5 results found Sort:

zilliztech
deep-searcher zilliztech
521
5.4k
apache-2.0
45
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
llm rag grok agent grok3 claude llama4 milvus openai zilliz deepseek agentic-rag deepseek-r1 deep-research vector-database reasoning-models
Created 2025-02-08
174 commits to master branch, last one 4 days ago
hao-ai-lab
Dynasor hao-ai-lab
23
146
mit
1
Simple extension on vLLM to help you speed up reasoning model without training.
llm deepseek-r1 reasoning-models
Created 2025-01-09
66 commits to main branch, last one about a month ago
UCSC-VLAA
MedReason UCSC-VLAA
7
81
unknown
3
MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs
reasoning medical-dataset reasoning-models medical-large-language-models
Created 2025-04-01
8 commits to main branch, last one 6 days ago
DolbyUUU
Logic-RL-Lite DolbyUUU
0
47
unknown
1
Lightweight replication study of DeepSeek-R1-Zero. Interesting findings include "No Aha Moment", "Longer CoT ≠ Accuracy", and "Language Mixing in Instruct Models".
llm gpt-o1 deepseek deepseek-r1 fine-tuning post-training reasoning-models reinforcement-learning reasoning-language-models
Created 2025-02-28
17 commits to main branch, last one 14 days ago
DolbyUUU
DeepEnlighten DolbyUUU
0
35
unknown
1
Pure RL to post-train base models for social reasoning capabilities. Lightweight replication of DeepSeek-R1-Zero with Social IQa dataset.
llm gpt-o1 deepseek deepseek-r1 fine-tuning post-training reasoning-models reinforcement-learning reasoning-language-models
Created 2025-03-12
9 commits to main branch, last one 29 days ago