readme

2026-06-27 16:14:08 +08:00 · 2023-04-22 00:27:30 +00:00
parent 830c8f2605
commit d149f12704
1 changed files with 2 additions and 0 deletions
@@ -12,12 +12,14 @@ How do we do this?
    - [llama.cpp/convert-pth-to-ggml.py](https://github.com/ggerganov/llama.cpp/blob/master/convert-gptq-to-ggml.py)


+
 # TODO

 - [x] lora -> hf
    - [ ] test this
 - [ ] hf -> 4bit
 - [ ] 4bit to -> ggml
+- [ ] test perplexity on llama and alpaca type prompts too! maybe use eluther evals

 # setup env