iAkashPaul
commited on
Commit
•
fb358cb
1
Parent(s):
9dddb40
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,27 @@
|
|
1 |
---
|
2 |
license: mit
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
tags:
|
4 |
+
- gemma
|
5 |
---
|
6 |
+
|
7 |
+
## Usage with Llama.cpp
|
8 |
+
|
9 |
+
```bash
|
10 |
+
git clone https://huggingface.co/iAkashPaul/Indic-gemma-2b-finetuned-sft-Navarasa-GGUF # & cd into it, update paths accordingly
|
11 |
+
|
12 |
+
./main --file prompt.md --lora ./models/Indic-gemma-2b-finetuned-sft-Navarasa/ggml-adapter-model.bin --lora-base ./models/indic-llm_Q8.gguf
|
13 |
+
./server --lora ./models/Indic-gemma-2b-finetuned-sft-Navarasa/ggml-adapter-model.bin --lora-base ./models/indic-llm_Q8.gguf -m ./models/indic-llm_Q8.gguf
|
14 |
+
|
15 |
+
```
|
16 |
+
|
17 |
+
## Prompt template for Instruction adherence-
|
18 |
+
|
19 |
+
Save this to a file(ex. prompt.md) & load it with the main executable.
|
20 |
+
|
21 |
+
```
|
22 |
+
### Instruction: Translate following sentence to Kannada.
|
23 |
+
|
24 |
+
### Input: This model is developed by Telugu LLM Labs
|
25 |
+
|
26 |
+
## Response:
|
27 |
+
```
|