Initial commit

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ggml-model-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+ggml-model-q2_K.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,29 @@
 ---
+datasets:
+- IlyaGusev/ru_turbo_saiga
+- IlyaGusev/ru_sharegpt_cleaned
+- IlyaGusev/oasst1_ru_main_branch
+- IlyaGusev/gpt_roleplay_realm
+- lksy/ru_instruct_gpt4
+language:
+- ru
+inference: false
+pipeline_tag: conversational
 license: llama2
 ---
+
+Llama.cpp compatible versions of an original [70B model](https://huggingface.co/IlyaGusev/saiga2_70b_lora).
+
+* Download one of the versions, for example `ggml-model-q4_1.gguf`.
+* Download [interact_llamacpp.py](https://raw.githubusercontent.com/IlyaGusev/rulm/master/self_instruct/src/interact_llamacpp.py)
+
+How to run:
+```
+sudo apt-get install git-lfs
+pip install llama-cpp-python fire
+
+python3 interact_llamacpp.py ggml-model-q4_1.gguf
+```
+
+System requirements:
+* 45GB RAM for q4_1

ggml-model-q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e7d244b5cd7633041bcb2bfdae2a6a0ed0392fc317eca48dc3a007055f69f10
+size 29279253408

ggml-model-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b4a893292ec33aeeadeef15ba5c66975ab79778c2d33bce3d576c95983d0c2
+size 43166823328