ggml-org/models-moved

stories15M : revert training context to 128

stories15M : bump training context to 256

gguf : bump training context from 256 to 2048

gguf : bump training context from 128 to 256

Upload 3 files

Upload stories260K-be.gguf

Upload mel_filters.npz

Update README.md

Add small split model

Upload stories260K-infill.gguf

models : add tiny jina reranker for CI pruposes

models : remove grok-1 and mixtral

Create README.md

Add phi-2 f16

Add grok-1 Q4_0 shards

models : add mistral 7B v0.2 iq3_0

Add split stories15M

models : add bert big-endian

models : add mixtral iq3_s

models : add bert

tinyllamas : add 260K model

models : add tinyllamas

Upload yolov3-tiny.weights

yolo : add sample image

Upload ggml-model-f16.gguf

.gitignore

Upload ggml-model-q8_0.gguf

phi-2 : move to folder

Upload ggml-model-q4_0.gguf

initial commit