Update README.md
Browse files
README.md
CHANGED
|
@@ -62,7 +62,8 @@ Made by: [FreedomIntelligence](https://huggingface.co/FreedomIntelligence)
|
|
| 62 |
## Quantization notes
|
| 63 |
Made with llama.cpp-b3938 with imatrix file based on Exllamav2 callibration dataset.
|
| 64 |
This model is meant to run with llama.cpp-compatible apps such as Text-Generation-WebUI, KoboldCpp, Jan, LM Studio and many many others.
|
| 65 |
-
17.12.2024: Readme update. It seems Q4_0_4_4, Q4_0_4_8 and Q4_0_8_8 support was removed in recent llama.cpp. I'll keep them but they might be no longer useful.
|
|
|
|
| 66 |
|
| 67 |
# Original model card
|
| 68 |
# Democratizing Medical LLMs For Much More Languages
|
|
|
|
| 62 |
## Quantization notes
|
| 63 |
Made with llama.cpp-b3938 with imatrix file based on Exllamav2 callibration dataset.
|
| 64 |
This model is meant to run with llama.cpp-compatible apps such as Text-Generation-WebUI, KoboldCpp, Jan, LM Studio and many many others.
|
| 65 |
+
17.12.2024: Readme update. It seems Q4_0_4_4, Q4_0_4_8 and Q4_0_8_8 support was removed in recent llama.cpp. I'll keep them but they might be no longer useful.
|
| 66 |
+
03.02.2025: Added Q4_0 and IQ4_NL quants as a substitute for Q4_0_X_Y quants for ARM devices with newer llama.cpp versions.
|
| 67 |
|
| 68 |
# Original model card
|
| 69 |
# Democratizing Medical LLMs For Much More Languages
|