Sam Paech PRO
sam-paech
AI & ML interests
Emotional intelligence, alignment, benchmarking
Recent Activity
upvoted
a
paper
16 days ago
EQ-Bench: An Emotional Intelligence Benchmark for Large Language Models
published
a dataset
21 days ago
sam-paech/gutenbergs_1_2_3_4-antislop-dpo
new activity
23 days ago
sam-paech/Darkest-muse-v1:Gemma 3 darkest muse?
Organizations
sam-paech's activity
Gemma 3 darkest muse?
1
3
#9 opened 23 days ago
by
Mispu
Image input
3
#8 opened about 2 months ago
by
mvsoom
Good settings for this model?
1
#5 opened 2 months ago
by
ElvisM
Best model so far (not just in the 9b category)
1
#6 opened 2 months ago
by
RickyRickC137
Review
1
1
#4 opened 4 months ago
by
Ardvark123

Love this model but I wish the context was higher
4
#3 opened 6 months ago
by
HannaLovvold
GSM8K results replication
1
2
#9 opened 6 months ago
by
sam-paech

This is very strong in slop and purple pose, I feel.
3
#2 opened 6 months ago
by
UniversalLove333
system prompt gemma2?
1
#1 opened 6 months ago
by
rwfrs
This model is exactly what I've been looking for!
1
#1 opened 6 months ago
by
PinkMoth

sam-paech/Delirium-v1
5
#391 opened 7 months ago
by
sam-paech


New activity in
sam-paech/gutenberg3-generalfiction-scifi-fantasy-romance-adventure-dpo
7 months ago
[bot] Conversion to Parquet
#1 opened 7 months ago
by
parquet-converter

Librarian Bot: Add language metadata for dataset
#2 opened 7 months ago
by
librarian-bot

tokenizer.model
4
#1 opened 7 months ago
by
mradermacher
WAR ON MINISTRATIONS
11
12
#1 opened about 1 year ago
by
TheDrummer

Hallucinations, misspellings etc. Something seems broken?
21
#10 opened 11 months ago
by
sam-paech

Running MMLU-Pro with Eleuther LM-Eval
2
#814 opened 10 months ago
by
sam-paech

EQ-Bench score
12
#8 opened over 1 year ago
by
sam-paech

Prompt format
6
#4 opened about 1 year ago
by
sam-paech

Regarding Concerns about MMLU Scores
71
#5 opened about 1 year ago
by
deleted