BackyardLabs
/

Eluwa-1.3b

Model card Files Files and versions

Yudhanjaya commited on Apr 24, 2023

Commit

b03b872

·

1 Parent(s): 252f443

Update README.md

Files changed (1) hide show

README.md +3 -4

README.md CHANGED Viewed

@@ -31,19 +31,18 @@ Below are the results of Vicuna-style testing: 80 questions in various categorie
 Within the bounds of our testing, it was, in fact, suprisingly good, exceeding its 2.7b cousin.
-A csv of questions, answers and GPT's reviews are also included in this repo in the /TestResults/ folder, along with the base model for comparison.
 ## Using Eluwa
 I used [oobabooga's text generation UI](https://github.com/oobabooga/text-generation-webui) for testing, because it lets me easily regenerate outputs, modify the conversation history passed to the model, and mess with parameters.
-To load Eluwa, download [OPT 6.7b from Huggingface](https://huggingface.co/facebook/opt-6.7b) and download both the .bin and .json file from the /model folder on this Github. Follow the instructions on the text generation UI repository to figure out where the model goes and how to load a LoRA. Eluwa goes in the /loras folder.
 ## Training and notes
 Training Eluwa is a straightforward process. It is essentially Facebook's GPT-like OPT 6.7b model, loaded in 8-bit and trained using [Stanford's Alapaca dataset](https://github.com/tatsu-lab/stanford_alpaca).
-Use the [Colab notebook here](https://huggingface.co/BackyardLabs/Eluwa/blob/main/Train_eluwa.ipynb). I've written notes in there on what the functions do.
 ## Why "Eluwa"?

 Within the bounds of our testing, it was, in fact, suprisingly good, exceeding its 2.7b cousin.
+A csv of questions, answers and GPT's reviews are also included in this repo in the /TestResults/ folder of the [Eluwa github repo](https://github.com/yudhanjaya/Eluwa), along with the base model for comparison.
 ## Using Eluwa
 I used [oobabooga's text generation UI](https://github.com/oobabooga/text-generation-webui) for testing, because it lets me easily regenerate outputs, modify the conversation history passed to the model, and mess with parameters.
+To load Eluwa, download [OPT 1.3b from Huggingface](https://huggingface.co/facebook/opt-1.3b) and download both the .bin and .json file from the /model folder on this Github. Follow the instructions on the text generation UI repository to figure out where the model goes and how to load a LoRA. Eluwa goes in the /loras folder.
 ## Training and notes
 Training Eluwa is a straightforward process. It is essentially Facebook's GPT-like OPT 6.7b model, loaded in 8-bit and trained using [Stanford's Alapaca dataset](https://github.com/tatsu-lab/stanford_alpaca).
+The training code is available on the [Eluwa github repo](https://github.com/yudhanjaya/Eluwa) and will as-is in Google Colab.
 ## Why "Eluwa"?