Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
dicta-il
/
dictalm-7b-instruct
like
12
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
10 months ago
.gitattributes
1.52 kB
initial commit
12 months ago
LICENSE
18.7 kB
Upload LICENSE
11 months ago
README.md
3.48 kB
Update README.md
10 months ago
config.json
1.01 kB
Upload folder using huggingface_hub
12 months ago
configuration_megatron_gpt.py
9.57 kB
Added flash attention
10 months ago
generation_config.json
132 Bytes
Upload folder using huggingface_hub
12 months ago
merges.txt
1.27 MB
Upload folder using huggingface_hub
12 months ago
modeling_megatron_gpt.py
55.1 kB
Added flash attention
10 months 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
12 months 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
12 months ago
pytorch_model.bin.index.json
39.4 kB
Upload folder using huggingface_hub
12 months ago
special_tokens_map.json
567 Bytes
Upload folder using huggingface_hub
12 months ago
tokenizer_config.json
890 Bytes
Upload folder using huggingface_hub
12 months ago
vocab.json
1.88 MB
Upload folder using huggingface_hub
12 months ago