TheBloke
/

koala-7B-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Ctrl+K

Ctrl+K

2 contributors

History: 44 commits

TheBloke's picture

Update for Transformers GPTQ support

9396416 over 1 year ago

.gitattributes

1.48 kB

initial commit about 2 years ago
README.md

11.8 kB

Update for Transformers GPTQ support over 1 year ago
config.json

735 Bytes

Update for Transformers GPTQ support over 1 year ago
generation_config.json

137 Bytes

Add JSON files about 2 years ago
model.safetensors

4 GB
LFS

Update for Transformers GPTQ support over 1 year ago
params.json

101 Bytes

Add JSON files about 2 years ago
quantize_config.json

158 Bytes

Update for Transformers GPTQ support over 1 year ago
special_tokens_map.json

410 Bytes

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. about 2 years ago
tokenizer.json

1.84 MB

Upload new GPTQs with varied parameters almost 2 years ago
tokenizer.model

500 kB
LFS

Add JSON files about 2 years ago
tokenizer_config.json

726 Bytes

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. about 2 years ago