mobiuslabsgmbh
/

Llama-3-8b-instruct_2bitgs64_hqq

Text Generation

Model card Files Files and versions Community

Llama-3-8b-instruct_2bitgs64_hqq

2 contributors

History: 17 commits

mobicham's picture

fix fp16 vram

25d87d5 verified 3 months ago

.gitattributes

1.7 kB

Upload llama3-2bit.gif 4 months ago
README.md

4.04 kB

fix fp16 vram 3 months ago
adapter_v0.1.lora

83 MB
LFS

adapter 4 months ago
config.json

728 Bytes
LFS

add json 4 months ago
llama3-2bit.gif

25.8 MB
LFS

Upload llama3-2bit.gif 4 months ago
qmodel.pt
Detected Pickle imports (8)
- "torch.uint8",
- "collections.OrderedDict",
- "torch._utils._rebuild_parameter",
- "torch.Size",
- "torch.ByteStorage",
- "torch._utils._rebuild_tensor_v2",
- "torch.bfloat16",
- "torch.BFloat16Storage"
How to fix it?
4.28 GB
LFS

upload model 4 months ago
special_tokens_map.json

296 Bytes
LFS

add json 4 months ago
tokenizer.json

9.09 MB
LFS

add json 4 months ago
tokenizer_config.json

51 kB
LFS

add json 4 months ago