LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

AdaptThink 1.5B Delta0.075 by THU-KEG

 »  All LLMs  »  THU-KEG  »  AdaptThink 1.5B Delta0.075   URL Share it on

  5   

AdaptThink 1.5B Delta0.075 is an open-source language model by THU-KEG. Features: 1.5b LLM, VRAM: 3.5GB, Context: 128K, License: mit, LLM Explorer Score: 0.19.

  Arxiv:2505.13417 Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a... Dataset:agentica-org/deepscale...   Efficient reasoning   Hybrid reasoning   Lrm   Qwen2   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/THU-KEG/AdaptThink-1.5B-delta0.075 

AdaptThink 1.5B Delta0.075 Benchmarks

LLME Score: 0.19317
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
AdaptThink 1.5B Delta0.075 (THU-KEG/AdaptThink-1.5B-delta0.075)
🌟 Advertise your project 🚀

AdaptThink 1.5B Delta0.075 Parameters and Internals

LLM NameAdaptThink 1.5B Delta0.075
Repository 🤗https://huggingface.co/THU-KEG/AdaptThink-1.5B-delta0.075 
Base Model(s)  deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B   deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Model Size1.5b
Required VRAM3.5 GB
Updated2026-01-04
MaintainerTHU-KEG
Model Typeqwen2
Model Files  3.5 GB
Model ArchitectureQwen2ForCausalLM
Licensemit
Context Length131072
Model Max Length131072
Transformers Version4.51.2
Tokenizer ClassLlamaTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>
Vocabulary Size151936
Torch Data Typebfloat16

Best Alternatives to AdaptThink 1.5B Delta0.075

Best Alternatives
Context / RAM
Downloads
Likes
ReaderLM V2500K / 3.1 GB14849779
Reader Lm 1.5B250K / 3.1 GB440608
DeepSeek R1 Distill Qwen 1.5B128K / 3.5 GB8307481465
VibeThinker 1.5B128K / 3.5 GB2025520
Ko R1 1.5B Preview128K / 7.1 GB159
Qwen2.5 1.5B128K / 3.1 GB888741150
AceInstruct 1.5B128K / 3.5 GB7688020
Qwen2 1.5B128K / 3.1 GB139863102
1.5B Cold Start SFT128K / 3.5 GB45030
OpenReasoning Nemotron 1.5B128K / 3.1 GB793456
Note: green Score (e.g. "73.2") means that the model is better than THU-KEG/AdaptThink-1.5B-delta0.075.

Rank the AdaptThink 1.5B Delta0.075 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 53373 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer