microsoft
/

Phi-3-mini-128k-instruct-onnx

Text Generation

Model card Files Files and versions Community

Phi-3-mini-128k-instruct-onnx / cuda /cuda-fp16

Ctrl+K

Ctrl+K

3 contributors

History: 6 commits

Gustavo de Rosa

fix(root): Also fixes the tokenizer.json to prevent mismatches.

e85d1b3 about 1 year ago

added_tokens.json

293 Bytes

Upload Phi-3-mini-128k-instruct ONNX models about 1 year ago
config.json

3.37 kB

Add files for Hugging Face's Optimum about 1 year ago
configuration_phi3.py

10.4 kB

Add files for Hugging Face's Optimum about 1 year ago
genai_config.json

1.73 kB

fix(genai_config): Adds extra EOS token to improve chat outputs. about 1 year ago
phi3-mini-128k-instruct-cuda-fp16.onnx

26.1 MB
LFS

Upload Phi-3-mini-128k-instruct ONNX models about 1 year ago
phi3-mini-128k-instruct-cuda-fp16.onnx.data

7.64 GB
LFS

Upload Phi-3-mini-128k-instruct ONNX models about 1 year ago
special_tokens_map.json

568 Bytes

Upload Phi-3-mini-128k-instruct ONNX models about 1 year ago
tokenizer.json

1.84 MB

fix(root): Also fixes the tokenizer.json to prevent mismatches. about 1 year ago
tokenizer.model

500 kB
LFS

Upload Phi-3-mini-128k-instruct ONNX models about 1 year ago
tokenizer_config.json

3.17 kB

fix(tokenizer_config): Adjusts rstrip of special tokens. about 1 year ago