Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models
Paper
•
2402.14848
•
Published
•
19
•
6
Cognitive Tech
cognitivetech
AI & ML interests
local first: research assistance starting with psychology book summaries
Organizations
cognitivetech's activity
what template are we using?
3
#8 opened 9 months ago
by
cognitivetech
chat template
4
2
#3 opened about 1 year ago
by
cognitivetech
Tokenizer mismatch all the time
2
#47 opened about 1 year ago
by
tian9
[Support] Community Articles
1
83
#5 opened about 1 year ago
by
victor
commented
3
papers
about 1 year ago
mistral 7b instruct v0.2
4
#4 opened about 1 year ago
by
cognitivetech
Model follows ChatML format, but does not have the special tokens for ChatML
24
#3 opened over 1 year ago
by
andysalerno
What is the max. content length of Mistral-7B-Instruct-v0.2?
17
#43 opened over 1 year ago
by
hanshupe
What are the context window (input) and output token limits ?
4
#24 opened over 1 year ago
by
sniffski
can we get this in v0.2?
3
#3 opened over 1 year ago
by
cognitivetech
this version has too much personality compared to v2.0
7
#1 opened over 1 year ago
by
cognitivetech
this version has too much personality compared to v2.0
7
#1 opened over 1 year ago
by
cognitivetech
this version has too much personality compared to v2.0
7
#1 opened over 1 year ago
by
cognitivetech