mosaicml
/

mpt-7b-instruct

Text Generation Transformers PyTorch

mpt custom_code Composer MosaicML llm-foundry text-generation-inference

License: cc-by-sa-3.0

Model card Files Files and versions Community

Resources

View closed (53)

How to improve inference runtime performance?

#67 opened 2 months ago by

Onnx export fails when using cuda:0 as init device

#66 opened 2 months ago by

changing "max_seq_len" has no effect

#64 opened 2 months ago by

How to run on Colab through CPU ?

#63 opened 3 months ago by

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

#61 opened 3 months ago by

Prompt for summarization

#60 opened 3 months ago by

Missing the space so badly 😞

#59 opened 3 months ago by

Adding `safetensors` variant of this model

#56 opened 3 months ago by

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

#55 opened 3 months ago by

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

#53 opened 3 months ago by

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

#46 opened 3 months ago by

few shot prompting best practices/examples

#34 opened 4 months ago by

Finetuning MPT-7B-Instruct in 4-bit

#33 opened 4 months ago by

KeyError in triton implementation

#25 opened 4 months ago by