Hugging Face's logo

mosaicml
/
mpt-7b-instruct

Text Generation
Transformers
PyTorch
mpt
Composer
MosaicML
llm-foundry
custom_code
text-generation-inference
Model card Files Community
74
New discussion

Adding `safetensors` variant of this model
#74 opened 8 months ago by SFconvertbot

Adding Evaluation Results
#70 opened about 1 year ago by leaderboard-pr-bot

How to improve inference runtime performance?

3
#67 opened over 1 year ago by redraptor

Onnx export fails when using cuda:0 as init device

1
#66 opened over 1 year ago by Akshay1996

changing "max_seq_len" has no effect
#64 opened over 1 year ago by giuliogalvan

How to run on Colab through CPU ?

#63 opened over 1 year ago by deepakkaura26

Whats the input Max Token Size for MPT 7B Instruct? (Usecase - Transcript Summarization)

1
#61 opened over 1 year ago by vibhanu

Prompt for summarization
#60 opened over 1 year ago by Sven00

Missing the space so badly 😞

7
#59 opened over 1 year ago by AayushShah

Adding `safetensors` variant of this model
#56 opened over 1 year ago by eyang9002

Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack

1
#55 opened over 1 year ago by sebrahimi

Fact check: Is MPT-7b developed with Alexa Skills Kit as it just claimed in my conversation?

2
#53 opened over 1 year ago by sh37

Fixing "RuntimeError: expected scalar type Half but found Float" error

2
#46 opened over 1 year ago by marygm

few shot prompting best practices/examples

1
#34 opened over 1 year ago by bharven

Finetuning MPT-7B-Instruct in 4-bit
#33 opened over 1 year ago by rmihaylov

KeyError in triton implementation

7
#25 opened over 1 year ago by datacow