Downloads · 30 days
16
4% of all-time downloads
gradjitta/llama2-7b-merged-finnish-alpaca-buggy
llama2-7b-merged-finnish-alpaca-buggy is a text generation model from gradjitta. Use it when you need the model to write or continue text. It is set up for transformers.
- Its a 500 step checkpoint of the following run
Downloads · 30 days
16
4% of all-time downloads
All-time downloads
443
Public
Repo size
13.5 GB
Likes
1
Public
Click a slice to open those files.
.bin13.5 GB · 100%
From the Hugging Face model README
python ./trl/examples/scripts/sft_trainer.py --model_name meta-llama/Llama-2-7b-hf --dataset_name datacrunch/finnish_alpaca --load_in_4bit --use_peft --batch_size 4 --gradient_accumulation_steps 2
I am still figuring out an efficient way of doing this, in the meantime you can test it
"Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. ### Instruction: Anna kolme vinkkiä terveenä pysymiseen. ###Response:"