MinishLab/model2vec issues and pull requests

#170 - Question - how does custom vocabulary work?

Issue - State: open - Opened by S-C-H 3 days ago - 1 comment

#169 - docs: Update plot

Pull Request - State: closed - Opened by Pringled 3 days ago - 1 comment

#168 - Reproducing evaluation results

Issue - State: closed - Opened by sky-2002 4 days ago - 7 comments

#167 - docs: Added new model results

Pull Request - State: closed - Opened by Pringled 4 days ago - 1 comment

#166 - increase version

Pull Request - State: closed - Opened by stephantul 6 days ago

#165 - feat: Improve distill for modernBERT

Pull Request - State: closed - Opened by stephantul 6 days ago

#164 - feat: Add optional embedding normalization to StaticModel loading

Pull Request - State: closed - Opened by davidberenstein1957 8 days ago

#163 - feat: float pca dims

Pull Request - State: closed - Opened by stephantul 10 days ago - 1 comment

#162 - fix: fix typing issue

Pull Request - State: closed - Opened by stephantul 10 days ago - 1 comment

#161 - remove unnecessary import

Pull Request - State: closed - Opened by stephantul 10 days ago - 1 comment

#160 - distill

Issue - State: closed - Opened by Mahhos 10 days ago - 10 comments

#159 - remove deduplication tutorial

Pull Request - State: closed - Opened by stephantul 10 days ago - 1 comment

#158 - fix: issue with modernbert tokenizer, add token pattern to _distill

Pull Request - State: closed - Opened by stephantul 10 days ago - 1 comment

#157 - docs: fix docstrings in distill

Pull Request - State: closed - Opened by stephantul 11 days ago - 1 comment

#156 - [Minor] Change fn name and docstring to use `model` instead of `model_name` where expected `PreTrainedModel`

Issue - State: closed - Opened by bhavnicksm 11 days ago

#155 - Bump version

Pull Request - State: closed - Opened by Pringled 12 days ago

#154 - feat: Updated save_pretrained to save sentence-transformers compatible models

Pull Request - State: closed - Opened by Pringled 12 days ago - 1 comment

#153 - may you clarify how you use Zipf

Issue - State: open - Opened by Sandy4321 16 days ago - 8 comments

#152 - Bump version

Pull Request - State: closed - Opened by Pringled 18 days ago

#151 - Add loading from st

Pull Request - State: closed - Opened by stephantul 18 days ago - 1 comment

#150 - Bump version

Pull Request - State: closed - Opened by Pringled 22 days ago - 1 comment

#149 - fix: Fixed local distillation

Pull Request - State: closed - Opened by Pringled 23 days ago - 1 comment

#148 - Load model without having to call `model_info`

Issue - State: closed - Opened by Bourhano 23 days ago - 4 comments
Labels: bug

#147 - Langchain Integration

Issue - State: closed - Opened by blacksmithop 27 days ago - 2 comments

#146 - Bump version

Pull Request - State: closed - Opened by Pringled 28 days ago - 1 comment

#145 - docs: update README.md

Pull Request - State: closed - Opened by eltociear 29 days ago

#144 - fix: Removed unneeded tokenize call

Pull Request - State: closed - Opened by Pringled about 1 month ago - 1 comment

#143 - docs: Add langchain example

Pull Request - State: closed - Opened by Pringled about 1 month ago - 1 comment

#142 - feat: Added multiprocessing threshold parameter

Pull Request - State: closed - Opened by Pringled about 1 month ago - 1 comment

#141 - feat: Add multiprocessing

Pull Request - State: closed - Opened by Pringled about 1 month ago - 2 comments

#140 - Add fittable

Pull Request - State: open - Opened by stephantul about 1 month ago - 1 comment

#139 - Multiprocess encoding for speed

Issue - State: closed - Opened by davidmezzetti about 1 month ago - 11 comments

#138 - feat: add support for pattern for unused tokens.

Pull Request - State: closed - Opened by stephantul about 1 month ago - 1 comment

#137 - Using Model2Vec for Token Classification

Issue - State: closed - Opened by kelayamatoz 2 months ago - 2 comments
Labels: question

#136 - feat: Updated config values

Pull Request - State: closed - Opened by Pringled 2 months ago - 1 comment

#135 - Vocabulary option for models with sentencepiece tokenizer.

Issue - State: closed - Opened by trpstra 2 months ago - 4 comments

#134 - Add `model2vec` to config.json

Issue - State: closed - Opened by davidmezzetti 2 months ago - 6 comments
Labels: enhancement

#133 - feat: Added semantic chunking with chonkie tutorial

Pull Request - State: closed - Opened by Pringled 2 months ago - 1 comment

#132 - About the reported scores on MSMARCO

Issue - State: closed - Opened by twadada 2 months ago - 1 comment

#131 - docs: Reworked documentation

Pull Request - State: closed - Opened by Pringled 2 months ago - 1 comment

#130 - docs: Add txtai integration docs

Pull Request - State: closed - Opened by Pringled 2 months ago

#129 - Bumped version

Pull Request - State: closed - Opened by Pringled 2 months ago

#128 - fix: Added jinja2 requirement

Pull Request - State: closed - Opened by Pringled 2 months ago - 1 comment

#127 - docs: Updated slogan

Pull Request - State: closed - Opened by Pringled 2 months ago - 1 comment

#126 - docs: Added langchain example

Pull Request - State: closed - Opened by Pringled 3 months ago - 1 comment

#125 - docs: Updated results table

Pull Request - State: closed - Opened by Pringled 3 months ago - 1 comment

#124 - fix: Fixed CI

Pull Request - State: closed - Opened by Pringled 3 months ago - 1 comment

#123 - Illegal config.json in the huggingface ecosystem!

Issue - State: closed - Opened by michaelfeil 3 months ago - 3 comments
Labels: question

#122 - docs: Update readme

Pull Request - State: closed - Opened by Pringled 3 months ago - 1 comment

#121 - Bump version

Pull Request - State: closed - Opened by Pringled 3 months ago - 1 comment

#120 - fix: Fixed package extras bug

Pull Request - State: closed - Opened by Pringled 3 months ago - 1 comment

#119 - feat: Added onnx and tokenizer files support script

Pull Request - State: closed - Opened by Pringled 3 months ago - 1 comment

#118 - Bump version

Pull Request - State: closed - Opened by Pringled 3 months ago - 1 comment

#117 - docs: Updated plot

Pull Request - State: closed - Opened by Pringled 3 months ago - 1 comment

#116 - docs: Add tokenlearn results

Pull Request - State: closed - Opened by Pringled 3 months ago - 1 comment

#115 - Question: Object has no attribute 'backend_tokenizer'`

Issue - State: closed - Opened by FahadEbrahim 3 months ago - 2 comments
Labels: bug

#114 - fix: normalize would lead to NaN for empty docs

Pull Request - State: closed - Opened by stephantul 3 months ago - 1 comment

#113 - feat: make encode_batch_fast optional

Pull Request - State: closed - Opened by stephantul 3 months ago - 1 comment

#112 - docs: Fixed broken links

Pull Request - State: closed - Opened by Pringled 3 months ago - 1 comment

#111 - AttributeError: 'tokenizers.Tokenizer' object has no attribute 'encode_batch_fast'

Issue - State: closed - Opened by su-park 3 months ago - 2 comments
Labels: bug, question

#110 - HFValidationError using custom model

Issue - State: closed - Opened by tomsquest 3 months ago - 3 comments
Labels: question

#109 - fix: don't rely on reported vocab size, log warning if inconsistent

Pull Request - State: closed - Opened by stephantul 3 months ago - 2 comments

#108 - Number of tokens (151646) does not match number of vectors (151643)

Issue - State: closed - Opened by su-park 3 months ago - 5 comments
Labels: bug

#107 - fix: update added tokens to be more agnostic

Pull Request - State: closed - Opened by stephantul 3 months ago - 1 comment

#106 - KeyError: 'special_tokens'"

Issue - State: closed - Opened by david-waterworth 3 months ago - 4 comments
Labels: bug

#105 - Support for LLM2VEC models?

Issue - State: closed - Opened by sandeep-krutrim 3 months ago - 2 comments
Labels: enhancement

#104 - increment version

Pull Request - State: closed - Opened by stephantul 3 months ago - 1 comment

#103 - docs: Fix broken link

Pull Request - State: closed - Opened by Pringled 4 months ago - 1 comment

#102 - docs: Added results link

Pull Request - State: closed - Opened by Pringled 4 months ago - 1 comment

#101 - fix: Reverted eos bos change

Pull Request - State: closed - Opened by Pringled 4 months ago - 2 comments

#99 - fix: rename show progress bar argument

Pull Request - State: closed - Opened by stephantul 4 months ago - 1 comment

#98 - enh: remove CLI command

Pull Request - State: closed - Opened by stephantul 4 months ago - 1 comment

#97 - WordLlama Vs. Model2Vec

Issue - State: closed - Opened by loretoparisi 4 months ago - 7 comments
Labels: question

#96 - feat: Add python3.9 support

Pull Request - State: closed - Opened by Pringled 4 months ago - 1 comment

#95 - Python 3.9 Support?

Issue - State: closed - Opened by davidmezzetti 4 months ago - 6 comments
Labels: enhancement

#94 - docs: Updated slogan

Pull Request - State: closed - Opened by Pringled 4 months ago - 1 comment

#92 - enhancement: Add explained variance messages

Pull Request - State: closed - Opened by stephantul 4 months ago - 1 comment

#91 - enhancement: Add dynamic version

Pull Request - State: closed - Opened by stephantul 4 months ago

#90 - Unexpected keyword argument 'token_type_ids' on distilling sentence-transformers/distiluse-base-multilingual-cased-v2

Issue - State: closed - Opened by AltamashRafiq 4 months ago - 4 comments
Labels: bug

#89 - feat: faster tokenization

Pull Request - State: closed - Opened by stephantul 4 months ago - 1 comment

#88 - feat: local loading

Pull Request - State: closed - Opened by stephantul 4 months ago - 1 comment

#87 - feat: Numpy inference

Pull Request - State: closed - Opened by stephantul 4 months ago - 1 comment

#86 - fix: move tensor to cpu

Pull Request - State: closed - Opened by stephantul 4 months ago - 1 comment

#85 - Potential tokenizer ordering issue

Issue - State: closed - Opened by zechengz 4 months ago - 2 comments
Labels: question

#84 - docs: Fixed broken link

Pull Request - State: closed - Opened by Pringled 4 months ago - 1 comment

#82 - docs: Move results and add blogpost

Pull Request - State: closed - Opened by Pringled 4 months ago - 1 comment

#81 - docs: Update readme

Pull Request - State: closed - Opened by Pringled 4 months ago - 1 comment

#80 - docs: Added Sentence Transformers example code

Pull Request - State: closed - Opened by Pringled 4 months ago - 1 comment

#79 - AttributeError: 'NoneType' object has no attribute 'get'

Issue - State: closed - Opened by aoezdTchibo 4 months ago - 2 comments

#78 - Fix distill model bos and eos token

Pull Request - State: closed - Opened by zechengz 4 months ago

#77 - fix: Fix token type ids not supported

Pull Request - State: closed - Opened by Pringled 4 months ago - 1 comment

#75 - Integration in other tools: cli & js (transformers.js)

Issue - State: closed - Opened by do-me 4 months ago - 10 comments
Labels: enhancement

GitHub / MinishLab/model2vec issues and pull requests