Autotrain compatible Base model:finetune:nbeerbower... Base model:nbeerbower/mahou-1.... Conversational Dataset:huggingfacetb/smoltalk Endpoints compatible Mistral Model-index Region:us Safetensors Sft Sharded Tensorflow Trl
Model Card on HF 🤗: https://huggingface.co/nbeerbower/SmolNemo-12B-FFT-experimental
SmolNemo 12B FFT Experimental Benchmarks
MMLU Pro: 2.41
GPQA: 1.34
MUSR: 5.92
BBH: 6.54
IFEval: 33.48 vs 88 (so35)-62%
MATH Lvl 5: 1.28
LLME Score: 0.23991
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)
SmolNemo 12B FFT Experimental Parameters and Internals
| LLM Name | SmolNemo 12B FFT Experimental |
| Repository 🤗 | https://huggingface.co/nbeerbower/SmolNemo-12B-FFT-experimental |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2025-04-27 |
| Maintainer | nbeerbower |
| Model Type | mistral |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.45.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|im_end|> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to SmolNemo 12B FFT Experimental
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Captain Eris Violet V0.420 12B | 1000K / 24.5 GB | 482281 | 41 |
| Dans SakuraKaze V1.0.0 12B | 1000K / 24.5 GB | 133 | 19 |
| ...r Nemo 12B Instruct R 21 09 24 | 1000K / 24.5 GB | 3985 | 118 |
| Violet Magcap 12B | 1000K / 24.5 GB | 151 | 16 |
| Captain Eris BMO Violent 12B | 1000K / 24.5 GB | 305 | 2 |
| ...s PersonalityEngine V1.1.0 12B | 1000K / 24.5 GB | 454 | 39 |
| MN 12B Mag Mell R1 | 1000K / 24.5 GB | 3035 | 159 |
| ...n Eris BMO Violent GRPO V0.420 | 1000K / 24.5 GB | 92 | 3 |
| Dolphin 2.9.3 Mistral Nemo 12B | 1000K / 24.5 GB | 4724 | 99 |
| Nullsworn 12B LINEAR | 1000K / 24.5 GB | 41 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than nbeerbower/SmolNemo-12B-FFT-experimental .
Rank the SmolNemo 12B FFT Experimental 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? 46761 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227