OccamRazor
/

pygmalion-6b-gptq-4bit

Text Generation

Inference Endpoints

Model card Files Files and versions Community

pygmalion-6b-gptq-4bit

1 contributor

History: 3 commits

OccamRazor's picture

Replace old quantization with new groupsize 128 quantization

bf7ab74 over 1 year ago

.gitattributes

1.48 kB

initial commit over 1 year ago
4bit-128g.pt
Detected Pickle imports (6)
- "torch.FloatStorage",
- "torch.HalfStorage",
- "torch.IntStorage",
- "torch.BoolStorage",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict"
What is a pickle import?
3.96 GB
LFS

Replace old quantization with new groupsize 128 quantization over 1 year ago
README.md

39 Bytes

initial commit over 1 year ago
added_tokens.json

4.33 kB

Add 4-bit quantization of Pygmalion-6B over 1 year ago
config.json

975 Bytes

Add 4-bit quantization of Pygmalion-6B over 1 year ago
merges.txt

456 kB

Add 4-bit quantization of Pygmalion-6B over 1 year ago
special_tokens_map.json

470 Bytes

Add 4-bit quantization of Pygmalion-6B over 1 year ago
tokenizer_config.json

816 Bytes

Add 4-bit quantization of Pygmalion-6B over 1 year ago
vocab.json

999 kB

Add 4-bit quantization of Pygmalion-6B over 1 year ago