stories15M / README.md
ngxson's picture
ngxson HF Staff
add README
7ab4245 verified
|
Raw History Blame Contribute Delete
520 Bytes
---
library_name: gguf
tags:
- llama.cpp
- test-model
---
# stories15M
Tiny model used by the [llama.cpp](https://github.com/ggml-org/llama.cpp) test suite and CI. It is **not** meant for real-world use.
Originally hosted at `ggml-org/models/tinyllamas/`.
- `stories15M*.gguf`: [karpathy/tinyllamas](https://huggingface.co/karpathy/tinyllamas) stories15M (F32, Q4_0, Q8_0)
- `stories15M-be*.gguf`: big-endian variants (s390x CI)
- `split/`: the same model split into 3 shards (F32 and Q8_0), for split-loading tests