Merge branch 'main' of https://huggingface.co/IlyaGusev/saiga_yandexgpt_8b_gguf into main

README.md

@@ -0,0 +1,33 @@
+---
+datasets:
+- IlyaGusev/saiga_scored
+- IlyaGusev/saiga_preferences
+language:
+- ru
+inference: false
+license: other
+license_name: yandexgpt-5-lite-8b-pretrain
+license_link: LICENSE
+---
+
+Llama.cpp compatible versions of an original [8B model](https://huggingface.co/IlyaGusev/saiga_yandexgpt_8b).
+
+Download one of the versions, for example `saiga_yandexgpt_8b.Q4_K_M.gguf`.
+```
+wget https://huggingface.co/IlyaGusev/saiga_yandexgpt_8b_gguf/resolve/main/saiga_yandexgpt_8b.Q4_K_M.gguf
+```
+
+Download [interact_gguf.py](https://raw.githubusercontent.com/IlyaGusev/saiga/refs/heads/main/scripts/interact_gguf.py)
+```
+https://raw.githubusercontent.com/IlyaGusev/saiga/refs/heads/main/scripts/interact_gguf.py
+```
+
+How to run:
+```
+pip install llama-cpp-python fire
+
+python3 interact_gguf.py saiga_yandexgpt_8b.Q4_K_M.gguf
+```
+
+System requirements:
+* 15GB RAM for q8_0 and less for smaller quantizations