BricksDisplay/phi-2-q4
By BricksDisplay · ↓ 13 · ♥ 0 · Updated 2024-03-23
What's in this repo
This page lists the files in BricksDisplay/phi-2-q4, including decoder_model.onnx, decoder_model_merged.onnx, decoder_model_merged_quantized.onnx and more.
- 6 ONNX models (.onnx files)
- 25 files, including 8 .json, 6 .onnx, 6 .onnx_data, 1 .md, 1 .0_self_attn_rotary_emb_constant_5_attr__value, 1 .0_self_attn_rotary_emb_constant_attr__value
- Last updated 2024-03-23
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/decoder_model.onnx | — | Download |
| onnx/decoder_model_merged.onnx | — | Download |
| onnx/decoder_model_merged_quantized.onnx | — | Download |
| onnx/decoder_model_quantized.onnx | — | Download |
| onnx/decoder_with_past_model.onnx | — | Download |
| onnx/decoder_with_past_model_quantized.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
Convert from microsoft/phi-2 and 4 bits quantized.
Require onnxruntime>=0.17.0
Model info
text-generation
transformers
transformers
onnx
phi
text-generation
custom_code
endpoints_compatible
region:us
↓ 13
♥ 0
Created: 2024-03-22
Updated: 2024-03-23
View on Hugging FaceFiles (25)
.gitattributes
README.md
_model_layers.0_self_attn_rotary_emb_Constant_5_attr__value
_model_layers.0_self_attn_rotary_emb_Constant_attr__value
added_tokens.json
config.json
generation_config.json
merges.txt
onnx/decoder_model.onnx
ONNX
onnx/decoder_model.onnx_data
onnx/decoder_model_merged.onnx
ONNX
onnx/decoder_model_merged.onnx_data
onnx/decoder_model_merged_quantized.onnx_data
onnx/decoder_model_quantized.onnx
ONNX
onnx/decoder_model_quantized.onnx_data
onnx/decoder_with_past_model.onnx
ONNX
onnx/decoder_with_past_model.onnx_data
onnx/decoder_with_past_model_quantized.onnx
ONNX
onnx/decoder_with_past_model_quantized.onnx_data
quantize_config.json
special_tokens_map.json
tokenizer.json
tokenizer_config.json
vocab.json