Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
jprafael
/
mpt-7b-instruct-sharded
like
3
Text Generation
Transformers
PyTorch
the_pile_books3
English
mpt
mosaicML
sharded
instruct
custom_code
text-generation-inference
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
mpt-7b-instruct-sharded
4 contributors
History:
19 commits
jprafael
Update README.md
7453303
over 1 year ago
.gitattributes
Safe
1.96 kB
add sharded checkpoint
over 1 year ago
README.md
Safe
1.82 kB
Update README.md
over 1 year ago
adapt_tokenizer.py
Safe
1.76 kB
🎨 format for readability
over 1 year ago
attention.py
Safe
18.1 kB
🎨 format for readability
over 1 year ago
blocks.py
Safe
2.99 kB
🎨 format for readability
over 1 year ago
config.json
Safe
1.27 kB
Replace model with mpt-7b-instruct, loaded in f16 and sharded to 2GB chunks
over 1 year ago
configuration_mpt.py
Safe
9.87 kB
🎨 format for readability
over 1 year ago
generation_config.json
Safe
91 Bytes
Replace model with mpt-7b-instruct, loaded in f16 and sharded to 2GB chunks
over 1 year ago
hf_prefixlm_converter.py
Safe
31.4 kB
🎨 format for readability
over 1 year ago
meta_init_context.py
Safe
3.81 kB
🎨 format for readability
over 1 year ago
modeling_mpt.py
Safe
20.2 kB
✨ gradient checkpointing
over 1 year ago
norm.py
Safe
3.06 kB
🎨 format for readability
over 1 year ago
param_init_fns.py
Safe
14.3 kB
🎨 format for readability
over 1 year ago
pytorch_model-00001-of-00007.bin
Safe
1.89 GB
LFS
Replace model with mpt-7b-instruct, loaded in f16 and sharded to 2GB chunks
over 1 year ago
pytorch_model-00002-of-00007.bin
Safe
1.88 GB
LFS
Replace model with mpt-7b-instruct, loaded in f16 and sharded to 2GB chunks
over 1 year ago
pytorch_model-00003-of-00007.bin
Safe
1.98 GB
LFS
Replace model with mpt-7b-instruct, loaded in f16 and sharded to 2GB chunks
over 1 year ago
pytorch_model-00004-of-00007.bin
Safe
1.91 GB
LFS
Replace model with mpt-7b-instruct, loaded in f16 and sharded to 2GB chunks
over 1 year ago
pytorch_model-00005-of-00007.bin
Safe
1.88 GB
LFS
Replace model with mpt-7b-instruct, loaded in f16 and sharded to 2GB chunks
over 1 year ago
pytorch_model-00006-of-00007.bin
Safe
1.88 GB
LFS
Replace model with mpt-7b-instruct, loaded in f16 and sharded to 2GB chunks
over 1 year ago
pytorch_model-00007-of-00007.bin
Safe
1.88 GB
LFS
Replace model with mpt-7b-instruct, loaded in f16 and sharded to 2GB chunks
over 1 year ago
pytorch_model.bin.index.json
Safe
16 kB
add sharded checkpoint
over 1 year ago
requirements.txt
Safe
37 Bytes
🔧 add a requirements from pipreqs
over 1 year ago
special_tokens_map.json
Safe
99 Bytes
add sharded checkpoint
over 1 year ago
tokenizer.json
Safe
2.11 MB
add sharded checkpoint
over 1 year ago
tokenizer_config.json
Safe
264 Bytes
add sharded checkpoint
over 1 year ago
