Software Forgets: Agent Traces Are the Memory
• 8
AI & ML interests
The AI community building the future.
Recent Activity
View all activity
Papers
Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation
Qualixar OS: A Universal Operating System for AI Agent Orchestration
Articles
alvarobartt
updated a
dataset about 2 hours ago
evalstate
updated a
bucket about 9 hours ago
Post
62
Sharing how I built the LongCat-Video-Avatar 1.5 Space (+500k views on X) in one agent session. Gave a coding agent its own AI lab on ZeroGPU, framed the goal, walked away. It designed, deployed, tested against the live API, fixed, shipped.
Full recipe with the copy-paste prompt: https://huggingface.co/blog/victor/building-zerogpu-spaces-autonomously
Full recipe with the copy-paste prompt: https://huggingface.co/blog/victor/building-zerogpu-spaces-autonomously
merve
updated a
dataset about 14 hours ago
YUKKKKKKKKKKKKK
submitted a
paper to Daily Papers about 16 hours ago
pagezyhf
updated a
dataset about 16 hours ago
lysandre
updated a
dataset about 16 hours ago
ariG23498
updated a
dataset about 17 hours ago
sayakpaul
updated a
dataset 1 day ago
nielsr
submitted a
paper to Daily Papers 6 days ago
akhaliq
submitted a
paper to Daily Papers 7 days ago
Post
149
Two large changes in kernel-builder this week:
kernel-builder now links libstdc++ dynamically. To support a wide range of systems, we build against libstdc++ from manylinux_2_28 (EL 8 and later).
Following our Torch support policy that the current and previous Torch versions are supported, Torch 2.10 support was removed. We will soon also support the Torch stable ABI, so that it is possible to write kernels that support a large number of Torch versions.
kernel-builder now links libstdc++ dynamically. To support a wide range of systems, we build against libstdc++ from manylinux_2_28 (EL 8 and later).
Following our Torch support policy that the current and previous Torch versions are supported, Torch 2.10 support was removed. We will soon also support the Torch stable ABI, so that it is possible to write kernels that support a large number of Torch versions.
Post
481
🤗 Announcing the Ettin Reranker family: six new state-of-the-art CrossEncoder rerankers for search from 17M to 1B parameters, plus the full training data and the ~150-line recipe. Built on the Ettin ModernBERT encoders, Apache 2.0. Details:
All six were trained with the same single-stage pointwise MSE distillation recipe, with mixedbread-ai/mxbai-rerank-large-v2 (1.54B) as the teacher. Only the learning rate and per-device batch size change between sizes. The 1B student matches the teacher within 0.0001 NDCG@10 on MTEB(eng, v2) Retrieval, the 150M is the strongest reranker I tested in the under-600M range, and the 17M beats the 33M ms-marco-MiniLM-L12-v2 by +0.051 NDCG@10 at roughly half the parameter count.
Speed matters as much as quality for a reranker, since it determines whether the model fits the latency budget between retrieval and showing results. Our 17M is the fastest reranker in the whole comparison at 7517 pairs/sec on an H100. Our 150M runs 2.3x faster than the two other 150M ModernBERT-base rerankers (gte-reranker-modernbert-base and granite-embedding-reranker-english-r2) because the modular Transformer module propagates unpadded inputs through every layer rather than just the FA2 attention kernel. And our 1B is 2.4x faster than its 1.5B teacher while matching it on quality.
I bootstrapped the training recipe with the new train-sentence-transformers Agent Skill shipped in Sentence Transformers v5.5.0. Install it with
I wrote a blog post walking through usage, results across six embedder pairings, the speed story, and the complete training script. Check it out, or just point your Agent to the URL:
https://huggingface.co/blog/ettin-reranker
Collection: https://huggingface.co/collections/cross-encoder/ettin-rerankers
All six were trained with the same single-stage pointwise MSE distillation recipe, with mixedbread-ai/mxbai-rerank-large-v2 (1.54B) as the teacher. Only the learning rate and per-device batch size change between sizes. The 1B student matches the teacher within 0.0001 NDCG@10 on MTEB(eng, v2) Retrieval, the 150M is the strongest reranker I tested in the under-600M range, and the 17M beats the 33M ms-marco-MiniLM-L12-v2 by +0.051 NDCG@10 at roughly half the parameter count.
Speed matters as much as quality for a reranker, since it determines whether the model fits the latency budget between retrieval and showing results. Our 17M is the fastest reranker in the whole comparison at 7517 pairs/sec on an H100. Our 150M runs 2.3x faster than the two other 150M ModernBERT-base rerankers (gte-reranker-modernbert-base and granite-embedding-reranker-english-r2) because the modular Transformer module propagates unpadded inputs through every layer rather than just the FA2 attention kernel. And our 1B is 2.4x faster than its 1.5B teacher while matching it on quality.
I bootstrapped the training recipe with the new train-sentence-transformers Agent Skill shipped in Sentence Transformers v5.5.0. Install it with
hf skills add train-sentence-transformers --claude and ask Claude Code (or Codex / Cursor / Gemini CLI) to fine-tune a SentenceTransformer, CrossEncoder, or SparseEncoder model on your data.I wrote a blog post walking through usage, results across six embedder pairings, the speed story, and the complete training script. Check it out, or just point your Agent to the URL:
https://huggingface.co/blog/ettin-reranker
Collection: https://huggingface.co/collections/cross-encoder/ettin-rerankers
Post
3093
Releasing my first kernel 🔥 MaxSim
Late-interaction retrieval (ColBERT / PyLate) bottlenecks on materializing the full similarity matrix. This kernel avoids it by using tiled scoring with simdgroup_matrix (Metal) and WMMA.
The result is 3–5× speedup compared to naive PyTorch baseline 🔥
Benchmarks:
- SmallRerank (B=32, C=10): up to 3.2× (M3 Pro) / 2.8× (A100)
- HeavyRerank (B=32, C=100): up to 3.8× (M3 Pro) / 5.3× (A100)
- LongDocStress (Ld=1024): up to 6.2× (L4)
Try it out 👇
https://huggingface.co/kernels/erikkaum/maxsim
Late-interaction retrieval (ColBERT / PyLate) bottlenecks on materializing the full similarity matrix. This kernel avoids it by using tiled scoring with simdgroup_matrix (Metal) and WMMA.
The result is 3–5× speedup compared to naive PyTorch baseline 🔥
Benchmarks:
- SmallRerank (B=32, C=10): up to 3.2× (M3 Pro) / 2.8× (A100)
- HeavyRerank (B=32, C=100): up to 3.8× (M3 Pro) / 5.3× (A100)
- LongDocStress (Ld=1024): up to 6.2× (L4)
Try it out 👇
https://huggingface.co/kernels/erikkaum/maxsim
Post
262
Hugging Face MCP Server v0.3.13
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The hf_jobs tool allows mounting of volumes with hf:// URI's and some additional notes about use for data analysis.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The hf_jobs tool allows mounting of volumes with hf:// URI's and some additional notes about use for data analysis.
Post
396
🤖 I've just published Sentence Transformers v5.5.0, headlined by a new train-sentence-transformers Agent Skill that lets your AI coding agent (Claude Code, Codex, Cursor, Gemini CLI, ...) train and finetune embedding, reranker, and sparse encoder models for you. Plus training losses & fixes. Details:
The skill bundles curated guidance for the whole training workflow across all three model types: base model selection, loss and evaluator choice, hard-negative mining, distillation, LoRA, Matryoshka, multilingual training, static embeddings, etc. It also ships production-ready training template scripts the agent can adapt. Install it with
On the loss side: EmbedDistillLoss is a new embedding-level distillation loss for SentenceTransformer. Instead of distilling teacher scores like MarginMSELoss, it aligns the student's embeddings directly with pre-computed teacher embeddings, wtih an optional learnable projection for when the student and teacher dimensions differ. Second, ADRMSELoss is a new listwise learning-to-rank loss for CrossEncoder from the Rank-DistilLLM paper, aimed at the LLM-distillation reranking setting.
encode() and predict() also gained a per-call processing_kwargs override, so you can change processor settings like max_length, a vision-language model's image resolution, or a video's fps, for a single call without rebuilding the model.
The Agent Skill is the part of this release I'm most keen for people to try. Curious to hear how it works for you. I've been using it myself a lot to quickly set up some training runs that immediately use a bunch of best practices.
> pip install sentence-transformers==5.5.0
> hf skills add train-sentence-transformers
The full release notes: https://github.com/huggingface/sentence-transformers/releases/tag/v5.5.0
The skill bundles curated guidance for the whole training workflow across all three model types: base model selection, loss and evaluator choice, hard-negative mining, distillation, LoRA, Matryoshka, multilingual training, static embeddings, etc. It also ships production-ready training template scripts the agent can adapt. Install it with
hf skills add train-sentence-transformers, then just describe what you want, e.g. "finetune a reranker on my (question, answer) pairs, mine hard negatives, and push it to the Hub".On the loss side: EmbedDistillLoss is a new embedding-level distillation loss for SentenceTransformer. Instead of distilling teacher scores like MarginMSELoss, it aligns the student's embeddings directly with pre-computed teacher embeddings, wtih an optional learnable projection for when the student and teacher dimensions differ. Second, ADRMSELoss is a new listwise learning-to-rank loss for CrossEncoder from the Rank-DistilLLM paper, aimed at the LLM-distillation reranking setting.
encode() and predict() also gained a per-call processing_kwargs override, so you can change processor settings like max_length, a vision-language model's image resolution, or a video's fps, for a single call without rebuilding the model.
The Agent Skill is the part of this release I'm most keen for people to try. Curious to hear how it works for you. I've been using it myself a lot to quickly set up some training runs that immediately use a bunch of best practices.
> pip install sentence-transformers==5.5.0
> hf skills add train-sentence-transformers
The full release notes: https://github.com/huggingface/sentence-transformers/releases/tag/v5.5.0
- 3 replies
evijit
submitted a
paper to Daily Papers 16 days ago
qgallouedec
posted an update 16 days ago
Post
10076
Shipped hf-sandbox! 🥡
🧪 Running an eval that executes model-generated C on a few thousand prompts? You probably don't want any of that on your laptop.
Just shipped hf-sandbox, a Modal-style sandbox API on top of Hugging Face Jobs. Spin up an isolated, ephemeral container, run untrusted code, get the result back. No Docker on your laptop, no infra to manage.
Just pip install hf-sandbox.
Early days (v0.1); feedback and issues very welcome:
👉 https://github.com/huggingface/hf-sandbox
🧪 Running an eval that executes model-generated C on a few thousand prompts? You probably don't want any of that on your laptop.
Just shipped hf-sandbox, a Modal-style sandbox API on top of Hugging Face Jobs. Spin up an isolated, ephemeral container, run untrusted code, get the result back. No Docker on your laptop, no infra to manage.
Just pip install hf-sandbox.
Early days (v0.1); feedback and issues very welcome:
👉 https://github.com/huggingface/hf-sandbox
- 1 reply
qgallouedec
posted an update 18 days ago
Post
330
**TRL v1.4 is out 🚀** Chunked NLL loss for SFT and a first-class **OpenReward** integration.
**Chunked NLL loss for SFT — drops peak VRAM by up to 14×**
Standard SFT materializes a full
Peak GPU memory, AdamW fp32:
- Qwen3-14B, 8×H100 FSDP2, 16k seq: 58.9 GB → 38.9 GB
- Qwen3-4B, 1×H100 80GB, 16k seq: OOM → 63.8 GB
- Qwen3-32B, 8×H100 FSDP2, 8k seq: OOM → 71.2 GB
End-to-end it's consistently as fast or faster than
Works with PEFT and VLMs out of the box.
**Open Reward Standard environment adapter**
The new
v1.4 also brings MFU helpers for dense + MoE models, GRPO support for Liger 0.8.0 (delta clipping + VESPO + KL bias correction), Tülu 3's length-normalized DPO loss, four more training chat templates (Cohere, Cohere2, Gemma 3, Qwen3-2507), and a 5+ GB CUDA memory leak fix in activation offloading.
Full release notes: https://github.com/huggingface/trl/releases/tag/v1.4.0
**Chunked NLL loss for SFT — drops peak VRAM by up to 14×**
Standard SFT materializes a full
[batch × seq × vocab] logits tensor before computing cross-entropy, which dominates peak memory at long context lengths. The new loss_type="chunked_nll" path drops ignored-label tokens before the lm_head matmul and computes cross-entropy in checkpointed chunks of 256.Peak GPU memory, AdamW fp32:
- Qwen3-14B, 8×H100 FSDP2, 16k seq: 58.9 GB → 38.9 GB
- Qwen3-4B, 1×H100 80GB, 16k seq: OOM → 63.8 GB
- Qwen3-32B, 8×H100 FSDP2, 8k seq: OOM → 71.2 GB
End-to-end it's consistently as fast or faster than
nll, and unlocks sequence lengths that don't fit at all under the standard path.SFTConfig(loss_type="chunked_nll")Works with PEFT and VLMs out of the box.
**Open Reward Standard environment adapter**
The new
trl.experimental.openreward adapter plugs any environment speaking the [Open Reward Standard](https://openrewardstandard.io) protocol into any TRL trainer that takes an environment_factory. One string — a catalog name or a URL — wires the dataset, factory, and reward_func slots; tools are bound dynamically from JSON Schema, no per-env wrapper code:from trl import GRPOTrainer
from trl.experimental.openreward import OpenRewardSpec
spec = OpenRewardSpec("Eigent/SETA", num_tasks=64)
trainer = GRPOTrainer(
...,
train_dataset=spec.train_dataset,
environment_factory=spec.environment_factory,
reward_funcs=spec.reward_funcs,
)v1.4 also brings MFU helpers for dense + MoE models, GRPO support for Liger 0.8.0 (delta clipping + VESPO + KL bias correction), Tülu 3's length-normalized DPO loss, four more training chat templates (Cohere, Cohere2, Gemma 3, Qwen3-2507), and a 5+ GB CUDA memory leak fix in activation offloading.
Full release notes: https://github.com/huggingface/trl/releases/tag/v1.4.0
Post
2195
Hugging Face MCP Server v0.3.12
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The hub_repo_details tool now enables Dataset inspection (view splits, sample rows).
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The hub_repo_details tool now enables Dataset inspection (view splits, sample rows).