TheBloke
/

koala-7B-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

2 contributors

History: 18 commits

TheBloke's picture

Update README.md

5c70aa1 over 1 year ago

.gitattributes

1.48 kB

initial commit over 1 year ago
README.md

5.7 kB

Update README.md over 1 year ago
config.json

507 Bytes

Add JSON files over 1 year ago
generation_config.json

137 Bytes

Add JSON files over 1 year ago
koala-7B-4bit-128g.no-act-order.ooba.pt
Detected Pickle imports (5)
- "torch.FloatStorage",
- "torch.HalfStorage",
- "collections.OrderedDict",
- "torch.IntStorage",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
4 GB
LFS

Add model made with oobabooga's older fork of GPTQ, suitable for use in text-generation-webui without requiring an update to GPTQ code. Also for GGML conversion. over 1 year ago
koala-7B-4bit-128g.pt

3.89 GB
LFS

Add model file over 1 year ago
koala-7B-4bit-128g.safetensors

3.89 GB
LFS

add safetensors model over 1 year ago
params.json

101 Bytes

Add JSON files over 1 year ago
special_tokens_map.json

2 Bytes

Add JSON files over 1 year ago
tokenizer.model

500 kB
LFS

Add JSON files over 1 year ago
tokenizer_config.json

141 Bytes

Add JSON files over 1 year ago