Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / nlpxucan/WizardLM issues and pull requests

#101 - Has anyone fine-tuned WizardCoder-15B-V1.0 successfully?

Issue - State: open - Opened by Valdanitooooo about 1 year ago - 1 comment

#100 - 请问下78k的数据什么时候能发下呢

Issue - State: open - Opened by sri-hk about 1 year ago - 2 comments

#99 - Licensing

Issue - State: open - Opened by deepakthanam about 1 year ago - 10 comments

#98 - update demo links

Pull Request - State: closed - Opened by ChiYeungLaw about 1 year ago

#97 - cant open demo

Issue - State: open - Opened by k1tano about 1 year ago - 6 comments

#96 - Questions about tokens limit

Issue - State: open - Opened by sunzx8 about 1 year ago - 1 comment

#93 - launch.py:428:sigkill_handler] Killing subprocess 31472

Issue - State: open - Opened by lionday about 1 year ago - 2 comments

#92 - Finetune From WizardLM/WizardCoder-15B-V1.0, but No effect

Issue - State: open - Opened by iawen about 1 year ago - 2 comments

#91 - Why 30B delta is 122GB?

Issue - State: open - Opened by dittops about 1 year ago - 1 comment

#90 - update: how to reproduce 59.8

Pull Request - State: closed - Opened by ChiYeungLaw about 1 year ago

#88 - Code of weight_diff_wizard.py is not complete

Issue - State: open - Opened by cornleaf about 1 year ago - 1 comment

#86 - update demo links

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#85 - Evol-Instruct Prompts for Code？

Issue - State: open - Opened by ahong007007 over 1 year ago - 1 comment

#83 - Decode problem of 13B

Issue - State: closed - Opened by WuNein over 1 year ago - 3 comments

#82 - evol-instruct for 78k samples

Issue - State: open - Opened by wwwjs over 1 year ago - 1 comment

#81 - Get messy words when run the inference

Issue - State: open - Opened by cornleaf over 1 year ago - 1 comment

#80 - Any finetune hardware recommendation?

Issue - State: open - Opened by wangjiyang over 1 year ago - 2 comments

#79 - finetune on WizardCoder-15B-V1.0

Issue - State: open - Opened by iawen over 1 year ago - 9 comments

#78 - Multi gpu for 30B

Issue - State: open - Opened by zachNA2 over 1 year ago - 1 comment

#77 - Codebase Evol-Instruct Training/Fine-Tuning

Issue - State: open - Opened by kenfink over 1 year ago - 1 comment

#76 - load mush slower than starcoder

Issue - State: closed - Opened by aliswel-mt over 1 year ago - 2 comments

#74 - 78k evolved code instructions

Issue - State: open - Opened by ahong007007 over 1 year ago - 1 comment

#73 - update mbpp eval codes and test data

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#72 - Wizardcoder for code completion?

Issue - State: closed - Opened by andreapiso over 1 year ago - 1 comment

#71 - Are you planning WizardLM 65B model?

Issue - State: open - Opened by mirek190 over 1 year ago - 1 comment

#70 - update demo links

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#69 - [WIP] add sft

Pull Request - State: closed - Opened by L1aoXingyu over 1 year ago

#68 - update video introduction

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#67 - update demo links

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#66 - Demo 64bit bitwise test minor issue found.

Issue - State: open - Opened by Swight1423 over 1 year ago - 1 comment

#65 - Why is the 30B version not listed on the Alpaca Eval leaderboard?

Issue - State: open - Opened by shstkvch over 1 year ago - 1 comment

#64 - new format, new finetune code?

Issue - State: open - Opened by ehartford over 1 year ago - 4 comments

#63 - update paper link and citation format

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#62 - update demo links

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#61 - errors in inference_wizardcoder.py

Issue - State: open - Opened by ahong007007 over 1 year ago - 1 comment

#60 - update acknowledgement

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#59 - 78k evolved code instructions

Issue - State: open - Opened by ahong007007 over 1 year ago - 12 comments

#58 - Add acknowledgement to HumanEval evaluation script from CodeT5+ repo

Issue - State: open - Opened by yuewang-cuhk over 1 year ago - 1 comment

#57 - update wizardcoder demo link

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#56 - update demo links

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#55 - update wizardcoder readme

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#54 - WizardCoder improvement request: Train on OpenAPI specs

Issue - State: closed - Opened by gottlike over 1 year ago - 1 comment

#53 - Code Instruction Data Release

Issue - State: open - Opened by Naman-ntc over 1 year ago - 2 comments

#52 - Plans for future improvements?

Issue - State: closed - Opened by gottlike over 1 year ago

#51 - Does WizardCoder's training data have spelling mistakes?

Issue - State: closed - Opened by xzuyn over 1 year ago - 1 comment

#50 - Update main readme with WizardCoder performance

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#49 - update wizardcoder readme

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#48 - Update WizardCoder

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#47 - Falcon SFT

Issue - State: open - Opened by jiangix-paper over 1 year ago - 1 comment

#46 - how to use prompt in 7B model

Issue - State: open - Opened by Mrfranken over 1 year ago - 1 comment

#45 - Evol instruct with Dolly

Issue - State: open - Opened by prashobh07 over 1 year ago

#44 - Update nlp and code tasks performance

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#43 - Update nlp and code tasks in README.md

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#42 - Update nlp and code tasks performance

Pull Request - State: closed - Opened by ChiYeungLaw over 1 year ago

#40 - Evol-Instruct on OSS FalconLM instead of LAMA?

Issue - State: open - Opened by vackosar over 1 year ago

#39 - 有没有考虑出一版中文数据集？

Issue - State: open - Opened by Morxrc over 1 year ago - 6 comments

#38 - from train import smart_tokenizer_and_embedding_resize

Issue - State: open - Opened by HristoBuyukliev over 1 year ago - 7 comments

#37 - Gradio demo erroring at the moment

Issue - State: closed - Opened by redbrain over 1 year ago - 3 comments

#36 - request for uploading gradio demo on repo

Issue - State: open - Opened by GeorvityLabs over 1 year ago - 1 comment

#35 - Dataset for evol 250k?

Issue - State: open - Opened by teknium1 over 1 year ago - 4 comments

#34 - Missing LICENSE file

Issue - State: open - Opened by TechnologyClassroom over 1 year ago - 2 comments

#33 - Add problem solving to evol-instruct

Issue - State: open - Opened by walking-octopus over 1 year ago - 3 comments

#32 - About Gradio

Issue - State: open - Opened by YJiangcm over 1 year ago - 1 comment

#31 - Use OpenAI Evals

Issue - State: open - Opened by walking-octopus over 1 year ago

#30 - Update distributed finetuning section

Pull Request - State: closed - Opened by wenxcs over 1 year ago

#29 - Load the model using the transformer and pytorch api

Issue - State: open - Opened by ziqizhang over 1 year ago

#28 - Alaways get the exactaly same answer with the same question

Issue - State: open - Opened by peaceyourself over 1 year ago - 2 comments

#27 - Fix bug in inference_wizardlm.py

Pull Request - State: closed - Opened by dreamgonfly over 1 year ago

#26 - AssertionError: LLaMA is now in HuggingFace's main branch.

Issue - State: open - Opened by SinanAkkoyun over 1 year ago - 1 comment

#25 - Error loading fine-tuned wizard model

Issue - State: open - Opened by gabriead over 1 year ago - 5 comments

#24 - training

Issue - State: open - Opened by SoroorMa over 1 year ago - 1 comment

#23 - Missing arguments in evaluate method

Issue - State: open - Opened by gabriead over 1 year ago

#21 - Model used for generating training data?

Issue - State: open - Opened by gabriead over 1 year ago - 1 comment

#20 - how to use with Auto-gpt

Issue - State: open - Opened by sudip550 over 1 year ago - 2 comments

#19 - Updated Readme.md

Pull Request - State: closed - Opened by TheSeer507 over 1 year ago

#18 - resume_from_checkpoint

Issue - State: open - Opened by ehartford over 1 year ago - 1 comment

#17 - fix perf bug, it was bouncing rapidly between cpu and gpu

Pull Request - State: closed - Opened by ehartford over 1 year ago - 1 comment

#16 - DeepSpeed Configuration JSON

Issue - State: open - Opened by ehartford over 1 year ago - 6 comments

#15 - fine-tuning only takes 7% VRAM

Issue - State: closed - Opened by ehartford over 1 year ago - 4 comments

#14 - Failed to recognize model when trying to load it in

Issue - State: open - Opened by jcuell2 over 1 year ago - 1 comment

#13 - CMD closes after I select WizardLM as my model.

Issue - State: open - Opened by Swatman1234 over 1 year ago - 2 comments

#12 - Have you tried LoRA?

Issue - State: open - Opened by vgoklani over 1 year ago - 3 comments

#11 - can't accurately process text

Issue - State: open - Opened by arsserpentarium over 1 year ago

#10 - Clarification in the paper

Issue - State: open - Opened by LeeShiyang over 1 year ago - 2 comments

#9 - Fix misspellings in Readme

Pull Request - State: closed - Opened by tpwatson over 1 year ago

#8 - Duplications in evol_instruct_70k dataset

Issue - State: open - Opened by chintu619 over 1 year ago - 2 comments

#6 - Huggingface space replication lagging

Issue - State: open - Opened by kafischer over 1 year ago - 2 comments

#5 - Over-hyping

Issue - State: closed - Opened by aggregate1166877 over 1 year ago - 9 comments

#4 - Remove "As an AI language model..." from dataset.

Issue - State: open - Opened by generalsvr over 1 year ago - 14 comments

#3 - dumb number tokenisation

Issue - State: open - Opened by arsserpentarium over 1 year ago - 2 comments

#2 - Update README.md

Pull Request - State: closed - Opened by eltociear over 1 year ago

#1 - Can you provide the code for reproducing the evolution instruction?

Issue - State: open - Opened by bestpredicts over 1 year ago - 6 comments