Update README.md
Browse files
README.md
CHANGED
@@ -13,6 +13,10 @@ base_model: LumiOpen/Viking-7B
|
|
13 |
datasets:
|
14 |
- mpasila/Finnish-Alpaca-Tiny
|
15 |
---
|
|
|
|
|
|
|
|
|
16 |
This is a merge of [mpasila/Finnish-Alpaca-Tiny-V2-LoRA-7B](https://huggingface.co/mpasila/Finnish-Alpaca-Tiny-V2-LoRA-7B).
|
17 |
|
18 |
LoRA trained in 4-bit with 2k context using [LumiOpen/Viking-7B](https://huggingface.co/LumiOpen/Viking-7B/) as the base model for 1 epoch.
|
|
|
13 |
datasets:
|
14 |
- mpasila/Finnish-Alpaca-Tiny
|
15 |
---
|
16 |
+
This is an ExLlamaV2 quantized model in 4bpw of [mpasila/Finnish-Alpaca-Tiny-V2-7B](https://huggingface.co/mpasila/Finnish-Alpaca-Tiny-V2-7B) using the default calibration dataset.
|
17 |
+
|
18 |
+
# Original Model card:
|
19 |
+
|
20 |
This is a merge of [mpasila/Finnish-Alpaca-Tiny-V2-LoRA-7B](https://huggingface.co/mpasila/Finnish-Alpaca-Tiny-V2-LoRA-7B).
|
21 |
|
22 |
LoRA trained in 4-bit with 2k context using [LumiOpen/Viking-7B](https://huggingface.co/LumiOpen/Viking-7B/) as the base model for 1 epoch.
|