Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
dicta-il
/
dictalm-7b-instruct
like
13
Follow
DICTA: The Israel Center for Text Analysis
33
Text Generation
Transformers
PyTorch
Hebrew
megatron_gpt
custom_code
arxiv:
2309.14568
License:
cc-by-4.0
Model card
Files
Files and versions
Community
8
Train
Use this model
f5c007b
dictalm-7b-instruct
3 contributors
History:
13 commits
Shaltiel
Added flash attention
f5c007b
about 1 year ago
.gitattributes
1.52 kB
initial commit
over 1 year ago
LICENSE
18.7 kB
Upload LICENSE
about 1 year ago
README.md
3.48 kB
Update README.md
about 1 year ago
config.json
1.01 kB
Upload folder using huggingface_hub
over 1 year ago
configuration_megatron_gpt.py
9.57 kB
Added flash attention
about 1 year ago
generation_config.json
132 Bytes
Upload folder using huggingface_hub
over 1 year ago
merges.txt
1.27 MB
Upload folder using huggingface_hub
over 1 year ago
modeling_megatron_gpt.py
55.1 kB
Added flash attention
about 1 year ago
pytorch_model-00001-of-00002.bin
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"torch.HalfStorage"
What is a pickle import?
9.97 GB
LFS
Upload e2.5 + instruct
about 1 year ago
pytorch_model-00002-of-00002.bin
pickle
Detected Pickle imports (3)
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"torch.HalfStorage"
What is a pickle import?
950 MB
LFS
Upload e2.5 + instruct
about 1 year ago
pytorch_model.bin.index.json
39.4 kB
Upload folder using huggingface_hub
over 1 year ago
special_tokens_map.json
567 Bytes
Upload folder using huggingface_hub
over 1 year ago
tokenizer_config.json
890 Bytes
Upload folder using huggingface_hub
over 1 year ago
vocab.json
1.88 MB
Upload folder using huggingface_hub
over 1 year ago