curtis-sun
/

diag-baichuan2-4bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

diag-baichuan2-4bit

1 contributor

History: 4 commits

curtis-sun's picture

update tokenizer according to https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat/discussions/18

c5b3968 verified about 1 year ago

.gitattributes

1.52 kB

initial commit about 1 year ago
Baichuan2 模型社区许可协议.pdf

258 kB

init about 1 year ago
Community License for Baichuan2 Model.pdf

203 kB

init about 1 year ago
README.md

67 Bytes

initial commit about 1 year ago
config.json

1.15 kB

init about 1 year ago
configuration_baichuan.py

1.56 kB

init about 1 year ago
generation_config.json

225 Bytes

init about 1 year ago
generation_utils.py

2.97 kB

init about 1 year ago
modeling_baichuan.py

32.5 kB

init about 1 year ago
pytorch_model.bin
Detected Pickle imports (10)
- "bitsandbytes.functional.QuantState",
- "torch.Size",
- "torch.ByteStorage",
- "torch.float32",
- "collections.OrderedDict",
- "torch._utils._rebuild_parameter",
- "torch.HalfStorage",
- "torch._utils._rebuild_tensor_v2",
- "torch.FloatStorage",
- "torch.float16"
How to fix it?
9.08 GB
LFS

init about 1 year ago
quantizer.py

9.19 kB

init about 1 year ago
special_tokens_map.json

544 Bytes

init about 1 year ago
tokenization_baichuan.py

9.03 kB

update tokenizer according to https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat/discussions/18 about 1 year ago
tokenizer.model

2 MB
LFS

init about 1 year ago
tokenizer_config.json

954 Bytes

init about 1 year ago