Update README.md
Browse files
README.md
CHANGED
|
@@ -293,21 +293,6 @@ Third Eye Blind remains a beloved rock band with a dedicated fan base. Their mus
|
|
| 293 |
|
| 294 |
## Provided Quants
|
| 295 |
|
| 296 |
-
| Link | Type | Size/GB | Notes |
|
| 297 |
-
|:-----|:-----|--------:|:------|
|
| 298 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | |
|
| 299 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
|
| 300 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
|
| 301 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
|
| 302 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
|
| 303 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
|
| 304 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
|
| 305 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
|
| 306 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
|
| 307 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
|
| 308 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
|
| 309 |
-
| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-SISaAI-Ko-merge-8B-Instruct-GGUF/resolve/main/Llama-3.1-SISaAI-Ko-merge-8B-Instruct.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
|
| 310 |
-
|
| 311 |
This graph compares the performance of various quantization methods, focusing on lower-quality quant types:
|
| 312 |
|
| 313 |
X-axis (bpw): Bits per weight. Lower values mean higher compression.
|
|
|
|
| 293 |
|
| 294 |
## Provided Quants
|
| 295 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 296 |
This graph compares the performance of various quantization methods, focusing on lower-quality quant types:
|
| 297 |
|
| 298 |
X-axis (bpw): Bits per weight. Lower values mean higher compression.
|