MDL
starcoder2-3b
bigcode
Parameters
3B
Downloads
124.6K
on HF
Likes
220
Avg score
—
Weights
Open
Released
Nov 29, 2023
About
starcoder2-3b is a 3B-parameter open-weights model in the starcoder2 family from bigcode.
bigcode-openrail-mtext-generation
Benchmark scores · 0
No benchmark scores yet.
The research behind this model
all papers mentioning it →GQA: Training Generalized Multi-Query Transformer Models from Multi-Head CheckpointsFlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessLongformer: The Long-Document TransformerEfficient Training of Language Models to Fill in the MiddleStarCoder 2 and The Stack v2: The Next Generation
Details
Publisherbigcode
Familystarcoder2
Parameters3B
Licensebigcode-openrail-m
WeightsOpen
ReleasedNov 29, 2023