Initial commit

.gitattributes

@@ -32,3 +32,6 @@ 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-q5_1.bin filter=lfs diff=lfs merge=lfs -text
+ggml-model-q8_0.bin filter=lfs diff=lfs merge=lfs -text
+ggml-model-q4_1.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,26 @@
+---
+datasets:
+- IlyaGusev/ru_turbo_alpaca
+- IlyaGusev/ru_turbo_saiga
+- IlyaGusev/ru_sharegpt_cleaned
+language:
+- ru
+inference: false
+pipeline_tag: text2text-generation
+---
+
+Llama.cpp compatible versions of an original [13B model](https://huggingface.co/IlyaGusev/saiga_13b_lora).
+
+* Download one of the versions, for example `ggml-model-q4_1.bin`.
+* Download [interact_saiga_llamacpp.py]([https://raw.githubusercontent.com/IlyaGusev/rulm/master/self_instruct/src/infer_saiga_llamacpp.py)
+
+How to run:
+```
+sudo apt-get install git-lfs
+pip install llama-cpp-python fire
+
+python3 interact_saiga_llamacpp.py ggml-model-q4_1.bin
+```
+
+System requirements:
+* 10GB RAM

ggml-model-q4_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fed0b0e45e8731d0e1a0c8ed5b36f83951887805147a2012b327fe9aa7a5b9
+size 9763701888

ggml-model-q5_1.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0098b1bab55b796bb9a1d596241f266205220738f3a9a9064990e44b78b2453
+size 9763701888

ggml-model-q8_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2bc1ee6a05625f78af12f0011ead209a049f986395c1b08eadcb9abd00f992
+size 14644495488