Fix README
Browse files
README.md
CHANGED
|
@@ -4,9 +4,8 @@ license: apache-2.0
|
|
| 4 |
|
| 5 |
Unofficial GGUF Quantizations of Grok-1. Should just run with llama.cpp once the [PR- Add grok-1 support #6204](https://github.com/ggerganov/llama.cpp/pull/6204) is merged.
|
| 6 |
|
| 7 |
-
You need to merge the GGUF file using `gguf-split` before using them (there's already a PR to change this).
|
| 8 |
The splits now use [PR: llama_model_loader: support multiple split/shard GGUFs](https://github.com/ggerganov/llama.cpp/pull/6187).
|
| 9 |
-
Therefore no merging using `gguf-split` is needed anymore.
|
| 10 |
|
| 11 |
For now only Q2_K Quant, others (Q3_K, Q4_K, Q5_K & Q6_K) are prepared waiting to upload.
|
| 12 |
|
|
|
|
| 4 |
|
| 5 |
Unofficial GGUF Quantizations of Grok-1. Should just run with llama.cpp once the [PR- Add grok-1 support #6204](https://github.com/ggerganov/llama.cpp/pull/6204) is merged.
|
| 6 |
|
|
|
|
| 7 |
The splits now use [PR: llama_model_loader: support multiple split/shard GGUFs](https://github.com/ggerganov/llama.cpp/pull/6187).
|
| 8 |
+
Therefore no merging using `gguf-split` is needed anymore. (hopefully) It's not merged yet so things might change.
|
| 9 |
|
| 10 |
For now only Q2_K Quant, others (Q3_K, Q4_K, Q5_K & Q6_K) are prepared waiting to upload.
|
| 11 |
|