in mlx-community/Phi-3-mini-4k-instruct-4bit-no-q-embed 6 months ago

Fix EOS token

#3 opened 8 months ago by

New activity in mlx-community/Phi-3-medium-4k-instruct-4bit 8 months ago

ValueError: Shapes (1,10,13,256) and (1,10,13,128) cannot be broadcast.

#2 opened 8 months ago by

New activity in mlx-community/Llama-3-8B-Instruct-262k-2bit 8 months ago

Model doesn't produce useful output

#2 opened 8 months ago by

Unsupported PostProcessor type: Sequence

#1 opened 8 months ago by