Initial commit

README.md

@@ -0,0 +1,38 @@
+---
+inference: false
+language:
+- bg
+license: mit
+tags:
+- torch
+---
+
+# LLaMA-7B
+
+This repo contains a low-rank adapter for LLaMA-7b trained on Bulgarian dataset.
+
+This model was introduced in [this paper](https://arxiv.org/abs/2106.09685). 
+
+## Model description
+
+The training data is private Bulgarian dataset. 
+
+## Intended uses & limitations
+
+This is an instruction-based model similart to ChatGPT but in Bulgarian. The inteded use is research-only.
+
+### How to use
+
+Here is how to use this model in PyTorch:
+
+```bash
+>>> pip install -r requirements.txt
+>>>
+>>> python generate.py \
+    --load_8bit \
+    --base_model 'yahma/llama-7b-hf' \
+    --lora_weights 'rmihaylov/alpaca-lora-bg-7b' \
+    --share_gradio
+```
+
+This will download both a base model and an adapter from huggingface. Then it will run a gradio interface for chatting.