StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.
3b
7b
15b
582.3K Pulls Updated 3 months ago
Updated 3 months ago
3 months ago
cad9bff49536 · 13GB
model
archstarcoder2
·
parameters16B
·
quantizationQ6_K
13GB
params
{
"stop": [
"<file_sep>",
"<|end_of_text|>"
]
}
41B
template
<file_sep>
{{- if .Suffix }}<fim_prefix>
{{ .Prompt }}<fim_suffix>{{ .Suffix }}<fim_middle>
{{- else
142B
license
BigCode Open RAIL-M v1 License Agreement
Section I: Preamble
This OpenRAIL-M License Agreement was
13kB
Readme
Supporting a context window of up to 16,384 tokens, StarCoder2 is the next generation of transparently trained open code LLMs.
starcoder2:instruct: a 15B model that follows natural and human-written instructionsstarcoder2:15bwas trained on 600+ programming languages and 4+ trillion tokens.starcoder2:7bwas trained on 17 programming languages and 3.5+ trillion tokens.starcoder2:3bwas trained on 17 programming languages and 3+ trillion tokens.
StarCoder2-15B is the best in its size class and matches 33B+ models on many evaluations. StarCoder2-3B matches the performance of StarCoder1-15B.