Intel
/

phi-2-int4-inc

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

intel/auto-round

Model card Files Files and versions Community

4 contributors

History: 14 commits

wenhuach's picture

replace with sym quantization as there is a large accuracy drop due to kernel issue

f201b74 6 months ago

.gitattributes

1.52 kB

initial commit 9 months ago
README.md

3.41 kB

replace with sym quantization as there is a large accuracy drop due to kernel issue 6 months ago
added_tokens.json

1.08 kB

first commit 9 months ago
config.json

1.25 kB

replace with sym quantization as there is a large accuracy drop due to kernel issue 6 months ago
configuration_phi.py

2.03 kB

first commit 9 months ago
merges.txt

456 kB

first commit 9 months ago
model.safetensors

1.84 GB
LFS

replace with sym quantization as there is a large accuracy drop due to kernel issue 6 months ago
modeling_phi.py

33.4 kB

first commit 9 months ago
quantize_config.json

464 Bytes

replace with sym quantization as there is a large accuracy drop due to kernel issue 6 months ago
special_tokens_map.json

441 Bytes

first commit 9 months ago
tokenizer.json

2.11 MB

replace with sym quantization as there is a large accuracy drop due to kernel issue 6 months ago
tokenizer_config.json

7.37 kB

replace with sym quantization as there is a large accuracy drop due to kernel issue 6 months ago
vocab.json

798 kB

first commit 9 months ago