microsoft
/

phi-1_5

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

8 contributors

History: 39 commits

gugarosa's picture

Enables to toggle fused_dense, flash_rotary and attn_pdrop in the configuration.

45f4b21 about 1 year ago

.gitattributes

1.52 kB

initial commit about 1 year ago
README.md

7.97 kB

Adds support for MQA/GQA and attention mask during training. about 1 year ago
Research License.docx

38.9 kB

Upload Research License.docx about 1 year ago
added_tokens.json

1.08 kB

Upload tokenizer about 1 year ago
config.json

707 Bytes

Support for `attention_mask` in forward pass. about 1 year ago
configuration_mixformer_sequential.py

2.14 kB

Enables to toggle fused_dense, flash_rotary and attn_pdrop in the configuration. about 1 year ago
generation_config.json

69 Bytes

Upload MixFormerSequentialForCausalLM about 1 year ago
merges.txt

456 kB

Upload tokenizer about 1 year ago
modeling_mixformer_sequential.py

31.1 kB

Fixes flash-attn import with a try/except statement about 1 year ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch._utils._rebuild_tensor_v2",
- "torch.HalfStorage",
- "collections.OrderedDict"
What is a pickle import?
2.84 GB
LFS

Upload MixFormerSequentialForCausalLM about 1 year ago
special_tokens_map.json

99 Bytes

Upload tokenizer about 1 year ago
tokenizer.json

2.11 MB

Upload tokenizer about 1 year ago
tokenizer_config.json

237 Bytes

Upload tokenizer about 1 year ago
vocab.json

798 kB

Upload tokenizer about 1 year ago