Downloads · 30 days
0
0% of all-time downloads
Weni/WeniGPT-QA-Zephyr-7B-4.0.2-KTO
WeniGPT-QA-Zephyr-7B-4.0.2-KTO is a machine learning model from Weni. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for trl. The card lists the license as mit.
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta] on the dataset Weni/WeniGPT-QA-Binarized-1.2.0 with the KTO trainer. It is part of the WeniGPT project for Weni. Description: WeniGPT Experiment usi…
Downloads · 30 days
0
0% of all-time downloads
All-time downloads
9
Public
Repo size
2.3 GB
Likes
0
Public
Click a slice to open those files.
.safetensors1.5 GB · 65%
From the Hugging Face model README
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta] on the dataset Weni/WeniGPT-QA-Binarized-1.2.0 with the KTO trainer. It is part of the WeniGPT project for Weni. Description: WeniGPT Experiment using KTO trainer with no collator
It achieves the following results on the evaluation set: {'eval_loss': 0.030648991465568542, 'eval_runtime': 234.2131, 'eval_samples_per_second': 1.994, 'eval_steps_per_second': 0.999, 'eval_rewards/chosen': 5.51336669921875, 'eval_logps/chosen': -155.14308166503906, 'eval_rewards/rejected': -19.720834732055664, 'eval_logps/rejected': -384.9552001953125, 'eval_kl': 0.35056793689727783, 'eval_rewards/margins': 25.238788604736328, 'epoch': 0.73}
This model has not been trained to avoid specific intructions.
Finetuning was done on the model HuggingFaceH4/zephyr-7b-beta with the following prompt:
---------------------
Question:
<|system|>
Você é um médico tratando um paciente com amnésia. Para responder as perguntas do paciente, você irá ler um texto anteriormente para se contextualizar. Se você trouxer informações desconhecidas, fora do texto lido, poderá deixar o paciente confuso. Se o paciente fizer uma questão sobre informações não presentes no texto, você precisa responder de forma educada que você não tem informação suficiente para responder, pois se tentar responder, pode trazer informações que não ajudarão o paciente recuperar sua memória. Lembre, se não estiver no texto, você precisa responder de forma educada que você não tem informação suficiente para responder. Precisamos ajudar o paciente.
<|user|>
Contexto: {context}
Questão: {question}</s>
<|assistant|>
---------------------
Response:
{response}</s>
---------------------
The following hyperparameters were used during training: