Resources

View closed (20)

Adding `safetensors` variant of this model

#34 opened 6 months ago by

SFconvertbot

Update replit_lm_tokenizer.py

#33 opened 7 months ago by

dobbySeo

Adapt code completion to SDK private language

#32 opened 12 months ago by

tomasmc

🚩 Integrate with fastChat ?

#31 opened about 1 year ago by

fengcaiwen

How to use GPU instead of CPU ? "you are using config.init_device='cpu', but you can also use config.init_device="meta"

#30 opened over 1 year ago by

ali-issa

GGML quantize script?

#29 opened over 1 year ago by

MichelNivard

Fix typos in README

#28 opened over 1 year ago by

madhavatreplit

Error when using attn_impl triton

#27 opened over 1 year ago by

Wraken

Add eos_token_id to config

#26 opened over 1 year ago by

madhavatreplit

Update generation_config.json

#25 opened over 1 year ago by

madhavatreplit

How to fill in the middle code?

#24 opened over 1 year ago by

realnex

activate use_cache to speed up inference

#23 opened over 1 year ago by

loubnabnl

How to train it with qlora?

#22 opened over 1 year ago by

Sardar

Triton is slower?

#21 opened over 1 year ago by

doguaraci

Update README for 8-bit and 4-bit

#20 opened over 1 year ago by

madhavatreplit

Update modeling_mpt.py

#19 opened over 1 year ago by

0xGrrr

Does this work with HF Inference API?

#18 opened over 1 year ago by

sagardesai

Update weights to MPT

#17 opened over 1 year ago by

madhavatreplit

Convert ReplitLM to MPT

#16 opened over 1 year ago by

madhavatreplit

Code to Code translation

#15 opened over 1 year ago by

tusharpiku

Speed UP method

#14 opened over 1 year ago by

luoji12345

huggigfacemodel deployment

#13 opened over 1 year ago by

arminnorouzi

ReplitLM does not support generation with right padding

#12 opened over 1 year ago by

merlinarer

Dataset Details

#11 opened over 1 year ago by

joaogui1

Question about the Code model

#10 opened over 1 year ago by

ComradeCat

RuntimeError: Device does not support shared memory of 98304bytes

#9 opened over 1 year ago by

leojames

Can use torch for attention implementation?

#8 opened over 1 year ago by

LouiSum

how to run the model locally?

#7 opened over 1 year ago by

828CFXLpyz

Expected minimum hardware requirements for inference?

#6 opened over 1 year ago by

zeroing

Update README.md

#5 opened over 1 year ago by

pirroh

Fine-tuned model

#4 opened over 1 year ago by

lentan

Update generation_config.json

#3 opened over 1 year ago by

madhavatreplit

Update config.json

#2 opened over 1 year ago by

madhavatreplit

Add files for release

#1 opened over 1 year ago by

madhavatreplit