Ecosyste.ms: Issues

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

GitHub / abertsch72/unlimiformer issues and pull requests

#66 - BookSum_Full BART Baseline script/code

Issue - State: open - Opened by saxenarohit 4 months ago - 4 comments

#65 - DatasetGenerationError

Issue - State: closed - Opened by pppyb 5 months ago - 1 comment

#64 - Unable to load dataset

Issue - State: open - Opened by Ozawa333 5 months ago - 4 comments

#63 - Error in running Llama 2 generation example

Issue - State: open - Opened by OswaldHe 8 months ago

#61 - Hardware Requirement for Running Llama-2 inferences

Issue - State: open - Opened by shang-zhu 10 months ago - 2 comments

#60 - LLama2_example output random words

Issue - State: open - Opened by KerolosAtef 10 months ago - 1 comment

#59 - Can't run the provided llama2 example

Issue - State: open - Opened by KerolosAtef 11 months ago - 6 comments

#58 - GPU VRAM Usage during training

Issue - State: open - Opened by KevinD777 11 months ago - 1 comment

#57 - reproducing your results

Issue - State: open - Opened by patrickocal 12 months ago - 7 comments

#56 - Prompt with Llama-2 stops after "Loading checkpoint shards: 0%"

Issue - State: closed - Opened by XmasRock 12 months ago - 2 comments

#55 - Use of other Encode/Decoder Models

Issue - State: open - Opened by rdmerillat about 1 year ago - 8 comments

#54 - IndexError when running inference with Llama-2 model

Issue - State: closed - Opened by shang-zhu about 1 year ago - 3 comments

#53 - Why is the inference so slow?

Issue - State: closed - Opened by cckao about 1 year ago - 3 comments

#51 - Script utilizing LLM

Issue - State: open - Opened by jcgeo9 about 1 year ago - 1 comment

#50 - Why "import sled" was commented out in run.py?

Issue - State: closed - Opened by shi-kejian about 1 year ago - 4 comments

#48 - Error Encountered While Running 'run_generation.py' Script

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

#47 - About adding a prefix and input length

Issue - State: closed - Opened by apapoudakis about 1 year ago - 3 comments

#46 - Relative positions in RoPE embeddings

Issue - State: open - Opened by AshwinRamachandran2002 about 1 year ago - 2 comments

#43 - Set max_size to 128 but use 512 tokens

Issue - State: closed - Opened by adivoj about 1 year ago - 2 comments

#42 - error while training

Issue - State: closed - Opened by kekekawaii2839 about 1 year ago - 2 comments

#41 - Errors on running llama with `test_datastore`

Issue - State: closed - Opened by wywyWang about 1 year ago - 8 comments

#40 - Question:too many indices for tensor of dimension 1

Issue - State: open - Opened by Lavi11C about 1 year ago - 16 comments

#39 - API server for unlimiformer

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

#38 - Running Unlimiformer with the `forward` method

Issue - State: open - Opened by testzer0 about 1 year ago - 3 comments

#37 - Fix typos

Pull Request - State: closed - Opened by szepeviktor about 1 year ago - 2 comments

#36 - Fix changes of the training_args variable

Pull Request - State: closed - Opened by 9au5a about 1 year ago - 1 comment

#35 - Not really an issue - TrainingArguments are now immutable

Issue - State: closed - Opened by 9au5a about 1 year ago - 2 comments

#34 - support other llms?

Issue - State: closed - Opened by chaunceyliu30 about 1 year ago - 3 comments

#33 - Steps to run the code

Issue - State: open - Opened by sahulsumra about 1 year ago - 5 comments

#32 - knn_args, unlimiformer_args, tokenizer is not defined

Issue - State: closed - Opened by laeljh about 1 year ago - 1 comment

#31 - Unused variable `q_embed` in the Llama's `preprocess_query` method

Issue - State: closed - Opened by seunghyukoh about 1 year ago - 1 comment

#30 - About the method `attention_forward_hook`

Issue - State: closed - Opened by seunghyukoh about 1 year ago - 2 comments

#29 - running unlimiformer inference on multiple gpus

Issue - State: closed - Opened by kekekawaii2839 about 1 year ago - 6 comments

#28 - Unable to produce any output with llama 2 summarization example

Issue - State: open - Opened by cem2ran about 1 year ago - 1 comment

#27 - I Will suggest you simple user interface using gradio.

Issue - State: open - Opened by imrankh46 about 1 year ago - 1 comment
Labels: help wanted, good first issue

#24 - ImportError: cannot import name 'Unlimiformer' from 'unlimiformer'

Issue - State: closed - Opened by yungsinatra0 over 1 year ago - 18 comments

#23 - Can unlimiformer work with common fine-tuning methods？

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

#22 - Update README.md

Pull Request - State: closed - Opened by VeryG00dName over 1 year ago - 1 comment

#21 - Encoder Only Unlimiformer

Issue - State: closed - Opened by YHL04 over 1 year ago - 5 comments

#20 - Error while evaluating

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

#19 - Working with 8bit and 4bit quantized models

Issue - State: open - Opened by jordancole21 over 1 year ago - 10 comments
Labels: enhancement, help wanted

#18 - Support multilingual model like mt0, mBart ?

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

#17 - Reproduce the +test Unlimiformer setup

Issue - State: closed - Opened by Leonard907 over 1 year ago - 7 comments

#16 - Can unlimiformer be trained on mutiple gpus?

Issue - State: open - Opened by Muxv over 1 year ago - 1 comment
Labels: help wanted

#15 - Making Unlimiformer work with decoder models (specifically LLaMA)

Issue - State: closed - Opened by StrangeTcy over 1 year ago - 8 comments

#13 - Typing checks fail

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

#12 - Is there any example codes to run?

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

#11 - How to reproduce the paper result?

Issue - State: closed - Opened by fake-warrior8 over 1 year ago - 1 comment

#10 - Is it able to change the base model ?

Issue - State: closed - Opened by thangnm99 over 1 year ago - 3 comments
Labels: help wanted

#9 - I have created a LinkedIn post for this repo.

Issue - State: closed - Opened by hemangjoshi37a over 1 year ago - 2 comments

#8 - environment requirements

Issue - State: closed - Opened by TrieuLe0801 over 1 year ago - 1 comment

#7 - Adding a minimal inference example

Pull Request - State: closed - Opened by abertsch72 over 1 year ago - 5 comments

#6 - Run with M1 MacOS

Issue - State: open - Opened by TrieuLe0801 over 1 year ago - 4 comments
Labels: help wanted

#5 - Inference example with external model

Issue - State: closed - Opened by chris-aeviator over 1 year ago - 2 comments

#4 - Update README.md

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

#3 - run.py referencing missing file

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

#2 - Question about decoder models

Issue - State: closed - Opened by flozi00 over 1 year ago - 6 comments
Labels: help wanted

#1 - Are the model weights open-sourced?

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