knowledgator/retrico-lm-0.8b-sft
0.8B • Updated • 55
AI & ML interests
Text classification, relations extraction, NER, computational biology
Recent Activity
View all activity
Papers
The Million-Label NER: Breaking Scale Barriers with GLiNER bi-encoder
GLiClass: Generalist Lightweight Model for Sequence Classification Tasks
Fixed a typo: Portuguese -> Dutch
#5 opened 10 days ago
by 
prhbrt
alexandrlukashov
updated a
model 5 days ago
alexandrlukashov
published a
model 5 days ago
Update README.md
1
#3 opened 5 days ago
by 
anthonyyazdaniml
add: ggml backend
#2 opened 7 days ago
by 
werent4
werent4
updated a
model 7 days ago
alexandrlukashov
updated a
model 15 days ago
werent4
authored a
paper about 2 months ago
alexandrlukashov
authored a
paper about 2 months ago
Ihor
authored a
paper about 2 months ago
BioMike
authored a
paper about 2 months ago
Post
305
🧠 One Model to Classify, Verify, and Guard — Meet GLiClass-Instruct
When we first released GLiClass, it was a fast, zero-shot text classifier that could rival cross-encoders at a fraction of the cost. But classification alone wasn't enough. Our real ambition was a single, lightweight model that could handle the diverse range of text-understanding tasks via classification.
We are excited to announce GLiClass-Instruct – a leap forward that transforms GLiClass from a classifier into an instruction-following, multi-task engine.
What's new:
▪️ Hierarchical labeling: organize labels into structured groups for complex taxonomies
▪️ In-context learning via examples: provide few-shot examples to adapt on the fly, no fine-tuning needed
▪️ Prompting support: guide classification behavior with natural-language task descriptions
▪️ EWC for preventing catastrophic forgetting: add new capabilities without losing old ones
▪️ 3x faster inference thanks to FlashDeBERTa
New multi-task capabilities:
Beyond topic classification and sentiment analysis, GLiClass now supports:
▪️ Hallucination detection: verify whether LLM outputs are grounded in context
▪️ Rule-following verification: check if content complies with custom guidelines
▪️ Safety classification: detect prompt injections, jailbreaks, and harmful requests
These tasks are crucial for building reliable and efficient agentic systems, where every LLM output needs to be verified, every user input needs to be screened, and every response needs to follow the rules, all at minimal latency.
We release 3 instruction-following models (edge, base, large), with the large model matching SoTA classification models while unlocking entirely new task categories.
🔗 Explore more:
GitHub repo: https://github.com/Knowledgator/GLiClass
Models: https://huggingface.co/knowledgator/gliclass-multitask-large-v1.0
Our other solutions: https://www.knowledgator.com/
Post
303
Meet **GLinker** — an ultra-fast, modular, **zero-shot entity linking** framework 🚀
When we introduced the **GLiNER bi-encoder** in 2024, it enabled efficient zero-shot NER across hundreds of entity types. But that was just the beginning. Our bigger goal was always clear: **linking text to millions of entities dynamically, without retraining**.
In other words: **true entity linking at scale** ⚡
This unlocks powerful applications:
▪️ More precise search with real-world entity disambiguation
▪️ Knowledge graph construction across diverse document collections
▪️ Wikification — turning raw text into richly linked, navigable knowledge
After nearly two years of research + engineering, this vision is now real.
We’re excited to release **GLinker** — a **production-ready**, zero-shot entity linking system powered by our novel **GLiNER bi-encoder**. It efficiently detects entity spans of any length and matches them directly to entity descriptions — **no retraining required**.
**Why GLinker?**
▪️ Production-ready: multi-layer caching (Redis → Elasticsearch → PostgreSQL)
▪️ Research-friendly: fully configurable YAML pipelines
▪️ High performance: precomputed embeddings for bi-encoder models
▪️ Scalable by design: DAG-based execution + efficient batch processing
GLinker transforms raw text into **structured, disambiguated entity mentions**, bridging unstructured language with large, evolving knowledge bases.
🔗 Explore more:
GitHub: https://github.com/Knowledgator/GLinker
Report: https://github.com/Knowledgator/GLinker/blob/main/papers/GLiNER_bi_Encoder_paper.pdf
Linking models: https://huggingface.co/collections/knowledgator/gliner-linker
Bi-encoder models: https://huggingface.co/collections/knowledgator/gliner-bi-encoder
When we introduced the **GLiNER bi-encoder** in 2024, it enabled efficient zero-shot NER across hundreds of entity types. But that was just the beginning. Our bigger goal was always clear: **linking text to millions of entities dynamically, without retraining**.
In other words: **true entity linking at scale** ⚡
This unlocks powerful applications:
▪️ More precise search with real-world entity disambiguation
▪️ Knowledge graph construction across diverse document collections
▪️ Wikification — turning raw text into richly linked, navigable knowledge
After nearly two years of research + engineering, this vision is now real.
We’re excited to release **GLinker** — a **production-ready**, zero-shot entity linking system powered by our novel **GLiNER bi-encoder**. It efficiently detects entity spans of any length and matches them directly to entity descriptions — **no retraining required**.
**Why GLinker?**
▪️ Production-ready: multi-layer caching (Redis → Elasticsearch → PostgreSQL)
▪️ Research-friendly: fully configurable YAML pipelines
▪️ High performance: precomputed embeddings for bi-encoder models
▪️ Scalable by design: DAG-based execution + efficient batch processing
GLinker transforms raw text into **structured, disambiguated entity mentions**, bridging unstructured language with large, evolving knowledge bases.
🔗 Explore more:
GitHub: https://github.com/Knowledgator/GLinker
Report: https://github.com/Knowledgator/GLinker/blob/main/papers/GLiNER_bi_Encoder_paper.pdf
Linking models: https://huggingface.co/collections/knowledgator/gliner-linker
Bi-encoder models: https://huggingface.co/collections/knowledgator/gliner-bi-encoder
Post
1328
Hey builders 👷♀️
We’re Knowledgator, the team behind open-source NLP models like GLiNER, GLiClass, and many other used for zero-shot text classification and information extraction.
If you’ve explored them on Hugging Face or used our frameworks from GitHub, we’d love your input:
🧩 Which of our models, like GLiNER or zero-shot classifiers, do you find helpful in your practical workflows?
🧩 How’s the setup, performance, and accuracy been for you?
🧩 Anything confusing, buggy, or missing that would make your workflow smoother?
Your feedback helps us improve speed, clarity, and stability for everyone in the open-source community.
💬 Comment directly here or join the discussion. We read every one 😉:
GitHub: https://github.com/Knowledgator
Discord: https://discord.gg/GXRcAVJQ
HuggingFace: knowledgator
📝 Want to shape our next release?
Click here to complete this 2-min survey: https://docs.google.com/forms/d/e/1FAIpQLSdyz2UMHrMDX8S9stpBk0wyfngtKSYzwk-02mN1VNYDdTw8OQ/viewform
We’re Knowledgator, the team behind open-source NLP models like GLiNER, GLiClass, and many other used for zero-shot text classification and information extraction.
If you’ve explored them on Hugging Face or used our frameworks from GitHub, we’d love your input:
🧩 Which of our models, like GLiNER or zero-shot classifiers, do you find helpful in your practical workflows?
🧩 How’s the setup, performance, and accuracy been for you?
🧩 Anything confusing, buggy, or missing that would make your workflow smoother?
Your feedback helps us improve speed, clarity, and stability for everyone in the open-source community.
💬 Comment directly here or join the discussion. We read every one 😉:
GitHub: https://github.com/Knowledgator
Discord: https://discord.gg/GXRcAVJQ
HuggingFace:
📝 Want to shape our next release?
Click here to complete this 2-min survey: https://docs.google.com/forms/d/e/1FAIpQLSdyz2UMHrMDX8S9stpBk0wyfngtKSYzwk-02mN1VNYDdTw8OQ/viewform
alexandrlukashov
authored a
paper 8 months ago
werent4
authored a
paper 8 months ago
Ihor
authored a
paper 8 months ago
BioMike
authored a
paper 8 months ago
Ihor
authored a
paper about 1 year ago
Post
1927
🚀 Reproducing DeepSeek R1 for Text-to-Graph Extraction
I’ve been working on replicating DeepSeek R1, focusing on zero-shot text-to-graph extraction—a challenging task where LMs extract entities and relations from text based on predefined types.
🧠 Key Insight:
Language models struggle when constrained by entity/relation types. Supervised training alone isn’t enough, but reinforcement learning (RL), specifically Guided Reward Policy Optimization (GRPO), shows promise.
💡 Why GRPO?
It trains the model to generate structured graphs, optimizing multiple reward functions (format, JSON validity, and extraction accuracy).
It allows the model to learn from both positive and hard negative examples dynamically.
RL can be fine-tuned to emphasize relation extraction improvements.
📊 Early Results:
Even with limited training, F1 scores consistently improved, and we saw clear benefits from RL-based optimization. More training = better performance!
🔬 Next Steps:
We’re scaling up experiments with larger models and high-quality data. Stay tuned for updates! Meanwhile, check out one of our experimental models here:
Ihor/Text2Graph-R1-Qwen2.5-0.5b
📔 Learn more details from the blog post: https://medium.com/p/d8b648d9f419
Feel free to share your thoughts and ask questions!
I’ve been working on replicating DeepSeek R1, focusing on zero-shot text-to-graph extraction—a challenging task where LMs extract entities and relations from text based on predefined types.
🧠 Key Insight:
Language models struggle when constrained by entity/relation types. Supervised training alone isn’t enough, but reinforcement learning (RL), specifically Guided Reward Policy Optimization (GRPO), shows promise.
💡 Why GRPO?
It trains the model to generate structured graphs, optimizing multiple reward functions (format, JSON validity, and extraction accuracy).
It allows the model to learn from both positive and hard negative examples dynamically.
RL can be fine-tuned to emphasize relation extraction improvements.
📊 Early Results:
Even with limited training, F1 scores consistently improved, and we saw clear benefits from RL-based optimization. More training = better performance!
🔬 Next Steps:
We’re scaling up experiments with larger models and high-quality data. Stay tuned for updates! Meanwhile, check out one of our experimental models here:
Ihor/Text2Graph-R1-Qwen2.5-0.5b
📔 Learn more details from the blog post: https://medium.com/p/d8b648d9f419
Feel free to share your thoughts and ask questions!
- 2 replies