Hugging Face – Posts

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

All HF Hub posts

AdinaY

posted an update 2 days ago

Post

2186

From ChatGPT Healthcare to Claude for healthcare, AI in medicine is speeding up🚀

Now BaichuanAI joins with Baichuan-M3 🏥 an open medical LLM trained for clinical decision-making

https://huggingface.co/collections/baichuan-inc/baichuan-m3

✨ 235B - Apache2.0
✨ Lower hallucinations via Fact-Aware RL
✨ Built for long medical chats

2 replies

YatharthS

posted an update about 22 hours ago

Post

1171

I just released NovaSR, a tiny 52kb audio upsampler that can enhance 3600 seconds of muffled 16khz audio in to clearer 48khz audio in just 1 second!

NovaSR can
- Enhance TTS model quality.
- Restore poor quality datasets.
- Work on any device(just 52kb which is smaller than a 3 second audio file!)

Model: YatharthS/NovaSR
Space to try it: YatharthS/NovaSR
Github repo: https://github.com/ysharma3501/NovaSR

sergiopaniego

posted an update 2 days ago

Post

2114

New REPL environment in OpenEnv available! ✨
Used in the Recursive Language Models (RLM) paper by Alex Zhang.

Ready for inference & post-training using trajectories. Handles long contexts:

> Run Python code in a sandbox
> Make recursive calls to LMs
> Explore data programmatically
> Return final result

Docs: https://meta-pytorch.org/OpenEnv/environments/repl/
Inference script: https://github.com/meta-pytorch/OpenEnv/blob/main/examples/repl_oolong_simple.py

TravisMuhlestein

posted an update 2 days ago

Post

1848

Agentic AI doesn’t fail because it lacks intelligence — it fails because it lacks context.

As agents become more autonomous, the real challenge shifts from generation to governance:
understanding when, why, and under what constraints an agent should act.

At GoDaddy, we’ve been treating context as a first-class primitive for agentic systems —
combining identity, intent, permissions, and environment so agents can operate responsibly in production.

Context is what turns automation into judgment.
Without it, autonomy becomes risk.

This post outlines how we’re thinking about the transition from task execution to context-aware agentic systems, and what that means for building AI that can be trusted at scale.

👉 How we build context for agentic AI:
https://www.godaddy.com/resources/news/how-godaddy-builds-context-for-agentic-ai

Curious how others here are modeling context, trust boundaries, and decision constraints in agentic architectures.

1 reply

Ujjwal-Tyagi

posted an update 1 day ago

Post

1816

I am very excited to see the release of nyuuzyou/gitee-code. This is exactly what I have been looking for. Thank you to @nyuuzyou for his hard work on this.

3 replies

nyuuzyou

posted an update 2 days ago

Post

1505

🇨🇳 Gitee Code Dataset - The Missing Piece of the Stack
nyuuzyou/gitee-code

Gitee is not included in the Software Heritage archive, meaning it is currently missing from datasets like The Stack. This release fills that massive gap, serving as the largest Chinese code dataset and one of the largest code corpuses overall.

- 819,472,785 files from 3,105,923 repositories
- 536 GB compressed Parquet storage
- 554 programming languages
- Extensive quality filtering: Removed vendor code, artifacts, and generated files
- Rich Chinese language understanding: High volume of Chinese comments and docs

Huge thanks to Hugging Face for the storage grant that made hosting this (and all my other datasets) possible!

I have also already dropped several other new code datasets and rolled out QoL improvements for older ones. I will be dropping posts on those throughout the week.

1 reply

mmhamdy

posted an update about 23 hours ago

Post

785

The new DeepSeek Engram paper is super fun! It also integrates mHC, and I suspect they're probably releasing all these papers to make the V4 report of reasonable length😄

Here's a nice short summary from Gemini

kanaria007

posted an update 2 days ago

Post

1970

✅ New Article: Designing Semantic Memory (v0.1)

Title:
🧠 Designing Semantic Memory: SIM/SIS Patterns for Real Systems
🔗 https://huggingface.co/blog/kanaria007/designing-semantic-memory

---

Summary:
Semantic Compression is about *what meaning to keep*.
This article is about *where that meaning lives*—and how to keep it *queryable, explainable, and governable* using two layers:

* *SIM*: operational semantic memory (low-latency, recent, jump-loop-adjacent)
* *SIS*: archival/analytic semantic store (long retention, heavy queries, audits)

Core idea: store “meaning” as *typed semantic units* with scope, provenance, goal tags, retention, and *backing_refs* (URI/hash/ledger anchors) so you can answer *“why did we do X?”* without turning memory into a blob.

---

Why It Matters:
• Prevents “semantic junk drawer” memory: *units become contracts*, not vibes
• Makes audits and incidents tractable: *reconstruct semantic context* (L3-grade)
• Preserves reversibility/accountability with *backing_refs*, even under redaction
• Adds semantic health checks: *SCover_sem / SInt / LAR_sem* (memory that stays reliable)

---

What’s Inside:
• Minimal *semantic_unit* schema you can run on relational/doc/graph backends
• Query/index playbook: ops (L1/L2) vs evidence/audit (L3)
• Domain patterns (CityOS / OSS supply chain / learning-support)
• Migration path: sidecar writer → low-risk reads → SI-Core integration
• Failure modes & anti-patterns: missing backing_refs, over-eager redaction, SIM-as-cache, etc.

---

📖 Structured Intelligence Engineering Series
Formal contracts live in the spec/eval packs; this is the *how-to-model / how-to-operate* layer for semantic memory that can survive real audits and real failures.

2 replies

sequelbox

posted an update 1 day ago

Post

1057

NEW RELEASE: it's here! Meet the newest member of the Valiant crew: Guardpoint, our new medical reasoning model!
- Trained on medical knowledge, management, diagnosis, and tasks from DeepSeek-V3.2-Speciale!
- Structured medical reasoning responses are efficient and informative, cutting token costs for faster inference!
- Wide-ranging knowledge base: trained on a wide variety of medical disciplines, patient types, and query structures!
- High quality medical responses emphasize performance, brevity, specificity, statistical rationality, and openness.

Get it now:
Guardpoint for Qwen 3 32B: ValiantLabs/Qwen3-32B-Guardpoint
Guardpoint for Qwen 3 14B: ValiantLabs/Qwen3-14B-Guardpoint
Powered by our new structured medical reasoning dataset: sequelbox/Superpotion-DeepSeek-V3.2-Speciale

We've been working hard on Guardpoint; we're really excited to share it with everyone!

We'll be bringing Guardpoint to more models soon, along with further releases for the Shining Valiant and Esper series!

Get our experimental models: https://huggingface.co/collections/sequelbox/experimental-reasoning-models
Get our reasoning datasets: https://huggingface.co/collections/sequelbox/reasoning-datasets

Help support our releases, donations used for our experimental models and datasets: sequelbox/SupportOpenSource

2026 is going to be an amazing year for open source AI! It's time for the AI revolution you need; from the bottom up, built together by all of us.

for love, friendship, and better days,
allegra

dhruv3006

posted an update 1 day ago

Post

1351

Voiden gives you two ways to work with GraphQL - so you can focus on writing and testing queries with confidence.

1. Importing a GraphQL Schema File

You can import a GraphQL schema file such as .graphql or .gql directly into Voiden.

When you do this:

- Voiden reads all types, queries, mutations, and subscriptions from the schema
- The schema becomes available locally and works well in offline scenarios
- You get a stable, version-controlled setup that aligns nicely with Git workflows

This approach is ideal when you already have the schema file and want full control over it.

2. Using GraphQL Introspection

Alternatively, you can provide a GraphQL endpoint URL to Voiden.

In this case :

- Voiden make an introspection query to the GraphQL server
- The server returns all available types, queries, mutations, and subscriptions
- Voiden automatically loads this information so you can start querying immediately

This option is perfect for quickly exploring a live GraphQL API or when the schema file is not available locally.

Use GraphQL in our beta version : https://voiden.md/beta

Recently active users