mosaicml
/

mpt-7b

Model card Files Files and versions Community

Resources

View closed (57)

Adding Evaluation Results

#86 opened 21 days ago by

leaderboard-pr-bot

[AUTOMATED] Model Memory Requirements

#85 opened 24 days ago by

model-sizer-bot

Fine-tuning Dataset Format

#81 opened 4 months ago by

Request: DOI

#80 opened 4 months ago by

What are the installation requirements for using triton?

#79 opened 5 months ago by

test peft with wte2linear

#77 opened 5 months ago by

test peft

#76 opened 5 months ago by

test peft compatible version

#75 opened 5 months ago by

test run https://huggingface.co/eluzhnica/mpt-30b-peft-compatible/tree/main

#74 opened 5 months ago by

test commit using https://huggingface.co/cekal/mpt-7b-peft-compatible/blob/main/modeling_mpt.py

#73 opened 5 months ago by

Comet line 296-297 to remove self.model_parallel

#72 opened 5 months ago by

How should I make the fine-tuned model available as an API to call for others? Without downloading the whole model

#71 opened 5 months ago by

How to append new token and train?

#70 opened 5 months ago by

fix HPU could not handle float16 in attention.py.

#68 opened 5 months ago by

"MPTForCausalLM not supported" error when using pipeline, but not when using from_pretrained

#67 opened 6 months ago by

After installing triton, running pipe() return "fatal error: cuda.h: No such file or directory " and "CalledProcessError: Command '['/usr/bin/gcc'...."

#66 opened 6 months ago by

Adding `safetensors` variant of this model

#65 opened 6 months ago by

Converting To Flax

#64 opened 6 months ago by

MPT-7b on colab - RAM of GPU not used

#50 opened 6 months ago by

Can support MPS device type?

#48 opened 6 months ago by

upstream-replit-updates

#43 opened 7 months ago by

Merge cekal/mpt-7b-peft-compatible

#42 opened 7 months ago by

Support gradient checkpointing

#41 opened 7 months ago by

Issue training With Triton

#40 opened 7 months ago by

MikeyBelllissimo

Finetuning MPT-7B in 4-bit

#39 opened 7 months ago by

attn_impl

#27 opened 7 months ago by

Fixes for PEFT Tuning based on iwalton3

#25 opened 7 months ago by

Can this be fine-tuned using Amazon SageMaker or run on a AMD GPU that is not CUDA-enabled?

#18 opened 7 months ago by

[Experiment] MPT 7B + LangChain Custom LLM + transformers.accelerator, on a POTATO

#16 opened 7 months ago by