Hugging Face's logo
Mike Cooper-Stachowsky's picture
18

Mike Cooper-Stachowsky

mstachow
·

AI & ML interests

None yet

Recent Activity

New activity about 2 months ago
microsoft/Phi-3.5-MoE-instruct:Model consistently gets into a loop to repeat itself if there is too much in the context window
View all activity

Organizations

University of Waterloo Virtual TA Group's profile picture

mstachow's activity

New activity in microsoft/Phi-3.5-MoE-instruct about 2 months ago

Model consistently gets into a loop to repeat itself if there is too much in the context window

2
#48 opened about 2 months ago by mstachow
New activity in OpenGVLab/InternVL2-40B 3 months ago

Mutilple gpu err

4
#9 opened 3 months ago by Toukesu
New activity in yifeihu/TFT-ID-1.0 4 months ago

What counts as "text"?

2
#1 opened 4 months ago by mstachow
New activity in OpenGVLab/InternVL2-40B 4 months ago

What is the significance of the parameters input_size of max_num?

5
#6 opened 4 months ago by mstachow
New activity in meta-llama/Prompt-Guard-86M 4 months ago

Model is extremely sensitive to the word "ignore"

4
#14 opened 4 months ago by mstachow
New activity in fmops/distilbert-prompt-injection 4 months ago

What is the context length of this model?

1
#2 opened 4 months ago by mstachow
updated a model 6 months ago
New activity in galatolo/cerbero-7b-openchat 7 months ago

Model keeps adding new input, even when using pipeline?

2
#1 opened 7 months ago by mstachow
New activity in TheBloke/sqlcoder-GPTQ about 1 year ago

It is not making use of my GPU.

1
#1 opened about 1 year ago by JeisonJimenez
New activity in TheBloke/openchat_3.5-16k-GPTQ about 1 year ago

Deeply confused about how this is running on my system - is it GPU or CPU?
#1 opened about 1 year ago by mstachow
New activity in facebook/mms-tts-eng about 1 year ago

Special tokens to control pausing?

3
#3 opened about 1 year ago by mstachow

What is the maximum token length of the model?

1
#2 opened about 1 year ago by mstachow
New activity in suno/bark about 1 year ago

Possibility to use on CUDA?

10
#12 opened over 1 year ago by mstachow
New activity in TheBloke/Llama-2-70B-Chat-GPTQ over 1 year ago

Out of memory error, but both system and GPU have plenty of memory

5
#37 opened over 1 year ago by mstachow
New activity in microsoft/speecht5_tts over 1 year ago

A note on preventing model hallucinations
#18 opened over 1 year ago by mstachow
New activity in suno/bark over 1 year ago

Model hallucinates almost every run

3
#15 opened over 1 year ago by mstachow
New activity in microsoft/speecht5_tts over 1 year ago

Working Hacky Code

2
#16 opened over 1 year ago by JHenzi

model sometimes repeats itself and glitches during speech.

1
#13 opened over 1 year ago by mstachow
New activity in declare-lab/flan-alpaca-gpt4-xl over 1 year ago

What does "recommended for better performance" mean?

2
#1 opened over 1 year ago by mstachow

What does "recommended for better performance" mean?

2
#1 opened over 1 year ago by mstachow