Chris Constant PRO
croqaz
AI & ML interests
Vintage LLMs
Recent Activity
updated a collection 1 day ago
Vintage-LLMs-list updated a collection 1 day ago
Vintage-LLMs-list updated a collection 1 day ago
Vintage-LLMs-listOrganizations
Remove ---- .... === ### dupes from datasets and tokenizer
๐ 1
4
#3 opened 21 days ago
by
foss22
Agentic 0,07 B LM tasks + complete list of use-cases for Vintage LMs
3
#3 opened 13 days ago
by
foss22
ร |ฤฏ|ร|ยง|ยฉ
1
#7 opened 16 days ago
by
foss22
Collect test inference or no value of collecting?
6
#1 opened 18 days ago
by
foss22
29 of 798 Wikipedia 1900-1990s neologisms
5
#1 opened 29 days ago
by
foss22
Questions in 454k vs 783k without questions
1
#5 opened 21 days ago
by
foss22
Extrapolation of 760 achievable steps/hour findins to 75k-steps based on what?
2
#1 opened 22 days ago
by
foss22
F16 NaN in 10 steps workaround
1
#2 opened 21 days ago
by
foss22
Over-filtering problem with current banned.txt
1
#2 opened 21 days ago
by
foss22
Under-filtering.
1
#3 opened 21 days ago
by
foss22
Redundancy
1
#4 opened 21 days ago
by
foss22
Per-profession vocab
๐ 1
6
#4 opened 22 days ago
by
foss22
[bot] Conversion to Parquet
#1 opened 26 days ago
by
parquet-converter
Collocations (easy, the same method) + extra mile: Idioms (hard, invent methods)
4
#3 opened 27 days ago
by
foss22
Rare Surnames/Topo-Gydronyms filtered out by 10,000,000 most frequent words
3
#2 opened 28 days ago
by
foss22
Why Casanova dominates?
2
#2 opened 28 days ago
by
foss22
Extracted with which code?
2
#1 opened 28 days ago
by
foss22
Training recipe
โค๏ธ 1
1
#2 opened about 1 month ago
by
croqaz
Documenting what each GGUF file does
๐ 10
2
#10 opened about 2 months ago
by
croqaz