microsoft
/

dolly-v2-7b-olive-optimized

Text Generation

Model card Files Files and versions

dolly-v2-7b-olive-optimized

13.7 GB

3 contributors

History: 5 commits

pavignol2's picture

Update usage to be specific to ORT+DML

e1f7518 over 2 years ago

.gitattributes

1.53 kB

Adding .onnx_data to ignore over 2 years ago
README.md

10.2 kB

Update usage to be specific to ORT+DML over 2 years ago
_gpt_neox_layers.0_attention_rotary_emb_Constant_5_attr__value

262 kB

Initial dolly-v2-7b Olive Optimized over 2 years ago
_gpt_neox_layers.0_attention_rotary_emb_Constant_attr__value

262 kB

Initial dolly-v2-7b Olive Optimized over 2 years ago
config.json

848 Bytes

Initial dolly-v2-7b Olive Optimized over 2 years ago
decoder_model_merged.onnx

4.17 MB
xet

Initial dolly-v2-7b Olive Optimized over 2 years ago
decoder_model_merged.onnx_data

13.7 GB
xet

Initial dolly-v2-7b Olive Optimized over 2 years ago
generation_config.json

111 Bytes

Initial dolly-v2-7b Olive Optimized over 2 years ago
instruct_pipeline.py

9.28 kB

Initial dolly-v2-7b Olive Optimized over 2 years ago
special_tokens_map.json

228 Bytes

Initial dolly-v2-7b Olive Optimized over 2 years ago
tokenizer.json

2.11 MB

Initial dolly-v2-7b Olive Optimized over 2 years ago
tokenizer_config.json

264 Bytes

Initial dolly-v2-7b Olive Optimized over 2 years ago