mobiuslabsgmbh
/

Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bit-metaoffload-HQQ

Text Generation

Mixture of Experts

Model card Files Files and versions Community

Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bit-metaoffload-HQQ

2 contributors

History: 12 commits

mobicham's picture

update qmodel with gs=128

cbbc082 12 months ago

.gitattributes

1.52 kB

update qmodel with gs=128 12 months ago
README.md

4.69 kB

update qmodel with gs=128 12 months ago
config.json

773 Bytes

update qmodel with gs=128 12 months ago
qmodel.pt
Detected Pickle imports (7)
- "torch._utils._rebuild_parameter",
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict",
- "torch.ByteStorage",
- "torch.HalfStorage",
- "torch.Size",
- "torch.float16"
How to fix it?
18.3 GB
LFS

update qmodel with gs=128 12 months ago
special_tokens_map.json

414 Bytes

update qmodel with gs=128 12 months ago
tokenizer.json

1.8 MB

update qmodel with gs=128 12 months ago
tokenizer.model

493 kB
LFS

update qmodel with gs=128 12 months ago
tokenizer_config.json

1.46 kB

update qmodel with gs=128 12 months ago