CodePlan: Repository-level Coding using LLMs and Planning
Paper
β’
2309.12499
β’
Published
β’
75
Muhtasham Oblokulov PRO
muhtasham
Β·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 4 hours ago
CodePlan: Repository-level Coding using LLMs and Planning
liked
a model
about 4 hours ago
unsloth/DeepSeek-R1-GGUF
upvoted
a
collection
about 4 hours ago
DeepSeek R1 (All Versions)
Organizations
muhtasham's activity
upvoted
a
paper
about 4 hours ago
liked
a
model
about 4 hours ago
upvoted
a
collection
about 4 hours ago
liked
a
Space
about 6 hours ago
liked
2
models
about 6 hours ago
liked
a
model
about 23 hours ago
upvoted
a
collection
about 23 hours ago
liked
a
Space
about 23 hours ago
liked
2
Spaces
1 day ago
liked
a
Space
2 days ago
liked
a
dataset
2 days ago
liked
a
model
2 days ago
upvoted
an
article
2 days ago
Article
Open-R1: a fully open reproduction of DeepSeek-R1
β’
434
liked
a
model
3 days ago
upvoted
a
collection
3 days ago
liked
a
model
3 days ago
reacted to
tomaarsen's
post with π₯
3 days ago
Post
2031
I've just shipped the Sentence Transformers v3.1.1 patch release, fixing the hard negatives mining utility for some models. This utility is extremely useful to get more performance out of your embedding training data.
β Hard negatives are texts that are rather similar to some anchor text (e.g. a query), but are not the correct match. They're difficult for a model to distinguish from the correct answer, often resulting in a stronger model after training.
π Beyond that, this release removes the numpy<2 restriction from v3.1.0. This was previously required for Windows as not all third-party libraries were updated to support numpy v2. With Sentence Transformers, you can now choose v1 or v2 of numpy.
Check out the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.1.1
I'm looking forward to releasing v3.2, I have some exciting things planned π
β Hard negatives are texts that are rather similar to some anchor text (e.g. a query), but are not the correct match. They're difficult for a model to distinguish from the correct answer, often resulting in a stronger model after training.
mine_hard_negatives docs: https://sbert.net/docs/package_reference/util.html#sentence_transformers.util.mine_hard_negativesπ Beyond that, this release removes the numpy<2 restriction from v3.1.0. This was previously required for Windows as not all third-party libraries were updated to support numpy v2. With Sentence Transformers, you can now choose v1 or v2 of numpy.
Check out the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.1.1
I'm looking forward to releasing v3.2, I have some exciting things planned π
reacted to
MoritzLaurer's
post with β€οΈ
3 days ago
Post
4627
#phdone - I defended my PhD yesterday! A key lesson: it is amazing how open science and open source can empower beginners with limited resources:
I first learned about instruction-based classifiers like BERT-NLI 3-4 years ago, through the @HuggingFace ZeroShotClassificationPipeline. Digging deeper into this, it was surprisingly easy to find new datasets, newer base models, and reusable fine-tuning scripts on the HF Hub to create my own zeroshot models - although I didn't know much about fine-tuning at the time.
Thanks to the community effect of the Hub, my models were downloaded hundreds of thousands of times after a few months. Seeing my research being useful for people motivated me to improve and upload newer models. Leaving my contact details in the model cards led to academic cooperation and consulting contracts (and eventually my job at HF).
That's the power of open science & open source: learning, sharing, improving, collaborating.
I mean every word in my thesis acknowledgments (screenshot). I'm very grateful to my supervisors @vanatteveldt @CasAndreu @KasperWelbers for their guidance; to @profAndreaRenda and @CEPS_thinktank for enabling me to work part-time during the first year; to @huggingface for creating awesome tools and an awesome platform; and to many others who are not active on social media.
Links to the full thesis and the collection of my most recent models are below.
PS: If someone happens to speak Latin, let me know if my diploma contains some hidden Illuminati code or something :D
I first learned about instruction-based classifiers like BERT-NLI 3-4 years ago, through the @HuggingFace ZeroShotClassificationPipeline. Digging deeper into this, it was surprisingly easy to find new datasets, newer base models, and reusable fine-tuning scripts on the HF Hub to create my own zeroshot models - although I didn't know much about fine-tuning at the time.
Thanks to the community effect of the Hub, my models were downloaded hundreds of thousands of times after a few months. Seeing my research being useful for people motivated me to improve and upload newer models. Leaving my contact details in the model cards led to academic cooperation and consulting contracts (and eventually my job at HF).
That's the power of open science & open source: learning, sharing, improving, collaborating.
I mean every word in my thesis acknowledgments (screenshot). I'm very grateful to my supervisors @vanatteveldt @CasAndreu @KasperWelbers for their guidance; to @profAndreaRenda and @CEPS_thinktank for enabling me to work part-time during the first year; to @huggingface for creating awesome tools and an awesome platform; and to many others who are not active on social media.
Links to the full thesis and the collection of my most recent models are below.
PS: If someone happens to speak Latin, let me know if my diploma contains some hidden Illuminati code or something :D
- 4 replies