Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
microsoft
/
phi-1_5
like
1.29k
Text Generation
Transformers
Safetensors
English
phi
nlp
code
Inference Endpoints
text-generation-inference
arxiv:
2309.05463
License:
mit
Model card
Files
Files and versions
Community
85
Train
Deploy
Use this model
85d9497
phi-1_5
8 contributors
History:
46 commits
susnato
add attn_pdrop and auto_map
85d9497
7 months ago
.gitattributes
1.52 kB
initial commit
9 months ago
README.md
7.97 kB
Adds support for MQA/GQA and attention mask during training.
7 months ago
Research License.docx
38.9 kB
Upload Research License.docx
9 months ago
added_tokens.json
1.08 kB
Upload tokenizer
9 months ago
config.json
787 Bytes
add attn_pdrop and auto_map
7 months ago
configuration_phi.py
8.44 kB
changes
7 months ago
generation_config.json
69 Bytes
Upload MixFormerSequentialForCausalLM
9 months ago
merges.txt
456 kB
Upload tokenizer
9 months ago
modeling_phi.py
58.2 kB
changes
7 months ago
pytorch_model.bin
pickle
Detected Pickle imports (3)
"collections.OrderedDict"
,
"torch.HalfStorage"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
2.84 GB
LFS
changes
7 months ago
special_tokens_map.json
99 Bytes
Upload tokenizer
9 months ago
tokenizer.json
2.11 MB
Upload tokenizer
9 months ago
tokenizer_config.json
237 Bytes
Upload tokenizer
9 months ago
vocab.json
798 kB
Upload tokenizer
9 months ago