Arxiv:2306.01708 Arxiv:2402.12354 Arxiv:2403.00946 Arxiv:2410.21228 Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mistral-n... Conversational Dataset:anthracite-org/c2 logs... Dataset:anthracite-org/kalo-op... Dataset:anthracite-org/kalo-op... Dataset:anthracite-org/nopm cl... Dataset:crestf411/limarp-ds Dataset:gryphe/sonnet3.5-charc... Endpoints compatible Instruct Mergekit Mistral Not-for-all-audiences Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/crestf411/MN-Slush
MN Slush Benchmarks
MMLU Pro: 27.87
GPQA: 9.84
MUSR: 8.49
BBH: 33.16
IFEval: 40.77 vs 88 (so35)-53.7%
MATH Lvl 5: 12.24
LLME Score: 0.32656
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)
MN Slush Parameters and Internals
| LLM Name | MN Slush |
| Repository 🤗 | https://huggingface.co/crestf411/MN-Slush |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2025-02-05 |
| Maintainer | crestf411 |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | MistralForCausalLM |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to MN Slush
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...r Nemo 12B Instruct R 21 09 24 | 1000K / 24.5 GB | 8449 | 106 |
| SauerkrautLM Nemo 12B Instruct | 1000K / 24.5 GB | 19527 | 22 |
| Mistral Nemo Wissenschaft 12B | 1000K / 24.5 GB | 5216 | 7 |
| Magnum V4 12B | 1000K / 24.5 GB | 844 | 39 |
| ChatWaifu V1.4 | 1000K / 24.5 GB | 97 | 19 |
| ChatWaifu 12B V2.0 | 1000K / 24.5 GB | 57 | 18 |
| ...tral Nemo Gutenberg Doppel 12B | 1000K / 24.5 GB | 61 | 5 |
| GodSlayer 12B ABYSS | 1000K / 24.5 GB | 84 | 5 |
| SAINEMO ReMIX | 1000K / 24.5 GB | 994 | 24 |
| Mistral Nemo Bophades 12B | 1000K / 24.5 GB | 48 | 8 |
Note: green Score (e.g. "73.2") means that the model is better than crestf411/MN-Slush .
Rank the MN Slush 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227