Igor Sosa
rogorido
AI & ML interests
None yet
Organizations
None yet
coding
pruebas
I am making some learning experiments.
-
cmarkea/distilcamembert-base-nli
Zero-Shot Classification • 68.1M • Updated • 126 • 13 -
bavarian-nlp/gliner-bavarian-v0.1
Updated • 1 -
openGPT-X/Teuken-7B-instruct-v0.6
Text Generation • 7B • Updated • 2.05k • 9 -
TheBloke/KafkaLM-70B-German-V0.1-AWQ
Text Generation • 69B • Updated • 13 • 3
infos
papers
-
AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs
Paper • 2508.16153 • Published • 160 -
LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models
Paper • 2403.13372 • Published • 175 -
LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations
Paper • 2509.03405 • Published • 23 -
KL3M Tokenizers: A Family of Domain-Specific and Character-Level Tokenizers for Legal, Financial, and Preprocessing Applications
Paper • 2503.17247 • Published • 1
datos
infos
coding
papers
-
AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs
Paper • 2508.16153 • Published • 160 -
LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models
Paper • 2403.13372 • Published • 175 -
LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations
Paper • 2509.03405 • Published • 23 -
KL3M Tokenizers: A Family of Domain-Specific and Character-Level Tokenizers for Legal, Financial, and Preprocessing Applications
Paper • 2503.17247 • Published • 1
pruebas
I am making some learning experiments.
-
cmarkea/distilcamembert-base-nli
Zero-Shot Classification • 68.1M • Updated • 126 • 13 -
bavarian-nlp/gliner-bavarian-v0.1
Updated • 1 -
openGPT-X/Teuken-7B-instruct-v0.6
Text Generation • 7B • Updated • 2.05k • 9 -
TheBloke/KafkaLM-70B-German-V0.1-AWQ
Text Generation • 69B • Updated • 13 • 3