Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,8 @@ Including the original LLaMA 3 models file cloning from the Meta HF repo. (https
|
|
| 13 |
|
| 14 |
If you have issues downloading the models from Meta or converting models for `llama.cpp`, feel free to download this one!
|
| 15 |
|
|
|
|
|
|
|
| 16 |
## Perplexity table on LLaMA 3 70B
|
| 17 |
|
| 18 |
Less perplexity is better. (credit to: [dranger003](https://github.com/ggerganov/llama.cpp/pull/6745#issuecomment-2093892514))
|
|
|
|
| 13 |
|
| 14 |
If you have issues downloading the models from Meta or converting models for `llama.cpp`, feel free to download this one!
|
| 15 |
|
| 16 |
+
### How to use the `gguf-split` / Model sharding demo : https://github.com/ggerganov/llama.cpp/discussions/6404
|
| 17 |
+
|
| 18 |
## Perplexity table on LLaMA 3 70B
|
| 19 |
|
| 20 |
Less perplexity is better. (credit to: [dranger003](https://github.com/ggerganov/llama.cpp/pull/6745#issuecomment-2093892514))
|