๐ Easy Fine-Tuning with Hugging Face SQL Console, Notebook Creator, and SFT
โข
12
Andrea Soria PRO
asoria
AI & ML interests
Maintainer of ๐คDatasets: Data processing
Recent Activity
liked
a dataset
7 days ago
datasets-examples/doc-video-1
updated
a dataset
8 days ago
asoria/webdataset_test
liked
a dataset
8 days ago
xjh19972/boson-nighttime
Articles
Organizations
asoria's activity
reacted to
cfahlgren1's
post with ๐ฅ๐
23 days ago
Post
2989
We just dropped an LLM inside the SQL Console ๐คฏ
The amazing, new Qwen/Qwen2.5-Coder-32B-Instruct model can now write SQL for any Hugging Face dataset โจ
It's 2025, you shouldn't be hand writing SQL! This is a big step in making it where anyone can do in depth analysis on a dataset. Let us know what you think ๐ค
The amazing, new Qwen/Qwen2.5-Coder-32B-Instruct model can now write SQL for any Hugging Face dataset โจ
It's 2025, you shouldn't be hand writing SQL! This is a big step in making it where anyone can do in depth analysis on a dataset. Let us know what you think ๐ค
posted
an
update
about 2 months ago
Post
1802
๐ Exploring Topic Modeling with BERTopic ๐ค
When you come across an interesting dataset, you often wonder:
Which topics frequently appear in these documents? ๐ค
What is this data really about? ๐
Topic modeling helps answer these questions by identifying recurring themes within a collection of documents. This process enables quick and efficient exploratory data analysis.
Iโve been working on an app that leverages BERTopic, a flexible framework designed for topic modeling. Its modularity makes BERTopic powerful, allowing you to switch components with your preferred algorithms. It also supports handling large datasets efficiently by merging models using the BERTopic.merge_models approach. ๐
๐ How do we make this work?
Hereโs the stack weโre using:
๐ Data Source โก๏ธ Hugging Face datasets with DuckDB for retrieval
๐ง Text Embeddings โก๏ธ Sentence Transformers (all-MiniLM-L6-v2)
โก Dimensionality Reduction โก๏ธ RAPIDS cuML UMAP for GPU-accelerated performance
๐ Clustering โก๏ธ RAPIDS cuML HDBSCAN for fast clustering
โ๏ธ Tokenization โก๏ธ CountVectorizer
๐ง Representation Tuning โก๏ธ KeyBERTInspired + Hugging Face Inference Client with Meta-Llama-3-8B-Instruct
๐ Visualization โก๏ธ Datamapplot library
Check out the space and see how you can quickly generate topics from your dataset: datasets-topics/topics-generator
Powered by @MaartenGr - BERTopic
When you come across an interesting dataset, you often wonder:
Which topics frequently appear in these documents? ๐ค
What is this data really about? ๐
Topic modeling helps answer these questions by identifying recurring themes within a collection of documents. This process enables quick and efficient exploratory data analysis.
Iโve been working on an app that leverages BERTopic, a flexible framework designed for topic modeling. Its modularity makes BERTopic powerful, allowing you to switch components with your preferred algorithms. It also supports handling large datasets efficiently by merging models using the BERTopic.merge_models approach. ๐
๐ How do we make this work?
Hereโs the stack weโre using:
๐ Data Source โก๏ธ Hugging Face datasets with DuckDB for retrieval
๐ง Text Embeddings โก๏ธ Sentence Transformers (all-MiniLM-L6-v2)
โก Dimensionality Reduction โก๏ธ RAPIDS cuML UMAP for GPU-accelerated performance
๐ Clustering โก๏ธ RAPIDS cuML HDBSCAN for fast clustering
โ๏ธ Tokenization โก๏ธ CountVectorizer
๐ง Representation Tuning โก๏ธ KeyBERTInspired + Hugging Face Inference Client with Meta-Llama-3-8B-Instruct
๐ Visualization โก๏ธ Datamapplot library
Check out the space and see how you can quickly generate topics from your dataset: datasets-topics/topics-generator
Powered by @MaartenGr - BERTopic
reacted to
celinah's
post with โค๏ธ
2 months ago
Post
1100
๐ฃ ๐๐๐๐๐๐๐๐๐๐๐_๐๐๐ v0.26.0 is out with some new features and improvements!
โจ ๐ง๐ผ๐ฝ ๐๐ถ๐ด๐ต๐น๐ถ๐ด๐ต๐๐:
- ๐ย Multiple access tokens support: Easily manage multiple access tokens with new CLI commands. Perfect for handling multiple tokens with specific permissions in production or when collaborating with external teams.
- ๐ผ๏ธ Conversational VLMs inference is now supported withย InferenceClient's chat completion!
- ๐ Daily Papers API: Seamlessly search and retrieve detailed paper information from the Hub!
Weโve also introduced multiple bug fixes and quality-of-life improvements - thanks to the awesome contributions from our community! ๐ค
Check out the release notes here: Wauplin/huggingface_hub#9
and you can try it out now ๐
โจ ๐ง๐ผ๐ฝ ๐๐ถ๐ด๐ต๐น๐ถ๐ด๐ต๐๐:
- ๐ย Multiple access tokens support: Easily manage multiple access tokens with new CLI commands. Perfect for handling multiple tokens with specific permissions in production or when collaborating with external teams.
- ๐ผ๏ธ Conversational VLMs inference is now supported withย InferenceClient's chat completion!
- ๐ Daily Papers API: Seamlessly search and retrieve detailed paper information from the Hub!
Weโve also introduced multiple bug fixes and quality-of-life improvements - thanks to the awesome contributions from our community! ๐ค
Check out the release notes here: Wauplin/huggingface_hub#9
and you can try it out now ๐
pip install huggingface_hub==0.26.0
reacted to
davidberenstein1957's
post with ๐ฅ
3 months ago
Post
1439
Want to get familiar with llama 3.2 and an actual example of structured data generation? Try out the Google Colab I created.
Notebook: https://colab.research.google.com/drive/1nHNXUbgwRMyjFeBZbQvNLqaXGkqE4Wcs?usp=sharing
Model: hugging-quants/Llama-3.2-3B-Instruct-Q8_0-GGUF
Dataset: argilla/FinePersonas-v0.1
Library: https://github.com/argilla-io/distilabel
Notebook: https://colab.research.google.com/drive/1nHNXUbgwRMyjFeBZbQvNLqaXGkqE4Wcs?usp=sharing
Model: hugging-quants/Llama-3.2-3B-Instruct-Q8_0-GGUF
Dataset: argilla/FinePersonas-v0.1
Library: https://github.com/argilla-io/distilabel
reacted to
anakin87's
post with ๐
3 months ago
Post
1734
๐ต๐ป ๐๐ ๐๐ง๐ญ๐ข๐ ๐๐๐ ๐ฐ๐ข๐ญ๐ก ๐ฆ ๐๐ฅ๐๐ฆ๐ 3.2
I was excited to explore Llama 3.2, but as a simple ๐ช๐บ EU guy, I don't have access to Meta's multimodal models ๐ฟ
๐ค So I thought: why not challenge the small 3B text model with Agentic RAG?
๐ฏ The plan:
- Build a system that tries to answer questions using a knowledge base.
- If the documents don't contain the answer, use Web search for additional context.
Check out my experimental notebook here: ๐ https://colab.research.google.com/github/deepset-ai/haystack-cookbook/blob/main/notebooks/llama32_agentic_rag.ipynb
My stack:
๐๏ธ haystack (https://haystack.deepset.ai/): open-source LLM orchestration framework
๐ฆ meta-llama/Llama-3.2-3B-Instruct
๐ฆ๐ free DuckDuckGo API, integrated with Haystack
โจ ๐๐ฉ๐ฆ ๐ณ๐ฆ๐ด๐ถ๐ญ๐ต๐ด? ๐๐ฏ๐ค๐ฐ๐ถ๐ณ๐ข๐จ๐ช๐ฏ๐จ - ๐ข ๐ง๐ฆ๐ธ ๐ฎ๐ฐ๐ฏ๐ต๐ฉ๐ด ๐ข๐จ๐ฐ, ๐ต๐ฉ๐ช๐ด ๐ญ๐ฆ๐ท๐ฆ๐ญ ๐ฐ๐ง ๐ฑ๐ฆ๐ณ๐ง๐ฐ๐ณ๐ฎ๐ข๐ฏ๐ค๐ฆ ๐ง๐ณ๐ฐ๐ฎ ๐ข ๐ด๐ฎ๐ข๐ญ๐ญ ๐ฎ๐ฐ๐ฅ๐ฆ๐ญ ๐ธ๐ฐ๐ถ๐ญ๐ฅ'๐ท๐ฆ ๐ฃ๐ฆ๐ฆ๐ฏ ๐ถ๐ฏ๐ต๐ฉ๐ช๐ฏ๐ฌ๐ข๐ฃ๐ญ๐ฆ!
This probably reflects the impressive IFEval score of the model (comparable to Llama 3.1 8B).
I was excited to explore Llama 3.2, but as a simple ๐ช๐บ EU guy, I don't have access to Meta's multimodal models ๐ฟ
๐ค So I thought: why not challenge the small 3B text model with Agentic RAG?
๐ฏ The plan:
- Build a system that tries to answer questions using a knowledge base.
- If the documents don't contain the answer, use Web search for additional context.
Check out my experimental notebook here: ๐ https://colab.research.google.com/github/deepset-ai/haystack-cookbook/blob/main/notebooks/llama32_agentic_rag.ipynb
My stack:
๐๏ธ haystack (https://haystack.deepset.ai/): open-source LLM orchestration framework
๐ฆ meta-llama/Llama-3.2-3B-Instruct
๐ฆ๐ free DuckDuckGo API, integrated with Haystack
โจ ๐๐ฉ๐ฆ ๐ณ๐ฆ๐ด๐ถ๐ญ๐ต๐ด? ๐๐ฏ๐ค๐ฐ๐ถ๐ณ๐ข๐จ๐ช๐ฏ๐จ - ๐ข ๐ง๐ฆ๐ธ ๐ฎ๐ฐ๐ฏ๐ต๐ฉ๐ด ๐ข๐จ๐ฐ, ๐ต๐ฉ๐ช๐ด ๐ญ๐ฆ๐ท๐ฆ๐ญ ๐ฐ๐ง ๐ฑ๐ฆ๐ณ๐ง๐ฐ๐ณ๐ฎ๐ข๐ฏ๐ค๐ฆ ๐ง๐ณ๐ฐ๐ฎ ๐ข ๐ด๐ฎ๐ข๐ญ๐ญ ๐ฎ๐ฐ๐ฅ๐ฆ๐ญ ๐ธ๐ฐ๐ถ๐ญ๐ฅ'๐ท๐ฆ ๐ฃ๐ฆ๐ฆ๐ฏ ๐ถ๐ฏ๐ต๐ฉ๐ช๐ฏ๐ฌ๐ข๐ฃ๐ญ๐ฆ!
This probably reflects the impressive IFEval score of the model (comparable to Llama 3.1 8B).
posted
an
update
3 months ago
Post
2459
๐ I wrote a tutorial on how to get started with the fine-tuning process using Hugging Face tools, providing an end-to-end workflow.
The tutorial covers creating a new dataset using the new SQL Console ๐ข and fine-tuning a model with SFT, guided by the Notebook Creator App ๐.
๐ You can read the full article here:
https://huggingface.co./blog/asoria/easy-fine-tuning-with-hf
asoria/auto-notebook-creator
The tutorial covers creating a new dataset using the new SQL Console ๐ข and fine-tuning a model with SFT, guided by the Notebook Creator App ๐.
๐ You can read the full article here:
https://huggingface.co./blog/asoria/easy-fine-tuning-with-hf
asoria/auto-notebook-creator
posted
an
update
3 months ago
Post
961
๐ Excited to share the latest update to the Notebook Creator Tool!
Now with basic fine-tuning support using Supervised Fine-Tuning! ๐ฏ
How it works:
1๏ธโฃ Choose your Hugging Face dataset and notebook type (SFT)
2๏ธโฃ Automatically generate your training notebook
3๏ธโฃ Start fine-tuning with your data!
Link to the app ๐ https://lnkd.in/e_3nmWrB
๐ก Want to contribute with new notebooks? ๐https://lnkd.in/eWcZ92dS
Now with basic fine-tuning support using Supervised Fine-Tuning! ๐ฏ
How it works:
1๏ธโฃ Choose your Hugging Face dataset and notebook type (SFT)
2๏ธโฃ Automatically generate your training notebook
3๏ธโฃ Start fine-tuning with your data!
Link to the app ๐ https://lnkd.in/e_3nmWrB
๐ก Want to contribute with new notebooks? ๐https://lnkd.in/eWcZ92dS
reacted to
m-ric's
post with ๐
3 months ago
Post
1651
๐๐ฟ๐ฒ ๐๐ด๐ฒ๐ป๐๐ ๐ฐ๐ฎ๐ฝ๐ฎ๐ฏ๐น๐ฒ ๐ฒ๐ป๐ผ๐๐ด๐ต ๐ณ๐ผ๐ฟ ๐๐ฎ๐๐ฎ ๐ฆ๐ฐ๐ถ๐ฒ๐ป๐ฐ๐ฒ? โ ๐ ๐ฒ๐ฎ๐๐๐ฟ๐ฒ ๐๐ต๐ฒ๐ถ๐ฟ ๐ฝ๐ฒ๐ฟ๐ณ๐ผ๐ฟ๐บ๐ฎ๐ป๐ฐ๐ฒ ๐๐ถ๐๐ต ๐๐ฆ๐๐ฒ๐ป๐ฐ๐ต ๐
A team from Tencent AI wanted to evaluate agentic systems on data science (DS) tasks : but they noticed that existing agentic benchmarks were severely limited in several aspects: they were limited to text and did not include tables or images, were only specific to certain packages, only performed exact match evaluationโฆ
โก๏ธ So they set out to build a much more exhaustive approach, to finally make the definitive DS agent benchmark.
๐ง๐ต๐ฒ ๐๐ฆ๐๐ฒ๐ป๐ฐ๐ต ๐ฑ๐ฎ๐๐ฎ๐๐ฒ๐
โช๏ธDS bench has 466 data analysis tasks and 74 data modelling tasks
โช๏ธThe tasks are sourced from ModelOff and Kaggle, the platforms hosting the most popular data science competitions
โช๏ธDifference with previous DS benchmarks:
โถ This benchmark leverages various modalities on top of text: images, Excel files, tables
โท Complex tables: sometimes several tables should be leveraged to answer one question
โธ The context is richer, with longer descriptions.
โช๏ธ Evaluation metrics : the benchmark is scored with an LLM as a judge, using a specific prompt.
๐๐ป๐๐ถ๐ด๐ต๐๐ ๐ณ๐ฟ๐ผ๐บ ๐ฒ๐๐ฎ๐น๐๐ฎ๐๐ถ๐ป๐ด ๐ฎ๐ด๐ฒ๐ป๐๐
โช๏ธ Their evaluation confirms that using LLMs in an agent setup, for instance by allowing them to run a single step of code execution, is more costly (especially with multi-turn frameworks like autogen) but also much more performant than the vanilla LLM.
โช๏ธ The sets of tasks solved by different models (like GPT-3.5 vs Llama-3-8B) has quite low overlap, which suggests that different models tend to try very different approches.
This new benchmark is really welcome, can't wait to try transformers agents on it! ๐ค
Read their full paper ๐ DSBench: How Far Are Data Science Agents to Becoming Data Science Experts? (2409.07703)
A team from Tencent AI wanted to evaluate agentic systems on data science (DS) tasks : but they noticed that existing agentic benchmarks were severely limited in several aspects: they were limited to text and did not include tables or images, were only specific to certain packages, only performed exact match evaluationโฆ
โก๏ธ So they set out to build a much more exhaustive approach, to finally make the definitive DS agent benchmark.
๐ง๐ต๐ฒ ๐๐ฆ๐๐ฒ๐ป๐ฐ๐ต ๐ฑ๐ฎ๐๐ฎ๐๐ฒ๐
โช๏ธDS bench has 466 data analysis tasks and 74 data modelling tasks
โช๏ธThe tasks are sourced from ModelOff and Kaggle, the platforms hosting the most popular data science competitions
โช๏ธDifference with previous DS benchmarks:
โถ This benchmark leverages various modalities on top of text: images, Excel files, tables
โท Complex tables: sometimes several tables should be leveraged to answer one question
โธ The context is richer, with longer descriptions.
โช๏ธ Evaluation metrics : the benchmark is scored with an LLM as a judge, using a specific prompt.
๐๐ป๐๐ถ๐ด๐ต๐๐ ๐ณ๐ฟ๐ผ๐บ ๐ฒ๐๐ฎ๐น๐๐ฎ๐๐ถ๐ป๐ด ๐ฎ๐ด๐ฒ๐ป๐๐
โช๏ธ Their evaluation confirms that using LLMs in an agent setup, for instance by allowing them to run a single step of code execution, is more costly (especially with multi-turn frameworks like autogen) but also much more performant than the vanilla LLM.
โช๏ธ The sets of tasks solved by different models (like GPT-3.5 vs Llama-3-8B) has quite low overlap, which suggests that different models tend to try very different approches.
This new benchmark is really welcome, can't wait to try transformers agents on it! ๐ค
Read their full paper ๐ DSBench: How Far Are Data Science Agents to Becoming Data Science Experts? (2409.07703)
posted
an
update
4 months ago
Post
820
I've been working on a Space to make it super easy to create notebooks and help users quickly understand and manipulate their data!
With just a few clicks automatically generate notebooks for:
๐ Exploratory Data Analysis
๐ง Text Embeddings
๐ค Retrieval-Augmented Generation (RAG)
โจ Automatic training is coming soon!
Check it out here asoria/auto-notebook-creator
Appreciate any feedback to improve this tool ๐ค
With just a few clicks automatically generate notebooks for:
๐ Exploratory Data Analysis
๐ง Text Embeddings
๐ค Retrieval-Augmented Generation (RAG)
โจ Automatic training is coming soon!
Check it out here asoria/auto-notebook-creator
Appreciate any feedback to improve this tool ๐ค
reacted to
davanstrien's
post with ๐
4 months ago
Post
3161
๐ Introducing Hugging Face Similar: a Chrome extension to find relevant datasets!
โจ Adds a "Similar Datasets" section to Hugging Face dataset pages
๐ Recommendations based on dataset READMEs
๐๏ธ Powered by https://huggingface.co./chromadb and https://huggingface.co./Snowflake embeddings.
You can try it here: https://chromewebstore.google.com/detail/hugging-face-similar/aijelnjllajooinkcpkpbhckbghghpnl?authuser=0&hl=en.
I am very happy to get feedback on whether this could be useful or not ๐ค
โจ Adds a "Similar Datasets" section to Hugging Face dataset pages
๐ Recommendations based on dataset READMEs
๐๏ธ Powered by https://huggingface.co./chromadb and https://huggingface.co./Snowflake embeddings.
You can try it here: https://chromewebstore.google.com/detail/hugging-face-similar/aijelnjllajooinkcpkpbhckbghghpnl?authuser=0&hl=en.
I am very happy to get feedback on whether this could be useful or not ๐ค
- 4 replies
reacted to
m-ric's
post with ๐
5 months ago
Post
2278
๐๐ด๐ฒ๐ป๐๐ถ๐ฐ ๐๐ฎ๐๐ฎ ๐ฎ๐ป๐ฎ๐น๐๐๐: ๐ฑ๐ฟ๐ผ๐ฝ ๐๐ผ๐๐ฟ ๐ฑ๐ฎ๐๐ฎ ๐ณ๐ถ๐น๐ฒ, ๐น๐ฒ๐ ๐๐ต๐ฒ ๐๐๐ ๐ฑ๐ผ ๐๐ต๐ฒ ๐ฎ๐ป๐ฎ๐น๐๐๐ถ๐ ๐โ๏ธ
Need to make quick exploratory data analysis? โก๏ธ Get help from an agent.
I was impressed by Llama-3.1's capacity to derive insights from data. Given a csv file, it makes quick work of exploratory data analysis and can derive interesting insights.
On the data from the Kaggle titanic challenge, that records which passengers survived the Titanic wreckage, it was able by itself to derive interesting trends like "passengers that paid higher fares were more likely to survive" or "survival rate was much higher for women than men".
The cookbook even lets the agent built its own submission to the challenge, and it ranks under 3,000 out of 17,000 submissions: ๐ not bad at all!
Try it for yourself in this Space demo ๐ m-ric/agent-data-analyst
Need to make quick exploratory data analysis? โก๏ธ Get help from an agent.
I was impressed by Llama-3.1's capacity to derive insights from data. Given a csv file, it makes quick work of exploratory data analysis and can derive interesting insights.
On the data from the Kaggle titanic challenge, that records which passengers survived the Titanic wreckage, it was able by itself to derive interesting trends like "passengers that paid higher fares were more likely to survive" or "survival rate was much higher for women than men".
The cookbook even lets the agent built its own submission to the challenge, and it ranks under 3,000 out of 17,000 submissions: ๐ not bad at all!
Try it for yourself in this Space demo ๐ m-ric/agent-data-analyst
- 2 replies
reacted to
albertvillanova's
post with ๐ฅ
7 months ago
Post
2699
Easily convert your script-based datasets to Parquet and explore them in the dataset viewer. ๐
๐ ๏ธ Use @huggingface Datasets CLI:
$ ๐๐๐๐๐๐๐๐-๐๐๐ ๐๐๐๐๐๐๐_๐๐_๐๐๐๐๐๐๐ ๐๐๐ด๐๐ฝ๐ฐ๐ผ๐ด/๐ณ๐ฐ๐๐ฐ๐๐ด๐_๐ฝ๐ฐ๐ผ๐ด
Learn more: https://huggingface.co./docs/datasets/main/en/cli#convert-to-parquet
#Data #AI
๐ ๏ธ Use @huggingface Datasets CLI:
$ ๐๐๐๐๐๐๐๐-๐๐๐ ๐๐๐๐๐๐๐_๐๐_๐๐๐๐๐๐๐ ๐๐๐ด๐๐ฝ๐ฐ๐ผ๐ด/๐ณ๐ฐ๐๐ฐ๐๐ด๐_๐ฝ๐ฐ๐ผ๐ด
Learn more: https://huggingface.co./docs/datasets/main/en/cli#convert-to-parquet
#Data #AI
reacted to
davanstrien's
post with ๐ฅ
8 months ago
Post
951
In my ongoing quest to learn more about building synthetic datasets, I've created an "Awesome Synthetic Datasets" list.
The aim is to lightly curate a collection of resources, tutorials, and tools for generating synthetic datasets using large language models.
I plan to add some "key techniques" to the repo, but for now, it focuses on important datasets, papers, and tools.
๐ https://github.com/davanstrien/awesome-synthetic-datasets
The aim is to lightly curate a collection of resources, tutorials, and tools for generating synthetic datasets using large language models.
I plan to add some "key techniques" to the repo, but for now, it focuses on important datasets, papers, and tools.
๐ https://github.com/davanstrien/awesome-synthetic-datasets
reacted to
tomaarsen's
post with โค๏ธ
10 months ago
Post
๐ค Sentence Transformers v2.4.0 for embedding models is now out! It introduces a lot of powerful features, such as:
1. Matryoshka Loss function - you can now train & perform inference on ๐ช Matryoshka Embedding models. See also our blogpost: https://huggingface.co./blog/matryoshka
2. CoSENTLoss & AnglELoss: State of the art loss functions. These are quite interesting, they outperform CosineSimilarityLoss on nearly all benchmarks as a drop-in replacement! See also the docs: https://sbert.net/docs/package_reference/losses.html#cosentloss
3. Prompt templates: Many popular models such as intfloat/multilingual-e5-large and BAAI/bge-large-en-v1.5 prefix their texts with prompts, so this adds configuration options to automatically include prompts using
4. Instructor support: Support for the INSTRUCTOR line of models, such as hkunlp/instructor-large. Learn how to use them here: https://sbert.net/docs/pretrained_models.html#instructor-models
5. Removed NLTK & sentencepiece dependencies: Should allow for a smaller installation & a slightly faster import!
6. Updated documentation: a new Loss Overview section: https://sbert.net/docs/training/loss_overview.html and more detailed loss functions: https://sbert.net/docs/package_reference/losses.html
And much more! See the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v2.4.0
Some more very exciting updates are still on the horizon!
1. Matryoshka Loss function - you can now train & perform inference on ๐ช Matryoshka Embedding models. See also our blogpost: https://huggingface.co./blog/matryoshka
2. CoSENTLoss & AnglELoss: State of the art loss functions. These are quite interesting, they outperform CosineSimilarityLoss on nearly all benchmarks as a drop-in replacement! See also the docs: https://sbert.net/docs/package_reference/losses.html#cosentloss
3. Prompt templates: Many popular models such as intfloat/multilingual-e5-large and BAAI/bge-large-en-v1.5 prefix their texts with prompts, so this adds configuration options to automatically include prompts using
model.encode(..., prompt_name="query") which will include a prompt with the name "query". More info in the docs: https://sbert.net/examples/applications/computing-embeddings/README.html#prompt-templates4. Instructor support: Support for the INSTRUCTOR line of models, such as hkunlp/instructor-large. Learn how to use them here: https://sbert.net/docs/pretrained_models.html#instructor-models
5. Removed NLTK & sentencepiece dependencies: Should allow for a smaller installation & a slightly faster import!
6. Updated documentation: a new Loss Overview section: https://sbert.net/docs/training/loss_overview.html and more detailed loss functions: https://sbert.net/docs/package_reference/losses.html
And much more! See the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v2.4.0
Some more very exciting updates are still on the horizon!
- 4 replies