A series of open-source Bulgarian language models fine-tuned for function calling and tool use. 2.6B, 9B, and 27B parameter variants.
Simeon Emanuilov PRO
s-emanuilov
AI & ML interests
Software Engineer & Ph.D. candidate | Specializing in ML/DL system development & applying AI to solve real-world business problems.
Recent Activity
updated
a collection
2 days ago
Tucan — Tool using and function calling in Bulgarian
updated
a collection
2 days ago
Tucan — Tool using and function calling in Bulgarian
updated
a collection
2 days ago
Tucan
Organizations
Papers to improve reasoning capabilities of language models
Papers exploring autonomous AI systems and frameworks for building intelligent agents that can perceive environment, plan actions and use tools.
-
Agent Laboratory: Using LLM Agents as Research Assistants
Paper • 2501.04227 • Published • 92 -
Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
Paper • 2501.05707 • Published • 20 -
Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training
Paper • 2501.11425 • Published • 106
Papers exploring RAG techniques that combine language models with external knowledge retrieval to improve accuracy and reduce hallucinations.
A collection of models along with the training dataset, designed to improve search queries and retrieval in RAG systems.
Papers on AI models that combine vision and language capabilities.
-
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
Paper • 2501.03895 • Published • 53 -
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs
Paper • 2501.06186 • Published • 66 -
Multimodal LLMs Can Reason about Aesthetics in Zero-Shot
Paper • 2501.09012 • Published • 10
Papers exploring efficient and lightweight language models that achieve strong performance while being smaller and faster than large foundation models
Papers exploring vector representations of text and other data types, focusing on embedding models, techniques, and applications for semantic search.
A series of open-source Bulgarian language models fine-tuned for function calling and tool use. 2.6B, 9B, and 27B parameter variants.
A collection of models along with the training dataset, designed to improve search queries and retrieval in RAG systems.
Papers to improve reasoning capabilities of language models
Papers on AI models that combine vision and language capabilities.
-
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
Paper • 2501.03895 • Published • 53 -
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs
Paper • 2501.06186 • Published • 66 -
Multimodal LLMs Can Reason about Aesthetics in Zero-Shot
Paper • 2501.09012 • Published • 10
Papers exploring autonomous AI systems and frameworks for building intelligent agents that can perceive environment, plan actions and use tools.
-
Agent Laboratory: Using LLM Agents as Research Assistants
Paper • 2501.04227 • Published • 92 -
Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
Paper • 2501.05707 • Published • 20 -
Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training
Paper • 2501.11425 • Published • 106
Papers exploring efficient and lightweight language models that achieve strong performance while being smaller and faster than large foundation models
Papers exploring RAG techniques that combine language models with external knowledge retrieval to improve accuracy and reduce hallucinations.
Papers exploring vector representations of text and other data types, focusing on embedding models, techniques, and applications for semantic search.