Michael Royzen PRO
michaelroyzen
AI & ML interests
None yet
Recent Activity
liked
a model
18 days ago
tencent/HunyuanVideo
liked
a model
19 days ago
meta-llama/Llama-3.3-70B-Instruct
liked
a Space
about 1 month ago
black-forest-labs/FLUX.1-dev
Organizations
michaelroyzen's activity
Wizardcoder controversy
19
#2 opened over 1 year ago
by
rombodawg
Issue/Bug replicating HumanEval result
9
#4 opened over 1 year ago
by
emrgnt-cmplxty
Phind-CodeLlama-13b model?
2
#3 opened over 1 year ago
by
rombodawg
I have some proof
1
#1 opened over 1 year ago
by
bhuwansaik
This might be the best coding model (Better than wizardcoder_python_34b)
5
#5 opened over 1 year ago
by
rombodawg
This is an absolute gem! Can't thank you enough.
12
#4 opened over 1 year ago
by
pgalko
Python-only or multi-lingual?
1
#2 opened over 1 year ago
by
andersonbcdefg
True humaneval score or NewHope repeat?
5
#1 opened over 1 year ago
by
rombodawg
instruct-answer format?
2
#1 opened over 1 year ago
by
theblackcat102
Bug: datasets.builder.DatasetGenerationError: An error occurred while generating the dataset
3
#30 opened over 1 year ago
by
michaelroyzen
Flan-T5 tokenizer supports neither Chinese nor many code-related tokens despite being advertised as such
1
#33 opened almost 2 years ago
by
michaelroyzen
Only BF16 Work. FP16 and 8INT generate non-sense for me currently.
9
#9 opened about 2 years ago
by
JulesGM
Activation function config inconsistent
6
#11 opened about 2 years ago
by
michaelroyzen
Activation function config inconsistent
6
#11 opened about 2 years ago
by
michaelroyzen
Activation function config inconsistent
6
#11 opened about 2 years ago
by
michaelroyzen