Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,22 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
---
|
4 |
+
This model is the original Mistral-ai 7B v0.1 model converted to the OpenNMT-py format.
|
5 |
+
By original, it means with interleaved rotary (option: rotary_interleave=True)
|
6 |
+
|
7 |
+
You need to install OpenNMT-py, instructions are here: https://github.com/OpenNMT/OpenNMT-py
|
8 |
+
|
9 |
+
Running inference:
|
10 |
+
Create a text input file with prompts (ex: "Show me some attractions in Boston")
|
11 |
+
then run:
|
12 |
+
onmt_translate --config mistral-inference.yaml --src input.txt --output output.txt
|
13 |
+
|
14 |
+
Running MMLU evaluation:
|
15 |
+
If you git clone the OpenNMT-py repo then you can run:
|
16 |
+
python eval_llm/MMLU/run_mmlu_opennmt.py --config mistral-inference.yaml
|
17 |
+
For this use case make sure you use max_length=1 in the config file
|
18 |
+
|
19 |
+
Finetuning:
|
20 |
+
Read this tuto: https://forum.opennmt.net/t/finetuning-llama-7b-13b-or-mosaicml-mpt-7b-reproduce-vicuna-alpaca/5272/56
|
21 |
+
onmt_train --config mistral-finetuning.yaml
|
22 |
+
|