1 contributor

History: 15 commits

casperhansen

Update quant_config.json

6c68c97 12 months ago

.gitattributes

1.52 kB

initial commit about 1 year ago
README.md

2.07 kB

Update README.md about 1 year ago
adapt_tokenizer.py

1.75 kB

MPT 7B 8K quantized about 1 year ago
attention.py

17.7 kB

MPT 7B 8K quantized about 1 year ago
awq_model_w4_g128.pt
Detected Pickle imports (4)
- "torch.IntStorage",
- "torch.HalfStorage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
3.76 GB
LFS

Rename mpt-7b-8k-chat-awq-w4-g128.pt to awq_model_w4_g128.pt about 1 year ago
blocks.py

2.55 kB

MPT 7B 8K quantized about 1 year ago
config.json

1.23 kB

Set initial device to cuda:0 for faster initial loading about 1 year ago
configuration_mpt.py

9.2 kB

MPT 7B 8K quantized about 1 year ago
custom_embedding.py

305 Bytes

MPT 7B 8K quantized about 1 year ago
flash_attn_triton.py

28.2 kB

MPT 7B 8K quantized about 1 year ago
generation_config.json

121 Bytes

MPT 7B 8K quantized about 1 year ago
hf_prefixlm_converter.py

27.2 kB

MPT 7B 8K quantized about 1 year ago
meta_init_context.py

3.64 kB

MPT 7B 8K quantized about 1 year ago
modeling_mpt.py

18.9 kB

MPT 7B 8K quantized about 1 year ago
norm.py

2.56 kB

MPT 7B 8K quantized about 1 year ago
param_init_fns.py

12.6 kB

MPT 7B 8K quantized about 1 year ago
pytorch_model.bin.index.json

16 kB

MPT 7B 8K quantized about 1 year ago
quant_config.json

90 Bytes

Update quant_config.json 12 months ago
special_tokens_map.json

206 Bytes

MPT 7B 8K quantized about 1 year ago
tokenizer.json

2.11 MB

MPT 7B 8K quantized about 1 year ago
tokenizer_config.json

237 Bytes

MPT 7B 8K quantized about 1 year ago

Detected Pickle imports (4)