Update README.md
Browse files
README.md
CHANGED
@@ -50,13 +50,13 @@ For the current version GGML files for Selfee 13B, please check [TheBloke/Selfee
|
|
50 |
|
51 |
I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`.
|
52 |
|
53 |
-
|
54 |
|
55 |
### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
|
56 |
|
57 |
-
These new quantisation methods are
|
58 |
|
59 |
-
They
|
60 |
|
61 |
## Explanation of the new k-quant methods
|
62 |
|
|
|
50 |
|
51 |
I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`.
|
52 |
|
53 |
+
These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.
|
54 |
|
55 |
### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
|
56 |
|
57 |
+
These new quantisation methods are compatible with llama.cpp as of June 6th, commit `2d43387`.
|
58 |
|
59 |
+
They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt.
|
60 |
|
61 |
## Explanation of the new k-quant methods
|
62 |
|