Autotrain compatible Base model:finetune:huggingfac... Base model:huggingfacetb/smoll... Code Conversational Cot En Endpoints compatible Instruct Llama Pytorch Reasoning Region:us Safetensors Sft Superthoughts Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/Pinkstack/Superthoughts-lite-1.8B-experimental-o1
Superthoughts Lite 1.8B Experimental O1 Benchmarks
MMLU Pro: 9.45
GPQA: 3.36
MUSR: 1.76
BBH: 9.13
IFEval: 3.75 vs 88 (so35)-95.7%
MATH Lvl 5: 3.17
LLME Score: 0.29278
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Superthoughts Lite 1.8B Experimental O1 Parameters and Internals
| LLM Name | Superthoughts Lite 1.8B Experimental O1 |
| Repository 🤗 | https://huggingface.co/Pinkstack/Superthoughts-lite-1.8B-experimental-o1 |
| Base Model(s) | |
| Model Size | 1.7b |
| Required VRAM | 3.6 GB |
| Updated | 2025-02-22 |
| Maintainer | Pinkstack |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.48.2 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 49152 |
| Torch Data Type | float16 |
Best Alternatives to Superthoughts Lite 1.8B Experimental O1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| SmolLM2 1.7B Instruct | 8K / 3.4 GB | 380890 | 549 |
| Superthoughts Lite V1 | 8K / 3.4 GB | 1065 | 2 |
| SmolTulu 1.7B Reinforced | 8K / 3.4 GB | 242 | 5 |
| SmolLM2 1.7B Instruct | 8K / 3.4 GB | 8549 | 4 |
| SmolLM2 1.7 Persona | 8K / 3.5 GB | 8 | 0 |
| ...RM 1 Smollm2 1.7B Lcot PyTorch | 8K / 3.4 GB | 75 | 0 |
| SmolLM2 Math IIO 1.7B Instruct | 8K / 3.4 GB | 107 | 8 |
| SmolLM2 1.7B Instruct | 8K / 3.4 GB | 115 | 3 |
| Immy V3 | 8K / 3.4 GB | 80 | 0 |
| SmolLM 1.7B Instruct | 2K / 3.4 GB | 30752 | 110 |
Note: green Score (e.g. "73.2") means that the model is better than Pinkstack/Superthoughts-lite-1.8B-experimental-o1 .
Rank the Superthoughts Lite 1.8B Experimental O1 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! 🌟
What open-source LLMs or SLMs are you in search of? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227