** Model upgraded and finetuned starting from LlaMa model. I hope everyone creates modes starting from this open-source project**

GPTQ conversion command (on CUDA branch):
CUDA_VISIBLE_DEVICES=0 python llama.py ../capibara-17b-4bit c4 --wbits 4 --true-sequential --groupsize 128 --save capibara-17b-4bit-128g.pt

Added 1 token to the tokenizer model:
python llama-tools/add_tokens.py capibara-17b/tokenizer.model /content/tokenizer.model llama-tools/test_list.txt

Enjoy