hf-internal-testing/transformers_daily_ci
Updated
•
79
•
1
Hugging Face Internal Testing Organization
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
hf-internal-testing's activity
hf-transformers-bot
updated
a
dataset
about 5 hours ago
Xenova
updated
a
model
about 9 hours ago
Xenova
published
a
model
about 18 hours ago
Post
1587
Introducing Kokoro.js, a new JavaScript library for running Kokoro TTS, an 82 million parameter text-to-speech model, 100% locally in the browser w/ WASM. Powered by 🤗 Transformers.js. WebGPU support coming soon!
👉 npm i kokoro-js 👈
Try it out yourself: webml-community/kokoro-web
Link to models/samples: onnx-community/Kokoro-82M-ONNX
You can get started in just a few lines of code!
Huge kudos to the Kokoro TTS community, especially taylorchu for the ONNX exports and Hexgrad for the amazing project! None of this would be possible without you all! 🤗
The model is also extremely resilient to quantization. The smallest variant is only 86 MB in size (down from the original 326 MB), with no noticeable difference in audio quality! 🤯
👉 npm i kokoro-js 👈
Try it out yourself: webml-community/kokoro-web
Link to models/samples: onnx-community/Kokoro-82M-ONNX
You can get started in just a few lines of code!
import { KokoroTTS } from "kokoro-js";
const tts = await KokoroTTS.from_pretrained(
"onnx-community/Kokoro-82M-ONNX",
{ dtype: "q8" }, // fp32, fp16, q8, q4, q4f16
);
const text = "Life is like a box of chocolates. You never know what you're gonna get.";
const audio = await tts.generate(text,
{ voice: "af_sky" }, // See `tts.list_voices()`
);
audio.save("audio.wav");Huge kudos to the Kokoro TTS community, especially taylorchu for the ONNX exports and Hexgrad for the amazing project! None of this would be possible without you all! 🤗
The model is also extremely resilient to quantization. The smallest variant is only 86 MB in size (down from the original 326 MB), with no noticeable difference in audio quality! 🤯
-
- 2 replies
Post
4083
🏎️ 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
albertvillanova
posted
an
update
11 days ago
Post
1771
Discover all the improvements in the new version of Lighteval: https://huggingface.co/docs/lighteval/
Post
3267
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
6237
First project of 2025: Vision Transformer Explorer
I built a web app to interactively explore the self-attention maps produced by ViTs. This explains what the model is focusing on when making predictions, and provides insights into its inner workings! 🤯
Try it out yourself! 👇
webml-community/attention-visualization
Source code: https://github.com/huggingface/transformers.js-examples/tree/main/attention-visualization
I built a web app to interactively explore the self-attention maps produced by ViTs. This explains what the model is focusing on when making predictions, and provides insights into its inner workings! 🤯
Try it out yourself! 👇
webml-community/attention-visualization
Source code: https://github.com/huggingface/transformers.js-examples/tree/main/attention-visualization
Post
2815
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
2130
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
Post
4066
Commits speak louder than words 🤪
* 4 new video models
* Multiple image models, including SANA & Flux Control
* New quantizers -> GGUF & TorchAO
* New training scripts
Enjoy this holiday-special Diffusers release 🤗
Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0
* 4 new video models
* Multiple image models, including SANA & Flux Control
* New quantizers -> GGUF & TorchAO
* New training scripts
Enjoy this holiday-special Diffusers release 🤗
Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0
tomaarsen
authored
a
paper
30 days ago
lhoestq
authored
a
paper
30 days ago
Post
2234
Introducing 📐𝐅𝐢𝐧𝐞𝐌𝐚𝐭𝐡: the best public math pre-training dataset with 50B+ tokens!
HuggingFaceTB/finemath
Math remains challenging for LLMs and by training on FineMath we see considerable gains over other math datasets, especially on GSM8K and MATH.
We build the dataset by:
🛠️ carefully extracting math data from Common Crawl;
🔎 iteratively filtering and recalling high quality math pages using a classifier trained on synthetic annotations to identify math reasoning and deduction.
We conducted a series of ablations comparing the performance of Llama-3.2-3B-Base after continued pre-training on FineMath and observe notable gains compared to the baseline model and other public math datasets.
We hope this helps advance the performance of LLMs on math and reasoning! 🚀
We’re also releasing all the ablation models as well as the evaluation code.
HuggingFaceTB/finemath-6763fb8f71b6439b653482c2
HuggingFaceTB/finemath
Math remains challenging for LLMs and by training on FineMath we see considerable gains over other math datasets, especially on GSM8K and MATH.
We build the dataset by:
🛠️ carefully extracting math data from Common Crawl;
🔎 iteratively filtering and recalling high quality math pages using a classifier trained on synthetic annotations to identify math reasoning and deduction.
We conducted a series of ablations comparing the performance of Llama-3.2-3B-Base after continued pre-training on FineMath and observe notable gains compared to the baseline model and other public math datasets.
We hope this helps advance the performance of LLMs on math and reasoning! 🚀
We’re also releasing all the ablation models as well as the evaluation code.
HuggingFaceTB/finemath-6763fb8f71b6439b653482c2
Post
3913
Introducing Moonshine Web: real-time speech recognition running 100% locally in your browser!
🚀 Faster and more accurate than Whisper
🔒 Privacy-focused (no data leaves your device)
⚡️ WebGPU accelerated (w/ WASM fallback)
🔥 Powered by ONNX Runtime Web and Transformers.js
Demo: webml-community/moonshine-web
Source code: https://github.com/huggingface/transformers.js-examples/tree/main/moonshine-web
🚀 Faster and more accurate than Whisper
🔒 Privacy-focused (no data leaves your device)
⚡️ WebGPU accelerated (w/ WASM fallback)
🔥 Powered by ONNX Runtime Web and Transformers.js
Demo: webml-community/moonshine-web
Source code: https://github.com/huggingface/transformers.js-examples/tree/main/moonshine-web
-
- 5 replies
Post
1953
In the past seven days, the Diffusers team has shipped:
1. Two new video models
2. One new image model
3. Two new quantization backends
4. Three new fine-tuning scripts
5. Multiple fixes and library QoL improvements
Coffee on me if someone can guess 1 - 4 correctly.
1. Two new video models
2. One new image model
3. Two new quantization backends
4. Three new fine-tuning scripts
5. Multiple fixes and library QoL improvements
Coffee on me if someone can guess 1 - 4 correctly.
- 1 reply
Post
6739
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
1722
Made a HF Dataset editor a la gg sheets here:
lhoestq/dataset-spreadsheets
With Dataset Spreadsheets:
✏️ Edit datasets in the UI
🔗 Share link with collaborators
🐍 Use locally in DuckDB or Python
Available for the 100,000+ parquet datasets on HF :)
With Dataset Spreadsheets:
✏️ Edit datasets in the UI
🔗 Share link with collaborators
🐍 Use locally in DuckDB or Python
Available for the 100,000+ parquet datasets on HF :)
Post
1140
Performance leap: TGI v3 is out. Processes 3x more tokens, 13x faster than vLLM on long prompts. Zero config !
3x more tokens.
By reducing our memory footprint, we’re able to ingest many more tokens and more dynamically than before. A single L4 (24GB) can handle 30k tokens on llama 3.1-8B, while vLLM gets barely 10k. A lot of work went into reducing the footprint of the runtime and its effect are best seen on smaller constrained environments.
13x faster
On long prompts (200k+ tokens) conversation replies take 27.5s in vLLM, while it takes only 2s in TGI. How so ? We keep the initial conversation around, so when a new reply comes in, we can answer almost instantly. The overhead of the lookup is ~5us. Thanks @Dani ël de Kok for the beast data structure.
Zero config
That’s it. Remove all the flags your are using and you’re likely to get the best performance. By evaluating the hardware and model, TGI carefully selects automatic values to give best performance. In production, we don’t have any flags anymore in our deployments. We kept all existing flags around, they may come in handy in niche scenarios.
Read more: https://huggingface.co/docs/text-generation-inference/conceptual/chunking
3x more tokens.
By reducing our memory footprint, we’re able to ingest many more tokens and more dynamically than before. A single L4 (24GB) can handle 30k tokens on llama 3.1-8B, while vLLM gets barely 10k. A lot of work went into reducing the footprint of the runtime and its effect are best seen on smaller constrained environments.
13x faster
On long prompts (200k+ tokens) conversation replies take 27.5s in vLLM, while it takes only 2s in TGI. How so ? We keep the initial conversation around, so when a new reply comes in, we can answer almost instantly. The overhead of the lookup is ~5us. Thanks @Dani ël de Kok for the beast data structure.
Zero config
That’s it. Remove all the flags your are using and you’re likely to get the best performance. By evaluating the hardware and model, TGI carefully selects automatic values to give best performance. In production, we don’t have any flags anymore in our deployments. We kept all existing flags around, they may come in handy in niche scenarios.
Read more: https://huggingface.co/docs/text-generation-inference/conceptual/chunking
Post
2090
Introducing a high-quality open-preference dataset to further this line of research for image generation.
Despite being such an inseparable component for modern image generation, open preference datasets are a rarity!
So, we decided to work on one with the community!
Check it out here:
https://huggingface.co/blog/image-preferences
Despite being such an inseparable component for modern image generation, open preference datasets are a rarity!
So, we decided to work on one with the community!
Check it out here:
https://huggingface.co/blog/image-preferences
- 7 replies