Update README.md

README.md

@@ -10,9 +10,19 @@ datasets:
 - EleutherAI/the_pile_deduplicated
 ---
 
+# Pythia Deduped Series GGML
 ### This repository contains quantized conversions of EleutherAI's Pythia Deduped checkpoints.
+*For use with frontends that support GGML quantized GPT-NeoX models, such as KoboldCpp and Oobabooga (with the CTransformers loader).*
+
+*Last updated on 2023-05-25.*
+
+For other versions of the models, see here:
+- [GGMLv1 q4_3](https://huggingface.co/Crataco/Pythia-Deduped-Series-GGML/tree/a695a4c30c01ed9a41200c01f85d47c819fc93dd/2023-04-20) (70M to 12B)
+- [GGMLv1 q5_0 / q5_1 / q8_0](https://huggingface.co/Crataco/Pythia-Deduped-Series-GGML/tree/a695a4c30c01ed9a41200c01f85d47c819fc93dd/2023-04-30) (70M to 2.8B)
+- [GGMLv1 q4_0 / q4_2](https://huggingface.co/Crataco/Pythia-Deduped-Series-GGML/tree/a695a4c30c01ed9a41200c01f85d47c819fc93dd/2023-05-06) (70M to 2.8B)
+- [GGMLv2 q4_0 / q5_1](https://huggingface.co/Crataco/Pythia-Deduped-Series-GGML/tree/a695a4c30c01ed9a41200c01f85d47c819fc93dd/2023-05-15) (70M to 2.8B)
+- [GGMLv3 q4_0 / q5_1](https://huggingface.co/Crataco/Pythia-Deduped-Series-GGML/tree/main)
 
-[Click here if you're looking for ggmlv1 and ggmlv2 models.](https://huggingface.co/Merry/ggml-pythia-deduped/tree/a695a4c30c01ed9a41200c01f85d47c819fc93dd).
 
 # RAM USAGE
 Model | RAM usage
@@ -33,15 +43,4 @@ ggmlv3-pythia-1b-deduped-q5_1.bin | 943.9 MiB
 ggmlv3-pythia-1.4b-deduped-q5_1.bin | 1.3 GiB
 ggmlv3-pythia-2.8b-deduped-q5_1.bin | 2.3 GiB
 
-*Tested on KoboldCpp with OpenBLAS enabled.*
-**Notes:**
-- The models have been converted with ggerganov/ggml's gpt-neox conversion script, and tested only on KoboldCpp. Other frontends that support GGML-based conversions of GPT-NeoX *should* work, but I can't promise anything.
-- They're sorted by date based on when they were converted so it was easier to track breaking changes. If you're just starting off I highly recommend the latest, which is currently 2023-05-25. Combined with KoboldCpp v1.25.1+ this improved the tokenizer, which in my testing reduces occurrences of broken words like "Alicae" or "Reimu Hai-ku-rei".
-
-# ALTERNATIVES
-If you're here because you want a smaller model to run on a device with constrained memory, consider the following, most (if not all) of which have GGML conversions available:
-- [**RedPajama-INCITE**](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-3B-v1) (3B, 7B), using the GPT-NeoX architecture
-- [**OpenLLaMA**](https://huggingface.co/openlm-research/open_llama_3b_600bt_preview) (3B, 7B), using the LLaMA architecture
-- [**MPT-1b-RedPajama-200b**](https://huggingface.co/mosaicml/mpt-1b-redpajama-200b) (1B), using the MPT architecture
-- [**RWKV-4 PilePlus**](https://huggingface.co/BlinkDL/rwkv-4-pileplus) (169M, 430M, 1.5B, 3B), using the RWKV architecture
-- [**GPT-2**](https://huggingface.co/gpt2-xl) (124M, 355M, 774M, 1.5B), using the GPT-2 architecture
+*Tested on KoboldCpp with OpenBLAS enabled.*