Merged Model Autotrain compatible Base model:zelk12/mt3-gen5-mai... Base model:zelk12/mt3-gen5-mmg... Conversational Endpoints compatible Gemma2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/zelk12/MT3-Gen5-gemma-2-9B_v1
MT3 Gen5 Gemma 2 9B V1 Benchmarks
MMLU Pro: 37.32
GPQA: 13.2
MUSR: 11.48
BBH: 44.16
IFEval: 79.96 vs 88 (so35)-9.1%
MATH Lvl 5: 10.95
LLME Score: 0.37852
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)
MT3 Gen5 Gemma 2 9B V1 Parameters and Internals
| LLM Name | MT3 Gen5 Gemma 2 9B V1 |
| Repository 🤗 | https://huggingface.co/zelk12/MT3-Gen5-gemma-2-9B_v1 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 9b |
| Required VRAM | 20.4 GB |
| Updated | 2025-01-03 |
| Maintainer | zelk12 |
| Model Type | gemma2 |
| Model Files | |
| Model Architecture | Gemma2ForCausalLM |
| License | gemma |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | bfloat16 |
Best Alternatives to MT3 Gen5 Gemma 2 9B V1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Gemma 2 9B It SimPO | 8K / 18.6 GB | 16599 | 137 |
| Gemma 2 9B It | 8K / 18.6 GB | 319700 | 608 |
| Gemma 2 9B | 8K / 37.1 GB | 123232 | 619 |
| ...2 9B Cpt Sahabatai V1 Instruct | 8K / 18.6 GB | 2545 | 28 |
| Wiroai Turkish Llm 9B | 8K / 37.1 GB | 36830 | 13 |
| MT Merge5 Gemma 2 9B | 8K / 20.4 GB | 38 | 2 |
| Magnolia V3 Gemma2 8K 9B | 8K / 18.6 GB | 30 | 2 |
| MT4 Gen5 Gemma 2 9B | 8K / 20.4 GB | 39 | 2 |
| MTM Merge Gemma 2 9B | 8K / 20.4 GB | 10 | 1 |
| MT Merge4 Gemma 2 9B | 8K / 20.4 GB | 80 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than zelk12/MT3-Gen5-gemma-2-9B_v1 .
Rank the MT3 Gen5 Gemma 2 9B 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! 🌟
What open-source LLMs or SLMs are you in search of? 40827 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227