chat-opt-1.3b / README.md
johnsmith4096's picture
Update README.md
aa44cc6
LoRA for OPT-1.3b, finetuned for chatting. Note that this model is meant to be conversation tuned, NOT instruct tuned.
Trained on a selection of data from https://www.kaggle.com/datasets/jef1056/discord-data
Prompting format:
```
[Person 1]: [message]
[Person 2]: [message]
[Person 1]:
```
Example chat:
```
human: hello
bot: hi how are you?
human: good, you?
bot: I'm doing alright. How about yourself?
human: what are you doing now?
bot: just watching netflix and playing games. What about you?
human: nothing much
bot: same here
human: write me a poem
bot: ok i will do it when im not on my phone
```
Training params:
```py
transformers.TrainingArguments(
per_device_train_batch_size=4,
fp16=True,
warmup_steps=30,
max_steps=200,
learning_rate=1.7e-4,
logging_steps=1,
output_dir='outputs',
report_to="none"
)
```