9 results found Sort:

zzli2022
Awesome-System2-Reasoning-LLM zzli2022
27
784
unknown
12
Latest Advances on System-2 Reasoning
o1 o3 r1 rl prm mcts system-2 benchmark reasoning slow-fast macro-action self-improve
Created 2025-02-09
46 commits to main branch, last one 2 days ago
turningpoint-ai
VisualThinker-R1-Zero turningpoint-ai
18
501
unknown
15
Explore the Multimodal “Aha Moment” on 2B Model
r1 grpo r1-zero deepseek reasoning multimodal deepseek-r1 multimodal-r1 post-training deepseek-r1-zero multimodal-journey reinforcement-learning
Created 2025-02-24
147 commits to main branch, last one a day ago
modelscope
awesome-deep-reasoning modelscope
9
293
unknown
3
Collect every awesome work about r1!
o1 r1 rl grpo qwen deepseek reasoning collection
Created 2025-01-30
81 commits to main branch, last one 6 hours ago
RyanLiu112
compute-optimal-tts RyanLiu112
19
220
mit
8
Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".
o1 r1 test-time-scaling large-language-model
Created 2025-02-10
53 commits to main branch, last one 27 days ago
SmallDoges
small-doge SmallDoges
11
116
apache-2.0
3
Doge Family of Small Language Model
r1 nlp python chinese pytorch deepseek-r1 transformer deep-learning mechine-learning foundation-models attention-mechanism small-language-models dynamic-mask-attention reinforcement-learning attention-is-all-you-need natural-language-processing cross-domain-mixture-of-experts
Created 2025-02-01
268 commits to main branch, last one a day ago
DMontgomery40
deepseek-mcp-server DMontgomery40
11
115
mit
1
Model Context Protocol server for DeepSeek's advanced language models
r1 mcp deepseek-r1 deepseek-v3 deepseek-api deepseek-chat model-context-protocol
Created 2025-01-21
21 commits to main branch, last one about a month ago
CJReinforce
PURE CJReinforce
3
88
unknown
2
SOTA RL fine-tuning solution for advanced math reasoning of LLM
o1 r1 rl llm reasoning mathematics reinforcement-learning reinforcement-finetuning
Created 2025-02-09
36 commits to main branch, last one 8 days ago
LazaUK
AIFoundry-DeepSeek-SDK LazaUK
6
31
mit
2
Notebooks to demo the use of Azure AI Python SDK / LangChain with DeepSeek R1 reasoning model in Azure AI Foundry.
ai r1 sdk azure openai python foundry deepseek langchain
Created 2025-02-02
30 commits to main branch, last one about a month ago
glide-the
InterpretationoDreams glide-the
2
29
apache-2.0
1
使用langchain进行任务规划，构建子任务的会话场景资源，通过MCTS任务执行器，来让每个子任务通过在上下文中资源，通过自身反思探索来获取自身对问题的最优答案；这种方式依赖模型的对齐偏好，我们在每种偏好上设计了一个工程框架，来完成自我对不同答案的奖励进行采样策略
r1 cot mcts-agents deep-research task-planning
Created 2023-09-16
226 commits to main branch, last one 9 days ago