phi4 / README.md
calcuis's picture
Update README.md
e5a5393 verified
|
raw
history blame
586 Bytes
---
license: mit
language:
- en
base_model:
- microsoft/phi-4-gguf
pipeline_tag: text-generation
tags:
- phi4
- gguf-connector
---
# gguf quantized and bug fixed version of phi4
## review
- bug fixed for: "ResponseError: llama runner process has terminated: GGML_ASSERT(hparams.n_swa > 0) failed"
- tq1_0 and tq2_0 are not usable; seems at least should start with q2_k
### how to run it
use any connector for interacting with gguf; i.e., [gguf-connector](https://pypi.org/project/gguf-connector/)
## reference
- base model: microsoft/[phi-4](https://huggingface.co/microsoft/phi-4)