Merged Model Arxiv:2212.04089 Arxiv:2311.03099 Autotrain compatible Base model:nvidia/acemath-7b-i... Base model:open-r1/openr1-qwen... Base model:qwen/qwen2.5-math-7... Conversational Endpoints compatible Instruct Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/formulae/mita-v1.2-7b-2-24-2025
Mita V1.2 7B 2 24 2025 Benchmarks
MMLU Pro: 26.21
GPQA: 7.49
MUSR: 12.63
BBH: 28.41
IFEval: 25.64 vs 88 (so35)-70.9%
MATH Lvl 5: 48.79
LLME Score: 0.29595
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)
Mita V1.2 7B 2 24 2025 Parameters and Internals
| LLM Name | Mita V1.2 7B 2 24 2025 |
| Repository 🤗 | https://huggingface.co/formulae/mita-v1.2-7b-2-24-2025 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 7b |
| Required VRAM | 15.2 GB |
| Updated | 2025-07-02 |
| Maintainer | formulae |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.48.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Mita V1.2 7B 2 24 2025
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 7B Instruct 1M | 986K / 15.4 GB | 1601961 | 334 |
| Qwen2.5 7B RRP 1M | 986K / 15.2 GB | 1722 | 6 |
| Hush Qwen2.5 7B RP V1.4 1M | 986K / 15.2 GB | 15 | 2 |
| Qwen2.5 7B CelestialHarmony 1M | 986K / 14.8 GB | 13 | 7 |
| Q2.5 Instruct 1M Harmony | 986K / 15.2 GB | 11 | 2 |
| Impish QWEN 7B 1M | 986K / 15.2 GB | 79 | 4 |
| COCO 7B Instruct 1M | 986K / 15.2 GB | 23 | 4 |
| Qwen2.5 7B Instruct 1M | 986K / 15.2 GB | 2028 | 2 |
| Apollo 7B | 986K / 15.2 GB | 13 | 0 |
| Qwen2.5 7B Sky R1 Mini | 986K / 15.2 GB | 11 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than formulae/mita-v1.2-7b-2-24-2025 .
Rank the Mita V1.2 7B 2 24 2025 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? 49328 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124