Merge branch 'main' of https://huggingface.co/IlyaGusev/saiga_30b_lora_llamacpp into main
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- IlyaGusev/ru_turbo_alpaca
|
| 4 |
+
- IlyaGusev/ru_turbo_saiga
|
| 5 |
+
- IlyaGusev/ru_sharegpt_cleaned
|
| 6 |
+
language:
|
| 7 |
+
- ru
|
| 8 |
+
inference: false
|
| 9 |
+
pipeline_tag: text2text-generation
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
Llama.cpp compatible version of an original [30B model](https://huggingface.co/IlyaGusev/saiga_30b_lora).
|
| 13 |
+
|
| 14 |
+
How to run:
|
| 15 |
+
```
|
| 16 |
+
sudo apt-get install git-lfs
|
| 17 |
+
pip install llama-cpp-python fire
|
| 18 |
+
|
| 19 |
+
git clone https://huggingface.co/IlyaGusev/saiga_30b_lora_llamacpp
|
| 20 |
+
|
| 21 |
+
cd saiga_30b_lora_llamacpp
|
| 22 |
+
python3 interact.py ggml-model-q4_1.bin
|
| 23 |
+
```
|