hlarcher
/

falcon-7b-v100s

Text Generation

RefinedWebModel

text-generation-inference

Model card Files Files and versions Community

falcon-7b-v100s

2 contributors

History: 2 commits

hlarcher's picture

hlarcher HF staff

Fix attention for Nvidia V100s compatibility (no FlashAttention). Based on work of puru22 for Falcon-40B

67f33d0 over 1 year ago

.gitattributes

1.48 kB

Initial fork over 1 year ago
.gitignore

3.99 kB

Fix attention for Nvidia V100s compatibility (no FlashAttention). Based on work of puru22 for Falcon-40B over 1 year ago
README.md

10.2 kB

Initial fork over 1 year ago
config.json

950 Bytes

Initial fork over 1 year ago
configuration_RW.py

2.61 kB

Initial fork over 1 year ago
generation_config.json

111 Bytes

Initial fork over 1 year ago
modelling_RW.py

49.4 kB

Fix attention for Nvidia V100s compatibility (no FlashAttention). Based on work of puru22 for Falcon-40B over 1 year ago
pytorch_model-00001-of-00002.bin
Detected Pickle imports (3)
- "collections.OrderedDict",
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
9.95 GB
LFS

Initial fork over 1 year ago
pytorch_model-00002-of-00002.bin
Detected Pickle imports (3)
- "collections.OrderedDict",
- "torch.BFloat16Storage",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
4.48 GB
LFS

Initial fork over 1 year ago
pytorch_model.bin.index.json

16.9 kB

Initial fork over 1 year ago
special_tokens_map.json

281 Bytes

Initial fork over 1 year ago
tokenizer.json

2.73 MB

Initial fork over 1 year ago
tokenizer_config.json

220 Bytes

Initial fork over 1 year ago