vince62s commited on
Commit
ab8b117
·
1 Parent(s): 700cec6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -7,16 +7,21 @@ By original, it means with interleaved rotary (option: rotary_interleave=True)
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
-
 
7
  You need to install OpenNMT-py, instructions are here: https://github.com/OpenNMT/OpenNMT-py
8
 
9
  Running inference:
10
+ ```
11
  Create a text input file with prompts (ex: "Show me some attractions in Boston")
12
  then run:
13
  onmt_translate --config mistral-inference.yaml --src input.txt --output output.txt
14
+ ```
15
 
16
  Running MMLU evaluation:
17
+ ```
18
  If you git clone the OpenNMT-py repo then you can run:
19
  python eval_llm/MMLU/run_mmlu_opennmt.py --config mistral-inference.yaml
20
  For this use case make sure you use max_length=1 in the config file
21
+ ```
22
 
23
  Finetuning:
24
+ ```
25
  Read this tuto: https://forum.opennmt.net/t/finetuning-llama-7b-13b-or-mosaicml-mpt-7b-reproduce-vicuna-alpaca/5272/56
26
  onmt_train --config mistral-finetuning.yaml
27
+ ```