Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
Paper
•
2503.07572
•
Published
•
25
Distillation Hugs
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Distillation-Hugs's activity
lewtun
authored
a
paper
about 15 hours ago
Post
1415
Introducing OlympicCoder: a series of open reasoning models that can solve olympiad-level programming problems 🧑💻
- 7B open-r1/OlympicCoder-7B
- 32B open-r1/OlympicCoder-32B
We find that OlympicCoder models outperform Claude 3.7 Sonnet, as well as others over 100x larger 💪
Together with the models, we are releasing:
📊CodeForces-CoTs: new dataset of code problems from the most popular competitive coding platform, with R1 traces in C++ and Python open-r1/codeforces-cots
🏆 IOI'2024: a new benchmark of VERY hard programming problems where even frontier models struggle to match human performance open-r1/ioi
For links to the models and datasets, check out our latest progress report from Open R1: https://huggingface.co./blog/open-r1/update-3
- 7B open-r1/OlympicCoder-7B
- 32B open-r1/OlympicCoder-32B
We find that OlympicCoder models outperform Claude 3.7 Sonnet, as well as others over 100x larger 💪
Together with the models, we are releasing:
📊CodeForces-CoTs: new dataset of code problems from the most popular competitive coding platform, with R1 traces in C++ and Python open-r1/codeforces-cots
🏆 IOI'2024: a new benchmark of VERY hard programming problems where even frontier models struggle to match human performance open-r1/ioi
For links to the models and datasets, check out our latest progress report from Open R1: https://huggingface.co./blog/open-r1/update-3
- 1 reply
Post
6124
An assembly of 18 European companies, labs, and universities have banded together to launch 🇪🇺 EuroBERT! It's a state-of-the-art multilingual encoder for 15 European languages, designed to be finetuned for retrieval, classification, etc.
🇪🇺 15 Languages: English, French, German, Spanish, Chinese, Italian, Russian, Polish, Portuguese, Japanese, Vietnamese, Dutch, Arabic, Turkish, Hindi
3️⃣ 3 model sizes: 210M, 610M, and 2.1B parameters - very very useful sizes in my opinion
➡️ Sequence length of 8192 tokens! Nice to see these higher sequence lengths for encoders becoming more common.
⚙️ Architecture based on Llama, but with bi-directional (non-causal) attention to turn it into an encoder. Flash Attention 2 is supported.
🔥 A new Pareto frontier (stronger *and* smaller) for multilingual encoder models
📊 Evaluated against mDeBERTa, mGTE, XLM-RoBERTa for Retrieval, Classification, and Regression (after finetuning for each task separately): EuroBERT punches way above its weight.
📝 Detailed paper with all details, incl. data: FineWeb for English and CulturaX for multilingual data, The Stack v2 and Proof-Pile-2 for code.
Check out the release blogpost here: https://huggingface.co./blog/EuroBERT/release
* EuroBERT/EuroBERT-210m
* EuroBERT/EuroBERT-610m
* EuroBERT/EuroBERT-2.1B
The next step is for researchers to build upon the 3 EuroBERT base models and publish strong retrieval, zero-shot classification, etc. models for all to use. I'm very much looking forward to it!
🇪🇺 15 Languages: English, French, German, Spanish, Chinese, Italian, Russian, Polish, Portuguese, Japanese, Vietnamese, Dutch, Arabic, Turkish, Hindi
3️⃣ 3 model sizes: 210M, 610M, and 2.1B parameters - very very useful sizes in my opinion
➡️ Sequence length of 8192 tokens! Nice to see these higher sequence lengths for encoders becoming more common.
⚙️ Architecture based on Llama, but with bi-directional (non-causal) attention to turn it into an encoder. Flash Attention 2 is supported.
🔥 A new Pareto frontier (stronger *and* smaller) for multilingual encoder models
📊 Evaluated against mDeBERTa, mGTE, XLM-RoBERTa for Retrieval, Classification, and Regression (after finetuning for each task separately): EuroBERT punches way above its weight.
📝 Detailed paper with all details, incl. data: FineWeb for English and CulturaX for multilingual data, The Stack v2 and Proof-Pile-2 for code.
Check out the release blogpost here: https://huggingface.co./blog/EuroBERT/release
* EuroBERT/EuroBERT-210m
* EuroBERT/EuroBERT-610m
* EuroBERT/EuroBERT-2.1B
The next step is for researchers to build upon the 3 EuroBERT base models and publish strong retrieval, zero-shot classification, etc. models for all to use. I'm very much looking forward to it!
- 1 reply
Post
2418
Extremely bullish on
@CohereForAI
's Aya Vision (8B & 32B) - new SOTA open-weight VLMs
- 8B wins up to 81% of the time in its class, better than Gemini Flash
- 32B beats Llama 3.2 90B!
- Covers 23 languages, excels in image captioning, VQA & more
- Integrated on transformers from Day 0!
Efficient multimodal models are here to stay!!🔥
Check out their blog! https://huggingface.co./blog/aya-vision
- 8B wins up to 81% of the time in its class, better than Gemini Flash
- 32B beats Llama 3.2 90B!
- Covers 23 languages, excels in image captioning, VQA & more
- Integrated on transformers from Day 0!
Efficient multimodal models are here to stay!!🔥
Check out their blog! https://huggingface.co./blog/aya-vision
tomaarsen
authored
a
paper
20 days ago
Post
4857
Introducing OpenR1-Math-220k!
open-r1/OpenR1-Math-220k
The community has been busy distilling DeepSeek-R1 from inference providers, but we decided to have a go at doing it ourselves from scratch 💪
What’s new compared to existing reasoning datasets?
♾ Based on AI-MO/NuminaMath-1.5: we focus on math reasoning traces and generate answers for problems in NuminaMath 1.5, an improved version of the popular NuminaMath-CoT dataset.
🐳 800k R1 reasoning traces: We generate two answers for 400k problems using DeepSeek R1. The filtered dataset contains 220k problems with correct reasoning traces.
📀 512 H100s running locally: Instead of relying on an API, we leverage vLLM and SGLang to run generations locally on our science cluster, generating 180k reasoning traces per day.
⏳ Automated filtering: We apply Math Verify to only retain problems with at least one correct answer. We also leverage Llama3.3-70B-Instruct as a judge to retrieve more correct examples (e.g for cases with malformed answers that can’t be verified with a rules-based parser)
📊 We match the performance of DeepSeek-Distill-Qwen-7B by finetuning Qwen-7B-Math-Instruct on our dataset.
🔎 Read our blog post for all the nitty gritty details: https://huggingface.co./blog/open-r1/update-2
open-r1/OpenR1-Math-220k
The community has been busy distilling DeepSeek-R1 from inference providers, but we decided to have a go at doing it ourselves from scratch 💪
What’s new compared to existing reasoning datasets?
♾ Based on AI-MO/NuminaMath-1.5: we focus on math reasoning traces and generate answers for problems in NuminaMath 1.5, an improved version of the popular NuminaMath-CoT dataset.
🐳 800k R1 reasoning traces: We generate two answers for 400k problems using DeepSeek R1. The filtered dataset contains 220k problems with correct reasoning traces.
📀 512 H100s running locally: Instead of relying on an API, we leverage vLLM and SGLang to run generations locally on our science cluster, generating 180k reasoning traces per day.
⏳ Automated filtering: We apply Math Verify to only retain problems with at least one correct answer. We also leverage Llama3.3-70B-Instruct as a judge to retrieve more correct examples (e.g for cases with malformed answers that can’t be verified with a rules-based parser)
📊 We match the performance of DeepSeek-Distill-Qwen-7B by finetuning Qwen-7B-Math-Instruct on our dataset.
🔎 Read our blog post for all the nitty gritty details: https://huggingface.co./blog/open-r1/update-2
andito
authored
a
paper
about 1 month ago
lewtun
authored
a
paper
about 1 month ago
Post
10238
We are reproducing the full DeepSeek R1 data and training pipeline so everybody can use their recipe. Instead of doing it in secret we can do it together in the open!
🧪 Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1.
🧠 Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code.
🔥 Step 3: show we can go from base model -> SFT -> RL via multi-stage training.
Follow along: https://github.com/huggingface/open-r1
🧪 Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1.
🧠 Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code.
🔥 Step 3: show we can go from base model -> SFT -> RL via multi-stage training.
Follow along: https://github.com/huggingface/open-r1
- 5 replies
Post
2205
I just released Sentence Transformers v3.4.0, featuring a memory leak fix, compatibility between the powerful Cached... losses and the Matryoshka loss modifier, and a bunch of fixes & small features.
🪆 Matryoshka & Cached loss compatibility
It is now possible to combine the powerful Cached... losses (which use in-batch negatives & a caching mechanism to allow for endless batch size & negatives) with the Matryoshka loss modifier which modifies a base loss such that it is trained not only on the maximum dimensionality (e.g. 1024 dimensions), but also on many lower dimensions (e.g. 768, 512, 256, 128, 64, 32).
After training, these models' embeddings can be truncated for faster retrieval, etc.
🎞️ Resolve memory leak when Model and Trainer are reinitialized
Due to a circular dependency between Trainer -> Model -> ModelCardData -> Trainer, deleting both the trainer & model still didn't free up the memory.
This led to a memory leak in scripts where you repeatedly do so.
➕ New Features
Many new small features, e.g. multi-GPU support for 'mine_hard_negatives', a 'margin' parameter to TripletEvaluator, and Matthews Correlation Coefficient in the BinaryClassificationEvaluator.
🐛 Bug Fixes
Also a bunch of fixes, for example that subsequent batches were not sorted when using the "no_duplicates" batch sampler. See the release notes for more details.
Full release notes: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.4.0
Big thanks to all community members who assisted in this release. 10 folks with their first contribution this time around!
🪆 Matryoshka & Cached loss compatibility
It is now possible to combine the powerful Cached... losses (which use in-batch negatives & a caching mechanism to allow for endless batch size & negatives) with the Matryoshka loss modifier which modifies a base loss such that it is trained not only on the maximum dimensionality (e.g. 1024 dimensions), but also on many lower dimensions (e.g. 768, 512, 256, 128, 64, 32).
After training, these models' embeddings can be truncated for faster retrieval, etc.
🎞️ Resolve memory leak when Model and Trainer are reinitialized
Due to a circular dependency between Trainer -> Model -> ModelCardData -> Trainer, deleting both the trainer & model still didn't free up the memory.
This led to a memory leak in scripts where you repeatedly do so.
➕ New Features
Many new small features, e.g. multi-GPU support for 'mine_hard_negatives', a 'margin' parameter to TripletEvaluator, and Matthews Correlation Coefficient in the BinaryClassificationEvaluator.
🐛 Bug Fixes
Also a bunch of fixes, for example that subsequent batches were not sorted when using the "no_duplicates" batch sampler. See the release notes for more details.
Full release notes: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.4.0
Big thanks to all community members who assisted in this release. 10 folks with their first contribution this time around!
Post
1631
𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝘁𝗵𝗲 𝘄𝗼𝗿𝗹𝗱'𝘀 𝘀𝗺𝗮𝗹𝗹𝗲𝘀𝘁 𝘃𝗶𝘀𝗶𝗼𝗻 𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗺𝗼𝗱𝗲𝗹!
We’re thrilled to share 𝗦𝗺𝗼𝗹𝗩𝗟𝗠 (256M & 500M)—the smallest Visual Language Models ever built. Think: running on <1GB of GPU memory—you can fine-tune it on your laptop and run it on your toaster!
Why It’s Game-Changing:
- 𝗢𝘂𝘁𝗽𝗲𝗿𝗳𝗼𝗿𝗺𝘀 𝗟𝗮𝗿𝗴𝗲𝗿 𝗠𝗼𝗱𝗲𝗹𝘀: Even the 256M model surpasses our SOTA 80B-parameter model from just 17 months ago. Over 300x reduction!
𝗠𝗶𝗴𝗵𝘁𝘆 𝗘𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝗰𝘆: The 256M version delivers 80% of our 2.2B model’s performance, and the 500M version hits 90%
𝗟𝗶𝗴𝗵𝘁𝗻𝗶𝗻𝗴-𝗙𝗮𝘀𝘁 𝗦𝗲𝗮𝗿𝗰𝗵: SmolVLM integrates with ColiPali for state-of-the-art retrieval speeds—on par with models 10x bigger. That means cheaper, faster indexing and real-world impact.
What’s New Under the Hood:
- 𝗡𝗲𝘄 𝗩𝗶𝘀𝗶𝗼𝗻 𝗘𝗻𝗰𝗼𝗱𝗲𝗿: Smaller overall size (400M -> 93M), but with higher resolution.
- 𝗛𝗶𝗴𝗵𝗲𝗿 𝗣𝗶𝘅𝗲𝗹𝘀/𝗧𝗼𝗸𝗲𝗻: 4096 vs. 1820—more efficient image processing.
- 𝗦𝗺𝗮𝗿𝘁 𝗧𝗼𝗸𝗲𝗻𝗶𝘇𝗮𝘁𝗶𝗼𝗻: Faster training and a performance boost.
Check our blog: https://huggingface.co./blog/smolervlm
The models: HuggingFaceTB/smolvlm-256m-and-500m-6791fafc5bb0ab8acc960fb0
The demo: HuggingFaceTB/SmolVLM-256M-Demo
We’re thrilled to share 𝗦𝗺𝗼𝗹𝗩𝗟𝗠 (256M & 500M)—the smallest Visual Language Models ever built. Think: running on <1GB of GPU memory—you can fine-tune it on your laptop and run it on your toaster!
Why It’s Game-Changing:
- 𝗢𝘂𝘁𝗽𝗲𝗿𝗳𝗼𝗿𝗺𝘀 𝗟𝗮𝗿𝗴𝗲𝗿 𝗠𝗼𝗱𝗲𝗹𝘀: Even the 256M model surpasses our SOTA 80B-parameter model from just 17 months ago. Over 300x reduction!
𝗠𝗶𝗴𝗵𝘁𝘆 𝗘𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝗰𝘆: The 256M version delivers 80% of our 2.2B model’s performance, and the 500M version hits 90%
𝗟𝗶𝗴𝗵𝘁𝗻𝗶𝗻𝗴-𝗙𝗮𝘀𝘁 𝗦𝗲𝗮𝗿𝗰𝗵: SmolVLM integrates with ColiPali for state-of-the-art retrieval speeds—on par with models 10x bigger. That means cheaper, faster indexing and real-world impact.
What’s New Under the Hood:
- 𝗡𝗲𝘄 𝗩𝗶𝘀𝗶𝗼𝗻 𝗘𝗻𝗰𝗼𝗱𝗲𝗿: Smaller overall size (400M -> 93M), but with higher resolution.
- 𝗛𝗶𝗴𝗵𝗲𝗿 𝗣𝗶𝘅𝗲𝗹𝘀/𝗧𝗼𝗸𝗲𝗻: 4096 vs. 1820—more efficient image processing.
- 𝗦𝗺𝗮𝗿𝘁 𝗧𝗼𝗸𝗲𝗻𝗶𝘇𝗮𝘁𝗶𝗼𝗻: Faster training and a performance boost.
Check our blog: https://huggingface.co./blog/smolervlm
The models: HuggingFaceTB/smolvlm-256m-and-500m-6791fafc5bb0ab8acc960fb0
The demo: HuggingFaceTB/SmolVLM-256M-Demo
-
- 1 reply
Post
4652
🏎️ 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:
2️⃣ an English Retrieval model and a general-purpose Multilingual similarity model (e.g. classification, clustering, etc.), both Apache 2.0
🧠 my modern training strategy: ideation -> dataset choice -> implementation -> evaluation
📜 my training scripts, using the Sentence Transformers library
📊 my Weights & Biases reports with losses & metrics
📕 my list of 30 training and 13 evaluation datasets
The 2 Static Embedding models have the following properties:
🏎️ 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'
0️⃣ Zero active parameters: No Transformer blocks, no attention, not even a matrix multiplication. Super speed!
📏 No maximum sequence length! Embed texts at any length (note: longer texts may embed worse)
📐 Linear instead of exponential complexity: 2x longer text takes 2x longer, instead of 2.5x or more.
🪆 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:
2️⃣ an English Retrieval model and a general-purpose Multilingual similarity model (e.g. classification, clustering, etc.), both Apache 2.0
🧠 my modern training strategy: ideation -> dataset choice -> implementation -> evaluation
📜 my training scripts, using the Sentence Transformers library
📊 my Weights & Biases reports with losses & metrics
📕 my list of 30 training and 13 evaluation datasets
The 2 Static Embedding models have the following properties:
🏎️ 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'
0️⃣ Zero active parameters: No Transformer blocks, no attention, not even a matrix multiplication. Super speed!
📏 No maximum sequence length! Embed texts at any length (note: longer texts may embed worse)
📐 Linear instead of exponential complexity: 2x longer text takes 2x longer, instead of 2.5x or more.
🪆 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
Post
3888
I was initially pretty sceptical about Meta's Coconut paper [1] because the largest perf gains were reported on toy linguistic problems. However, these results on machine translation are pretty impressive!
https://x.com/casper_hansen_/status/1875872309996855343
Together with the recent PRIME method [2] for scaling RL, reasoning for open models is looking pretty exciting for 2025!
[1] Training Large Language Models to Reason in a Continuous Latent Space (2412.06769)
[2] https://huggingface.co./blog/ganqu/prime
https://x.com/casper_hansen_/status/1875872309996855343
Together with the recent PRIME method [2] for scaling RL, reasoning for open models is looking pretty exciting for 2025!
[1] Training Large Language Models to Reason in a Continuous Latent Space (2412.06769)
[2] https://huggingface.co./blog/ganqu/prime
Post
3034
That didn't take long! Nomic AI has finetuned the new ModernBERT-base encoder model into a strong embedding model for search, classification, clustering and more!
Details:
🤖 Based on ModernBERT-base with 149M parameters.
📊 Outperforms both nomic-embed-text-v1 and nomic-embed-text-v1.5 on MTEB!
🏎️ Immediate FA2 and unpacking support for super efficient inference.
🪆 Trained with Matryoshka support, i.e. 2 valid output dimensionalities: 768 and 256.
➡️ Maximum sequence length of 8192 tokens!
2️⃣ Trained in 2 stages: unsupervised contrastive data -> high quality labeled datasets.
➕ Integrated in Sentence Transformers, Transformers, LangChain, LlamaIndex, Haystack, etc.
🏛️ Apache 2.0 licensed: fully commercially permissible
Try it out here: nomic-ai/modernbert-embed-base
Very nice work by Zach Nussbaum and colleagues at Nomic AI.
Details:
🤖 Based on ModernBERT-base with 149M parameters.
📊 Outperforms both nomic-embed-text-v1 and nomic-embed-text-v1.5 on MTEB!
🏎️ Immediate FA2 and unpacking support for super efficient inference.
🪆 Trained with Matryoshka support, i.e. 2 valid output dimensionalities: 768 and 256.
➡️ Maximum sequence length of 8192 tokens!
2️⃣ Trained in 2 stages: unsupervised contrastive data -> high quality labeled datasets.
➕ Integrated in Sentence Transformers, Transformers, LangChain, LlamaIndex, Haystack, etc.
🏛️ Apache 2.0 licensed: fully commercially permissible
Try it out here: nomic-ai/modernbert-embed-base
Very nice work by Zach Nussbaum and colleagues at Nomic AI.
Post
2310
This paper (
HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs (2412.18925)) has a really interesting recipe for inducing o1-like behaviour in Llama models:
* Iteratively sample CoTs from the model, using a mix of different search strategies. This gives you something like Stream of Search via prompting.
* Verify correctness of each CoT using GPT-4o (needed because exact match doesn't work well in medicine where there are lots of aliases)
* Use GPT-4o to reformat the concatenated CoTs into a single stream that includes smooth transitions like "hmm, wait" etc that one sees in o1
* Use the resulting data for SFT & RL
* Use sparse rewards from GPT-4o to guide RL training. They find RL gives an average ~3 point boost across medical benchmarks and SFT on this data already gives a strong improvement.
Applying this strategy to other domains could be quite promising, provided the training data can be formulated with verifiable problems!
* Iteratively sample CoTs from the model, using a mix of different search strategies. This gives you something like Stream of Search via prompting.
* Verify correctness of each CoT using GPT-4o (needed because exact match doesn't work well in medicine where there are lots of aliases)
* Use GPT-4o to reformat the concatenated CoTs into a single stream that includes smooth transitions like "hmm, wait" etc that one sees in o1
* Use the resulting data for SFT & RL
* Use sparse rewards from GPT-4o to guide RL training. They find RL gives an average ~3 point boost across medical benchmarks and SFT on this data already gives a strong improvement.
Applying this strategy to other domains could be quite promising, provided the training data can be formulated with verifiable problems!
- 1 reply
tomaarsen
authored
a
paper
3 months ago
Post
6930
We outperform Llama 70B with Llama 3B on hard math by scaling test-time compute 🔥
How? By combining step-wise reward models with tree search algorithms :)
We show that smol models can match or exceed the performance of their much larger siblings when given enough "time to think"
We're open sourcing the full recipe and sharing a detailed blog post.
In our blog post we cover:
📈 Compute-optimal scaling: How we implemented DeepMind's recipe to boost the mathematical capabilities of open models at test-time.
🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique. This simple yet effective method improves diversity and delivers better performance, particularly at large test-time compute budgets.
🧭 Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM
Here's the links:
- Blog post: HuggingFaceH4/blogpost-scaling-test-time-compute
- Code: https://github.com/huggingface/search-and-learn
Enjoy!
How? By combining step-wise reward models with tree search algorithms :)
We show that smol models can match or exceed the performance of their much larger siblings when given enough "time to think"
We're open sourcing the full recipe and sharing a detailed blog post.
In our blog post we cover:
📈 Compute-optimal scaling: How we implemented DeepMind's recipe to boost the mathematical capabilities of open models at test-time.
🎄 Diverse Verifier Tree Search (DVTS): An unpublished extension we developed to the verifier-guided tree search technique. This simple yet effective method improves diversity and delivers better performance, particularly at large test-time compute budgets.
🧭 Search and Learn: A lightweight toolkit for implementing search strategies with LLMs and built for speed with vLLM
Here's the links:
- Blog post: HuggingFaceH4/blogpost-scaling-test-time-compute
- Code: https://github.com/huggingface/search-and-learn
Enjoy!
- 2 replies
Post
1962
SmolVLM speeding locally on a laptop thanks to mlx-vlm and
@Gradio ! Try it with two lines:
pip install git+https://github.com/andimarafioti/mlx-vlm.git@stream-generate-fix
python -m mlx_vlm.chat_ui --model mlx-community/SmolVLM-Instruct-8bit
Gotta love the MLX community! Big thanks to @pcuenq and @prince_canuma !
@Gradio ! Try it with two lines:
pip install git+https://github.com/andimarafioti/mlx-vlm.git@stream-generate-fix
python -m mlx_vlm.chat_ui --model mlx-community/SmolVLM-Instruct-8bit
Gotta love the MLX community! Big thanks to @pcuenq and @prince_canuma !
Post
3371
Let's go! We are releasing SmolVLM, a smol 2B VLM built for on-device inference that outperforms all models at similar GPU RAM usage and tokens throughputs.
- SmolVLM generates tokens 7.5 to 16 times faster than Qwen2-VL! 🤯
- Other models at this size crash a laptop, but SmolVLM comfortably generates 17 tokens/sec on a macbook! 🚀
- SmolVLM can be fine-tuned on a Google collab! Or process millions of documents with a consumer GPU!
- SmolVLM even outperforms larger models in video benchmarks, despite not even being trained on videos!
Check out more!
Demo: HuggingFaceTB/SmolVLM
Blog: https://huggingface.co./blog/smolvlm
Model: HuggingFaceTB/SmolVLM-Instruct
Fine-tuning script: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
- SmolVLM generates tokens 7.5 to 16 times faster than Qwen2-VL! 🤯
- Other models at this size crash a laptop, but SmolVLM comfortably generates 17 tokens/sec on a macbook! 🚀
- SmolVLM can be fine-tuned on a Google collab! Or process millions of documents with a consumer GPU!
- SmolVLM even outperforms larger models in video benchmarks, despite not even being trained on videos!
Check out more!
Demo: HuggingFaceTB/SmolVLM
Blog: https://huggingface.co./blog/smolvlm
Model: HuggingFaceTB/SmolVLM-Instruct
Fine-tuning script: https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
Post
5768
I just released Sentence Transformers v3.3.0 & it's huge! 4.5x speedup for CPU with OpenVINO int8 static quantization, training with prompts for a free perf. boost, PEFT integration, evaluation on NanoBEIR, and more! Details:
1. We integrate Post-Training Static Quantization using OpenVINO, a very efficient solution for CPUs that processes 4.78x as many texts per second on average, while only hurting performance by 0.36% on average. There's a new
2. We add the option to train with prompts, e.g. strings like "query: ", "search_document: " or "Represent this sentence for searching relevant passages: ". It's as simple as using the
3. Sentence Transformers now supports training PEFT adapters via 7 new methods for adding new adapters or loading pre-trained ones. You can also directly load a trained adapter with SentenceTransformer as if it's a normal model. Very useful for e.g. 1) training multiple adapters on 1 base model, 2) training bigger models than otherwise possible, or 3) cheaply hosting multiple models by switching multiple adapters on 1 base model.
4. We added easy evaluation on NanoBEIR, a subset of BEIR a.k.a. the MTEB Retrieval benchmark. It contains 13 datasets with 50 queries and up to 10k documents each. Evaluation is fast, and can easily be done during training to track your model's performance on general-purpose information retrieval tasks.
Additionally, we also deprecate Python 3.8, add better compatibility with Transformers v4.46.0, and more. Read the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.3.0
1. We integrate Post-Training Static Quantization using OpenVINO, a very efficient solution for CPUs that processes 4.78x as many texts per second on average, while only hurting performance by 0.36% on average. There's a new
export_static_quantized_openvino_model method to quantize a model.2. We add the option to train with prompts, e.g. strings like "query: ", "search_document: " or "Represent this sentence for searching relevant passages: ". It's as simple as using the
prompts argument in SentenceTransformerTrainingArguments. Our experiments show that you can easily reach 0.66% to 0.90% relative performance improvement on NDCG@10 at no extra cost by adding "query: " before each training query and "document: " before each training answer.3. Sentence Transformers now supports training PEFT adapters via 7 new methods for adding new adapters or loading pre-trained ones. You can also directly load a trained adapter with SentenceTransformer as if it's a normal model. Very useful for e.g. 1) training multiple adapters on 1 base model, 2) training bigger models than otherwise possible, or 3) cheaply hosting multiple models by switching multiple adapters on 1 base model.
4. We added easy evaluation on NanoBEIR, a subset of BEIR a.k.a. the MTEB Retrieval benchmark. It contains 13 datasets with 50 queries and up to 10k documents each. Evaluation is fast, and can easily be done during training to track your model's performance on general-purpose information retrieval tasks.
Additionally, we also deprecate Python 3.8, add better compatibility with Transformers v4.46.0, and more. Read the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.3.0