Base model:finetune:mistralai/... Base model:mistralai/mistral-n... Dataset:pocketdoc/dans-memoryc... En Instruct Mistral Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Dans-DiscountModels/Dans-Instruct-CoreCurriculum-12b-ChatML
Dans Instruct CoreCurriculum 12B ChatML Benchmarks
MMLU Pro: 20.06
GPQA: 4.03
MUSR: 5.71
BBH: 26.05
IFEval: 21.11 vs 88 (so35)-76%
MATH Lvl 5: 0.53
LLME Score: 0.25441
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)
Dans Instruct CoreCurriculum 12B ChatML Parameters and Internals
| LLM Name | Dans Instruct CoreCurriculum 12B ChatML |
| Repository 🤗 | https://huggingface.co/Dans-DiscountModels/Dans-Instruct-CoreCurriculum-12b-ChatML |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2025-01-16 |
| Maintainer | Dans-DiscountModels |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.44.0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <pad> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to Dans Instruct CoreCurriculum 12B ChatML
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...r Nemo 12B Instruct R 21 09 24 | 1000K / 24.5 GB | 9207 | 99 |
| SauerkrautLM Nemo 12B Instruct | 1000K / 24.5 GB | 5712 | 22 |
| Magnum V4 12B | 1000K / 24.5 GB | 695 | 37 |
| Mistral Nemo Wissenschaft 12B | 1000K / 24.5 GB | 4751 | 6 |
| MN Slush | 1000K / 24.5 GB | 181 | 14 |
| ChatWaifu 12B V2.0 | 1000K / 24.5 GB | 110 | 18 |
| ChatWaifu V1.4 | 1000K / 24.5 GB | 43 | 16 |
| Mistral Nemo Bophades 12B | 1000K / 24.5 GB | 85 | 8 |
| ...tral Nemo Gutenberg Doppel 12B | 1000K / 24.5 GB | 62 | 4 |
| ...stral Nemo Gutenberg2 12B Test | 1000K / 24.5 GB | 16 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Dans-DiscountModels/Dans-Instruct-CoreCurriculum-12b-ChatML .
Rank the Dans Instruct CoreCurriculum 12B ChatML 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? 41470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227