๐ฎ๐น๐ฏ๐ต๐ง๐ท Generating multilingual instruction datasets with Magpie ๐ฆโโฌ
โข
18
Stefano Fiorucci PRO
anakin87
AI & ML interests
Contributing to Haystack LLM framework ๐๏ธ. Language Models: orchestration, post-training, synthetic data...
Recent Activity
liked
a dataset
4 days ago
anakin87/evol-dpo-ita-reranked
liked
a dataset
4 days ago
anakin87/fine-instructions-ita-70k
new activity
4 days ago
google/gemma-2-9b:Fine-tuning Hyperparameters
Articles
Organizations
anakin87's activity
liked
2
datasets
4 days ago
Fine-tuning Hyperparameters
8
#27 opened 7 months ago
by
tanliboy
liked
a
dataset
5 days ago
replied to
their
post
6 days ago
Ok, I understand...
In the past, I've also fine-tuned models with different licenses.
You may be interested in https://huggingface.co/anakin87/Phi-3.5-mini-ITA (MIT license).
upvoted
an
article
6 days ago
Article
Fine-tune ModernBERT for RAG with Synthetic Data
By
โข
โข
28
posted
an
update
6 days ago
Post
1533
๐๐๐ฐ ๐๐ญ๐๐ฅ๐ข๐๐ง ๐๐ฆ๐๐ฅ๐ฅ ๐๐๐ง๐ ๐ฎ๐๐ ๐ ๐๐จ๐๐๐ฅ๐ฌ: ๐๐๐ฆ๐ฆ๐ ๐๐๐จ๐ ๐๐ง๐๐ฌ๐ข๐ฌ ๐๐จ๐ฅ๐ฅ๐๐๐ญ๐ข๐จ๐ง ๐๐๐ฎ๐น
I am happy to release two new language models for the Italian Language!
๐ช Gemma 2 9B Neogenesis ITA
anakin87/gemma-2-9b-neogenesis-ita
Building on the impressive work by VAGO Solutions, I applied Direct Preference Optimization with a mix of Italian and English data.
Using Spectrum, I trained 20% of model layers.
๐ Evaluated on the Open ITA LLM leaderboard ( mii-llm/open_ita_llm_leaderboard), this model achieves strong performance.
To beat it on this benchmark, you'd need a 27B model ๐
๐ค Gemma 2 2B Neogenesis ITA
anakin87/gemma-2-2b-neogenesis-ita
This smaller variant is fine-tuned from the original Gemma 2 2B it by Google.
Through a combination of Supervised Fine-Tuning and Direct Preference Optimization, I trained 25% of the layers using Spectrum.
๐ Compared to the original model, it shows improved Italian proficiency, good for its small size.
Both models were developed during the recent #gemma competition on Kaggle.
๐ Training code: https://www.kaggle.com/code/anakin87/post-training-gemma-for-italian-and-beyond
๐ Thanks @FinancialSupport and mii-llm for the help during evaluation.
I am happy to release two new language models for the Italian Language!
๐ช Gemma 2 9B Neogenesis ITA
anakin87/gemma-2-9b-neogenesis-ita
Building on the impressive work by VAGO Solutions, I applied Direct Preference Optimization with a mix of Italian and English data.
Using Spectrum, I trained 20% of model layers.
๐ Evaluated on the Open ITA LLM leaderboard ( mii-llm/open_ita_llm_leaderboard), this model achieves strong performance.
To beat it on this benchmark, you'd need a 27B model ๐
๐ค Gemma 2 2B Neogenesis ITA
anakin87/gemma-2-2b-neogenesis-ita
This smaller variant is fine-tuned from the original Gemma 2 2B it by Google.
Through a combination of Supervised Fine-Tuning and Direct Preference Optimization, I trained 25% of the layers using Spectrum.
๐ Compared to the original model, it shows improved Italian proficiency, good for its small size.
Both models were developed during the recent #gemma competition on Kaggle.
๐ Training code: https://www.kaggle.com/code/anakin87/post-training-gemma-for-italian-and-beyond
๐ Thanks @FinancialSupport and mii-llm for the help during evaluation.
-
- 3 replies
updated
4
Spaces
9 days ago
updated
a
model
9 days ago
liked
a
dataset
9 days ago
updated
a
model
9 days ago
liked
a
model
9 days ago
published
a
Space
9 days ago
updated
a
collection
9 days ago
upvoted
a
collection
11 days ago
liked
a
Space
11 days ago
reacted to
tomaarsen's
post with โค๏ธ
11 days ago
Post
4322
๐๏ธ Today I'm introducing a method to train static embedding models that run 100x to 400x faster on CPU than common embedding models, while retaining 85%+ of the quality! Including 2 fully open models: training scripts, datasets, metrics.
We apply our recipe to train 2 Static Embedding models that we release today! We release:
2๏ธโฃ an English Retrieval model and a general-purpose Multilingual similarity model (e.g. classification, clustering, etc.), both Apache 2.0
๐ง my modern training strategy: ideation -> dataset choice -> implementation -> evaluation
๐ my training scripts, using the Sentence Transformers library
๐ my Weights & Biases reports with losses & metrics
๐ my list of 30 training and 13 evaluation datasets
The 2 Static Embedding models have the following properties:
๐๏ธ Extremely fast, e.g. 107500 sentences per second on a consumer CPU, compared to 270 for 'all-mpnet-base-v2' and 56 for 'gte-large-en-v1.5'
0๏ธโฃ Zero active parameters: No Transformer blocks, no attention, not even a matrix multiplication. Super speed!
๐ No maximum sequence length! Embed texts at any length (note: longer texts may embed worse)
๐ Linear instead of exponential complexity: 2x longer text takes 2x longer, instead of 2.5x or more.
๐ช Matryoshka support: allow you to truncate embeddings with minimal performance loss (e.g. 4x smaller with a 0.56% perf. decrease for English Similarity tasks)
Check out the full blogpost if you'd like to 1) use these lightning-fast models or 2) learn how to train them with consumer-level hardware: https://huggingface.co/blog/static-embeddings
The blogpost contains a lengthy list of possible advancements; I'm very confident that our 2 models are only the tip of the iceberg, and we may be able to get even better performance.
Alternatively, check out the models:
* sentence-transformers/static-retrieval-mrl-en-v1
* sentence-transformers/static-similarity-mrl-multilingual-v1
We apply our recipe to train 2 Static Embedding models that we release today! We release:
2๏ธโฃ an English Retrieval model and a general-purpose Multilingual similarity model (e.g. classification, clustering, etc.), both Apache 2.0
๐ง my modern training strategy: ideation -> dataset choice -> implementation -> evaluation
๐ my training scripts, using the Sentence Transformers library
๐ my Weights & Biases reports with losses & metrics
๐ my list of 30 training and 13 evaluation datasets
The 2 Static Embedding models have the following properties:
๐๏ธ Extremely fast, e.g. 107500 sentences per second on a consumer CPU, compared to 270 for 'all-mpnet-base-v2' and 56 for 'gte-large-en-v1.5'
0๏ธโฃ Zero active parameters: No Transformer blocks, no attention, not even a matrix multiplication. Super speed!
๐ No maximum sequence length! Embed texts at any length (note: longer texts may embed worse)
๐ Linear instead of exponential complexity: 2x longer text takes 2x longer, instead of 2.5x or more.
๐ช Matryoshka support: allow you to truncate embeddings with minimal performance loss (e.g. 4x smaller with a 0.56% perf. decrease for English Similarity tasks)
Check out the full blogpost if you'd like to 1) use these lightning-fast models or 2) learn how to train them with consumer-level hardware: https://huggingface.co/blog/static-embeddings
The blogpost contains a lengthy list of possible advancements; I'm very confident that our 2 models are only the tip of the iceberg, and we may be able to get even better performance.
Alternatively, check out the models:
* sentence-transformers/static-retrieval-mrl-en-v1
* sentence-transformers/static-similarity-mrl-multilingual-v1
- 1 reply