|
--- |
|
license: mit |
|
tags: |
|
- ollama |
|
--- |
|
|
|
Convert and Quantized of [TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T/tree/main) using llama.cpp |
|
|
|
## Guide to replicate |
|
[Convert and Quantize model to GGUF](https://medium.com/@sarinsuriyakoon/convert-pytorch-model-to-quantize-gguf-to-run-on-ollama-5c5dbc458208) |
|
|
|
## Description |
|
|
|
This is for my own experiment with Ollama, because Ollama usually put chat fine-tuning in their library. It would be hard to know if my fine-tuning LoRA Adapter works if I don't use base/pretrain model version |
|
|
|
## Ollama |
|
- Model Page https://ollama.com/pacozaa/tinyllama |
|
- `ollama run pacozaa/tinyllama` |
