Autotrain compatible Base model:epistemeai/reasonin... Base model:finetune:epistemeai... Conversational En Endpoints compatible Instruct Llama Region:us Safetensors Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/EpistemeAI/ReasoningCore-1.0-3B-Instruct-r01-Reflect-Math
ReasoningCore 1.0 3B Instruct R01 Reflect Math Benchmarks
MMLU Pro: 20.26
GPQA: 1.34
MUSR: 1.6
BBH: 19.82
IFEval: 59.03 vs 88 (so35)-32.9%
MATH Lvl 5: 14.8
LLME Score: 0.27778
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)
ReasoningCore 1.0 3B Instruct R01 Reflect Math Parameters and Internals
| LLM Name | ReasoningCore 1.0 3B Instruct R01 Reflect Math |
| Repository 🤗 | https://huggingface.co/EpistemeAI/ReasoningCore-1.0-3B-Instruct-r01-Reflect-Math |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 6.5 GB |
| Updated | 2025-04-09 |
| Maintainer | EpistemeAI |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Gated Model | Yes |
| Model Architecture | LlamaForCausalLM |
| License | proprietary |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <|finetune_right_pad_id|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to ReasoningCore 1.0 3B Instruct R01 Reflect Math
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 1695709 | 1610 |
| DeepSeek R1 Distill Llama 3B | 128K / 6.5 GB | 1782 | 15 |
| Llama 3.2 3B RP Toxic Fuse | 128K / 6.4 GB | 153 | 2 |
| TwinLlama 3.2 3B Instruct | 128K / 6.5 GB | 35 | 0 |
| Zeitgeist 3B V1 | 128K / 6.5 GB | 105 | 5 |
| Llama 3.2 3B Instruct | 128K / 6.5 GB | 141152 | 73 |
| ... 3.2 3B Math Instruct RE1 ORPO | 128K / 6.5 GB | 48 | 0 |
| ReasoningCore 3B T1 1 | 128K / 6.5 GB | 22 | 1 |
| ...lama 3.2 Rabbit Ko 3B Instruct | 128K / 6.5 GB | 1594 | 11 |
| Llama 3.2 3B ToxicKod | 128K / 6.4 GB | 4 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than EpistemeAI/ReasoningCore-1.0-3B-Instruct-r01-Reflect-Math .
Rank the ReasoningCore 1.0 3B Instruct R01 Reflect Math 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? 49991 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124