xlang-ai / instructor-embedding

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

xlang-ai/instructor-embedding Issues

Model not loading
Updated a month ago3
How the training data is divided？
Updated a month ago4
Redundant code & Tokenize issue
Updated a month ago2
KeyError `task_name`
Updated a month ago3
Improving inference time
Updated a month ago1
Some weights of the model checkpoint at /home/rnd/wmj/instructor-large/instructor-embedding/output/checkpoint-6500/ were not used when initializing T5EncoderModel: ['2.linear.weight'] - This IS expected if you are initializing T5EncoderModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing T5EncoderModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). max_seq_length 512
Updated 2 months ago
Traceback (most recent call last): File "/home/instructor-embedding/evaluation/prompt_retrieval/main_civil.py", line 15, in <module> from InstructorEmbedding import INSTRUCTOR ImportError: cannot import name 'INSTRUCTOR' from 'InstructorEmbedding' (/home/instructor-embedding/InstructorEmbedding/__init__.py)
Closed 2 months ago
fine-tune HKUNLP/instructor-embedding
Updated 2 months ago7
Phrase embeddings in context
Updated 2 months ago2
Fine-tune cross- encoder by "Instruction-Finetuned Text"
Updated 3 months ago
Are document instructions not used for evaluation?
Closed 3 months ago2
Chinese support?
Updated 3 months ago1
Why I cannot save model?
Updated 4 months ago3
You script to quantize the instructor models simply doesn't work.
Updated 4 months ago7
Discrepancy in training data versions
Updated 5 months ago
not getting exactly the same embedding for different batchsize
Updated 5 months ago5
No matching distribution found for instructor
Closed 6 months ago
LICENSE is missing copyright owner name(s) and year
Closed 6 months ago1
Are these embeddings Contextualized Embeddings ?
Updated 6 months ago1
Save and load dynamically quantized model
Updated 6 months ago4
domain adaptation method using GPL on instructor
Closed 7 months ago3
What if instruction+text merged?
Closed 7 months ago2
Different types of embedding used internally inside the tool?
Closed 7 months ago2
Evaluation settings of INSTRUCTOR
Updated 7 months ago11
Is it ok to train directly using the T5 model as a base? Are the results guaranteed?
Closed 7 months ago2
Fine-tuning for sentence comparison
Updated 7 months ago3
Pip install does not include dependencies
Closed 7 months ago2
what is the max input size?
Closed 7 months ago5
Kernel dies when calling HuggingFaceInstructEmbedding
Closed 7 months ago2
Modified MTEB Install fails - After rectification it leads to OSError
Closed 7 months ago2
Example of classification inference (Zero Shot?)
Closed 7 months ago6
Inference using TensorRT
Updated 7 months ago1
evaluate with retrained model, but bug: Some weights of the model checkpoint at /checkpoint-22000 were not used when initializing T5EncoderModel:
Closed 7 months ago5
cannot reproduce the results of INSTRUCTOR.
Closed 7 months ago2
Runtime Optimization
Updated 7 months ago1
quantization and gpu acceleration of the quantized model.
Updated 7 months ago1
Instruction for keywords retrievial
Closed 7 months ago2
How would you use instructor o find duplicate items in similar texts, e.g short bug descriptions?
Closed 7 months ago2
Inconsistency between the instruction template suggested vs that in the training data
Updated 7 months ago5
Comparative Performance Analysis: Single Dataset Fine-Tuning Versus Multi-Dataset Instruction-Based Fine-Tuning on Task A
Closed 7 months ago3
max_sequence_length and splitting text into smaller chunks
Closed 7 months ago1
pythons > 3.7?
Closed 7 months ago2
Issue with Evaluation ArguAna
Updated 7 months ago5
Production Level Updates
Updated 8 months ago2
Cosine Similarity of Anchor and Negative is not taken into consideration in Loss calculation
Closed 8 months ago1
how to parse instructions into the chroma - instructor model integration
Closed 10 months ago1
gettin oom on train
Closed a year ago1
Representing metadata and conditionally encoding text for a specific task
Closed a year ago2
Reproduction of training INSTRUCTOR
Updated a year ago4
training with deepspeed got oom
Closed a year ago