4bit Autotrain compatible Base model:agentica-org/deepsc... Base model:finetune:agentica-o... Conversational Dataset:bespokelabs/bespoke-st... Dataset:cognitivecomputations/... Dataset:openai/gsm8k Dataset:primeintellect/numinam... Dataset:simplescaling/s1k Edge-device En Endpoints compatible Finetuned Quantized Qwen2 Reasoning Region:us Research Safetensors Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/Daemontatox/mini-Cogito-R1
Mini Cogito R1 Benchmarks
MMLU Pro: 5.35
GPQA: 4.92
MUSR: 2.99
BBH: 6.04
IFEval: 22.98 vs 88 (so35)-73.9%
MATH Lvl 5: 27.49
LLME Score: 0.27
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)
Mini Cogito R1 Parameters and Internals
| LLM Name | Mini Cogito R1 |
| Repository 🤗 | https://huggingface.co/Daemontatox/mini-Cogito-R1 |
| Base Model(s) | |
| Model Size | 1.5b |
| Required VRAM | 3.5 GB |
| Updated | 2025-05-09 |
| Maintainer | Daemontatox |
| Model Type | qwen2 |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 24576 |
| Model Max Length | 24576 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | LlamaTokenizerFast |
| Padding Token | <|vision_pad|> |
| Vocabulary Size | 151936 |
| Torch Data Type | bfloat16 |
Best Alternatives to Mini Cogito R1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...ill Qwen 1.5B Unsloth Bnb 4bit | 128K / 1.8 GB | 29949 | 15 |
| ... R1 Distill Qwen 1.5B Bnb 4bit | 128K / 1.6 GB | 4948 | 10 |
| DeepSeek R1 ForumNXT | 128K / 3.5 GB | 10 | 0 |
| Research PathfinderAI | 128K / 3.5 GB | 19 | 0 |
| Umbr0x 1.5B V3.1 16bit 2 | 128K / 15.2 GB | 19 | 0 |
| Qwen2 1.5B SFT 16bit Alpha | 128K / 3.1 GB | 85 | 0 |
| ...pSeek R1 Distill Qwen 1.5B 500 | 128K / 1.7 GB | 5 | 0 |
| Atlas Flash 1.5B Preview | 128K / 3.5 GB | 112 | 2 |
| Deep Ft8 Grp 16bit | 128K / 3.5 GB | 5 | 0 |
| Deep Ft5 Grp 16bit | 128K / 3.5 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Daemontatox/mini-Cogito-R1 .
Rank the Mini Cogito R1 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? 47197 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227