Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Nethermind
/
Mpt-Instruct-DotNet-XS
like
0
Follow
Nethermind
2
Text Generation
Transformers
PyTorch
English
mosaic_gpt
csharp
mpt
instruct
1b
llm
.net
custom_code
License:
cc-by-sa-3.0
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
main
Mpt-Instruct-DotNet-XS
6.64 GB
1 contributor
History:
5 commits
Kabumbus
GGML models that can run f16 41.68 ms per token and q8 23.76 ms per token giving good results
56d7c99
over 2 years ago
.gitattributes
1.52 kB
initial commit
over 2 years ago
README.md
3.78 kB
Usage example
over 2 years ago
attention.py
13.8 kB
Trained model
over 2 years ago
config.json
1.08 kB
Trained model
over 2 years ago
configuration_mosaic_gpt.py
8.87 kB
Trained model
over 2 years ago
generation_config.json
91 Bytes
Trained model
over 2 years ago
ggml-model-f16.bin
2.62 GB
xet
GGML models that can run f16 41.68 ms per token and q8 23.76 ms per token giving good results
over 2 years ago
ggml-model-q8_0.bin
1.39 GB
xet
GGML models that can run f16 41.68 ms per token and q8 23.76 ms per token giving good results
over 2 years ago
gpt_blocks.py
3.11 kB
Trained model
over 2 years ago
low_precision_layernorm.py
1.27 kB
Trained model
over 2 years ago
mosaic_gpt.py
19.5 kB
Trained model
over 2 years ago
param_init_fns.py
15.9 kB
Trained model
over 2 years ago
pytorch_model.bin
2.62 GB
xet
Trained model
over 2 years ago
special_tokens_map.json
131 Bytes
Trained model
over 2 years ago
tokenizer.json
2.11 MB
Trained model
over 2 years ago
tokenizer_config.json
264 Bytes
Trained model
over 2 years ago
