Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
TheBloke
/
MPT-7B-GGML
like
21
Transformers
5 datasets
mpt
Composer
MosaicML
llm-foundry
StreamingDatasets
arxiv:
6 papers
License:
apache-2.0
Model card
Files
Files and versions
Community
4
Train
Deploy
Use this model
e4f226b
MPT-7B-GGML
2 contributors
History:
20 commits
TheBloke
Update README.md
e4f226b
over 1 year ago
.gitattributes
1.48 kB
initial commit
over 1 year ago
README.md
14 kB
Update README.md
over 1 year ago
mpt-7b.ggmlv2.fp16.bin
13.3 GB
LFS
Rename mpt7b.ggmlv2.fp16.bin to mpt-7b.ggmlv2.fp16.bin
over 1 year ago
mpt-7b.ggmlv2.q4_0.bin
4.16 GB
LFS
Rename mpt7b.ggmlv2.q4_0.bin to mpt-7b.ggmlv2.q4_0.bin
over 1 year ago
mpt-7b.ggmlv2.q4_1.bin
4.99 GB
LFS
Rename mpt7b.ggmlv2.q4_1.bin to mpt-7b.ggmlv2.q4_1.bin
over 1 year ago
mpt-7b.ggmlv2.q5_0.bin
4.57 GB
LFS
Rename mpt7b.ggmlv2.q5_0.bin to mpt-7b.ggmlv2.q5_0.bin
over 1 year ago
mpt-7b.ggmlv2.q5_1.bin
4.99 GB
LFS
Rename mpt7b.ggmlv2.q5_1.bin to mpt-7b.ggmlv2.q5_1.bin
over 1 year ago
mpt-7b.ggmlv2.q8_0.bin
7.48 GB
LFS
Rename mpt7b.ggmlv2.q8_0.bin to mpt-7b.ggmlv2.q8_0.bin
over 1 year ago