Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,9 @@
|
|
| 1 |
---
|
| 2 |
license: llama3.1
|
| 3 |
---
|
| 4 |
-
Q4_K_M GGUF quant of [Reflection-Llama-3.1-70B](https://huggingface.co/mattshumer/Reflection-Llama-3.1-70B) - fixed version
|
| 5 |
-
Runs great on 48GB VRAM, tested
|
| 6 |
-
|
|
|
|
| 7 |
All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel:
|
| 8 |
<a href="https://www.buymeacoffee.com/TeeZee" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
|
|
|
|
| 1 |
---
|
| 2 |
license: llama3.1
|
| 3 |
---
|
| 4 |
+
Q4_K_M GGUF quant of [Reflection-Llama-3.1-70B](https://huggingface.co/mattshumer/Reflection-Llama-3.1-70B) - fixed version.<br>
|
| 5 |
+
Runs great on 48GB VRAM, tested.<br>
|
| 6 |
+
Ollama modelfile added - version with original system prompt - output is split into "thinking" and "output" tags.<br>
|
| 7 |
+
If you want llama 3.1 'vanilla' experience, just remove SYSTEM from modelfile before creating ollama model.<br><br>
|
| 8 |
All comments are greatly appreciated, download, test and if you appreciate my work, consider buying me my fuel:
|
| 9 |
<a href="https://www.buymeacoffee.com/TeeZee" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
|