Update for Transformers GPTQ support

Delete koala-13B-4bit-128g.pt

Delete koala-13B-4bit-128g.no-act-order.ooba.pt

Delete koala-13B-4bit-128g.safetensors

Upload new GPTQs with varied parameters

Upload new GPTQs with varied parameters

Upload new GPTQs with varied parameters

Upload new GPTQs with varied parameters

Upload new GPTQs with varied parameters

Upload new GPTQs with varied parameters

Upload new GPTQs with varied parameters

Upload new GPTQs with varied parameters

Upload new GPTQs with varied parameters

Upload new GPTQs with varied parameters

Update README.md

Updating model files

Update README.md

Update special_tokens_map.json to match other models, like Vicuna - the Koala conversion process does not fill out this file, but based on the code I think these special tokens should be defined.

Update tokenizer_config.json to match other models, like Vicuna - the Koala conversion process does not fill out this file, but based on the code I think these special tokens should be defined.

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Add new pt file created with oobabooga's older CUDA fork of GPTQ

Update README.md

Update README.md

Update README.md

Add safetensors

Push model

Update README.md

Update README.md

Update README.md

initial commit