4bit Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mistral-n... Chat Conversational Dataset:rubenroy/gammacorpus-v... De En Endpoints compatible Es Fr Gammacorpus Geneva Instruct It Ja Mistral Pt Quantized Region:us Ru Safetensors Sharded Tensorflow Trl Unsloth Zh
Model Card on HF 🤗: https://huggingface.co/rubenroy/Geneva-12B-GCv2-5m
Geneva 12B GCv2 5M Benchmarks
MMLU Pro: 25
GPQA: 5.03
MUSR: 5.19
BBH: 32.65
IFEval: 25.86 vs 88 (so35)-70.6%
MATH Lvl 5: 8.01
LLME Score: 0.31999
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)
Geneva 12B GCv2 5M Parameters and Internals
| LLM Name | Geneva 12B GCv2 5M |
| Repository 🤗 | https://huggingface.co/rubenroy/Geneva-12B-GCv2-5m |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2025-03-12 |
| Maintainer | rubenroy |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en fr de es it pt ru zh ja |
| Quantization Type | 4bit |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <pad> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to Geneva 12B GCv2 5M
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ReWiz Nemo 12B Instruct | 1000K / 24.5 GB | 31 | 2 |
| ...omix Unleashed 12B V0.6.1 8bit | 1000K / 12.9 GB | 26 | 2 |
| ...o Instruct 12B Philosophy Math | 1000K / 24.5 GB | 32 | 1 |
| Ava 1.0 12B | 1000K / 24.5 GB | 34 | 4 |
| Poemma 12B | 1000K / 24.5 GB | 27 | 2 |
| ...t RP Noodles 12B V1.4 EXL2 8.0 | 1000K / 12.5 GB | 34 | 2 |
| Lumimaid Magnum 12B EXL2 8.0 | 1000K / 12.6 GB | 27 | 4 |
| DeepOpus 1 12B Preview | 128K / 24.5 GB | 18 | 0 |
| DeepNeo 1 12B Preview | 128K / 24.5 GB | 15 | 0 |
| ...r Nemo 12B Instruct R 21 09 24 | 1000K / 24.5 GB | 6838 | 114 |
Note: green Score (e.g. "73.2") means that the model is better than rubenroy/Geneva-12B-GCv2-5m .
Rank the Geneva 12B GCv2 5M 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? 44902 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227