mobiuslabsgmbh
/

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

Text Generation

Mixture of Experts

Model card Files Files and versions

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

Ctrl+K

Ctrl+K

2 contributors

History: 7 commits

appoose's picture

adding vram usage

48d4273 verified over 1 year ago

.gitattributes

1.52 kB

initial commit over 1 year ago
README.md

3.53 kB

adding vram usage over 1 year ago
config.json

773 Bytes

upload model over 1 year ago
qmodel.pt
Detected Pickle imports (7)
- "torch.ByteStorage",
- "torch._utils._rebuild_parameter",
- "torch.Size",
- "torch._utils._rebuild_tensor_v2",
- "torch.HalfStorage",
- "collections.OrderedDict",
- "torch.float16"
How to fix it?
18.3 GB
xet

upload model over 1 year ago
special_tokens_map.json

414 Bytes

upload model over 1 year ago
tokenizer.json

1.8 MB

upload model over 1 year ago
tokenizer.model

493 kB
xet

upload model over 1 year ago
tokenizer_config.json

1.46 kB

upload model over 1 year ago