Commit
•
8f07cf5
1
Parent(s):
e699473
Update README.md
Browse files
README.md
CHANGED
|
@@ -21,8 +21,8 @@ This repo contains GGUF format model files for [yentinglin/Llama-3-Taiwan-70B-In
|
|
| 21 |
| [llama-3-taiwan-70b-instruct-q4_k_m.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-70B-Instruct-GGUF/blob/main/llama-3-taiwan-70b-instruct-q4_k_m.gguf) | Q4_K_M | 4 | 42.5 GB|
|
| 22 |
| [llama-3-taiwan-70b-instruct-q5_k_s.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-70B-Instruct-GGUF/blob/main/llama-3-taiwan-70b-instruct-q5_k_s.gguf) | Q5_K_S | 5 | 48.7 GB|
|
| 23 |
| [llama-3-taiwan-70b-instruct-q5_k_m.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-70B-Instruct-GGUF/blob/main/llama-3-taiwan-70b-instruct-q5_k_m.gguf) | Q5_K_M | 5 | 49.9 GB|
|
| 24 |
-
| [llama-3-taiwan-70b-instruct-q6_k.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-70B-Instruct-GGUF/blob/main/llama-3-taiwan-70b-instruct-q6_k.gguf) | Q6_K | 6 | 59.89 GB|
|
| 25 |
-
| [llama-3-taiwan-70b-instruct-q8_0.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-70B-Instruct-GGUF/blob/main/llama-3-taiwan-70b-instruct-q8_0.gguf) | Q8_0 | 8 | 75 GB|
|
| 26 |
|
| 27 |
## Original model card
|
| 28 |
|
|
|
|
| 21 |
| [llama-3-taiwan-70b-instruct-q4_k_m.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-70B-Instruct-GGUF/blob/main/llama-3-taiwan-70b-instruct-q4_k_m.gguf) | Q4_K_M | 4 | 42.5 GB|
|
| 22 |
| [llama-3-taiwan-70b-instruct-q5_k_s.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-70B-Instruct-GGUF/blob/main/llama-3-taiwan-70b-instruct-q5_k_s.gguf) | Q5_K_S | 5 | 48.7 GB|
|
| 23 |
| [llama-3-taiwan-70b-instruct-q5_k_m.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-70B-Instruct-GGUF/blob/main/llama-3-taiwan-70b-instruct-q5_k_m.gguf) | Q5_K_M | 5 | 49.9 GB|
|
| 24 |
+
| [llama-3-taiwan-70b-instruct-q6_k.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-70B-Instruct-GGUF/blob/main/llama-3-taiwan-70b-instruct-q6_k-00001-of-00002.gguf) | Q6_K | 6 | 59.89 GB|
|
| 25 |
+
| [llama-3-taiwan-70b-instruct-q8_0.gguf](https://huggingface.co/chienweichang/Llama-3-Taiwan-70B-Instruct-GGUF/blob/main/llama-3-taiwan-70b-instruct-q8_0-00001-of-00002.gguf) | Q8_0 | 8 | 75 GB|
|
| 26 |
|
| 27 |
## Original model card
|
| 28 |
|