TheBloke
/

vicuna-7B-1.1-GPTQ

Text Generation

Model card Files Files and versions

vicuna-7B-1.1-GPTQ

7.79 GB

1 contributor

History: 16 commits

TheBloke's picture

Create quantize_config.json

01c5a6b over 2 years ago

.gitattributes

1.48 kB

initial commit over 2 years ago
README.md

7.66 kB

Update README.md over 2 years ago
config.json

581 Bytes

Update config.json over 2 years ago
generation_config.json

136 Bytes

Update generation_config.json over 2 years ago
quantize_config.json

123 Bytes

Create quantize_config.json over 2 years ago
special_tokens_map.json

411 Bytes

Update special_tokens_map.json over 2 years ago
tokenizer.model

500 kB
xet

Add model over 2 years ago
tokenizer_config.json

699 Bytes

Update tokenizer_config.json over 2 years ago
vicuna-7B-1.1-GPTQ-4bit-128g.no-act-order.pt
Detected Pickle imports (5)
- "torch.FloatStorage",
- "torch._utils._rebuild_tensor_v2",
- "torch.IntStorage",
- "collections.OrderedDict",
- "torch.HalfStorage"
What is a pickle import?
3.89 GB
xet

Add no-act-order model over 2 years ago
vicuna-7B-1.1-GPTQ-4bit-128g.safetensors

3.89 GB
xet

Add model over 2 years ago