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

Superthoughts Lite V1 by Pinkstack

 »  All LLMs  »  Pinkstack  »  Superthoughts Lite V1   URL Share it on

  985   
  Arxiv:2402.03300   Autotrain compatible Base model:finetune:huggingfac... Base model:huggingfacetb/smoll...   Conversational   Cot   Dataset:openai/gsm8k Dataset:pinkstack/intructions-...   En   Endpoints compatible   Grpo   Instruct   Llama   Pytorch   Reasoning   Region:us   Rl   Safetensors   Superthoughts   Trl
Model Card on HF 🤗: https://huggingface.co/Pinkstack/Superthoughts-lite-v1 

Superthoughts Lite V1 Benchmarks

MMLU Pro: 8.39
GPQA: 4.14
MUSR: 3.43
BBH: 8.9
IFEval: 16.59 vs 88 (so35)-81.1%
MATH Lvl 5: 2.95
LLME Score: 0.31202
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Superthoughts Lite V1 (Pinkstack/Superthoughts-lite-v1)

Superthoughts Lite V1 Parameters and Internals

LLM NameSuperthoughts Lite V1
Repository 🤗https://huggingface.co/Pinkstack/Superthoughts-lite-v1 
Base Model(s)  HuggingFaceTB/SmolLM2-1.7B-Instruct   HuggingFaceTB/SmolLM2-1.7B-Instruct
Model Size1.7b
Required VRAM3.4 GB
Updated2025-03-21
MaintainerPinkstack
Model Typellama
Instruction-BasedYes
Model Files  3.4 GB   3.4 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.48.3
Tokenizer ClassGPT2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size49153
Torch Data Typefloat16

Best Alternatives to Superthoughts Lite V1

Best Alternatives
Context / RAM
Downloads
Likes
SmolLM2 1.7B Instruct 16K16K / 3.4 GB17027
SmolLM2 1.7B Instruct8K / 3.4 GB549436580
SmolTulu 1.7B Reinforced8K / 3.4 GB4385
SmolLM2 1.7B R1 Distilled8K / 3.4 GB910
...ghts Lite 1.8B Experimental O18K / 3.6 GB2631
...urtis E1 SmolLM2 1.7B Instruct8K / 6.7 GB500
SmolLM2 1.7B Instruct8K / 3.4 GB47944
SmolLM2 1.7 Persona8K / 3.5 GB50
...RM 1 Smollm2 1.7B Lcot PyTorch8K / 3.4 GB170
SmolLM2 Math IIO 1.7B Instruct8K / 3.4 GB562
Note: green Score (e.g. "73.2") means that the model is better than Pinkstack/Superthoughts-lite-v1.

Rank the Superthoughts Lite V1 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? 45354 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.
Release v20241227
  Support LLM Explorer