Autotrain compatible Base model:elizezen/himeyuri-v... Base model:epiculous/crimson d... Base model:gryphe/pantheon-rp-... Base model:merge:elizezen/hime... Base model:merge:epiculous/cri... Base model:merge:gryphe/panthe... Base model:merge:sao10k/mn-12b... Base model:sao10k/mn-12b-lyra-... Conversational Dataset:aixsatoshi swallow mx ... Dataset:antiven0m physical rea... Dataset:aratako/synthetic-japa... Dataset:aratako/synthetic-japa... Dataset:aratako/synthetic-jp-e... Dataset:aratako rosebleu 1on1 ... Dataset:argilla capybara prefe... Dataset:flammenai character ro... Dataset:gryphe/sonnet3.5-slimo... Dataset:jondurbi py dpo Dataset:jondurbin gutenberg dp... Dataset:jondurbin truthy dpo Dataset:kalomaze/opus instruct... Dataset:kyujinpy orca math dpo Dataset:nbeerbower gutenberg2 ... Dataset:roleplay4fun/aesir-v1.... Dataset:skunkworksai/reasoning... En Endpoints compatible Instruct Ja Merge Mergekit Mistral Nsfw Region:us Roleplay Safetensors Sharded Tensorflow Visual novel
Model Card on HF 🤗: https://huggingface.co/spow12/ChatWaifu_12B_v2.0
ChatWaifu 12B V2.0 Benchmarks
MMLU Pro: 26.53
GPQA: 3.58
MUSR: 15.83
BBH: 31.17
IFEval: 47.68 vs 88 (so35)-45.8%
MATH Lvl 5: 7.1
LLME Score: 0.28738
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)
ChatWaifu 12B V2.0 Parameters and Internals
| LLM Name | ChatWaifu 12B V2.0 |
| Repository 🤗 | https://huggingface.co/spow12/ChatWaifu_12B_v2.0 |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2025-03-20 |
| Maintainer | spow12 |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en ja |
| Model Architecture | MistralForCausalLM |
| License | cc-by-nc-4.0 |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.45.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <unk> |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives to ChatWaifu 12B V2.0
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...r Nemo 12B Instruct R 21 09 24 | 1000K / 24.5 GB | 6423 | 114 |
| SauerkrautLM Nemo 12B Instruct | 1000K / 24.5 GB | 5100 | 22 |
| MN Slush | 1000K / 24.5 GB | 401 | 22 |
| Mistral Nemo Wissenschaft 12B | 1000K / 24.5 GB | 2194 | 8 |
| EtherealAurora 12B V2 | 1000K / 24.5 GB | 183 | 3 |
| Magnum V4 12B | 1000K / 24.5 GB | 255 | 39 |
| ChatWaifu V1.4 | 1000K / 24.5 GB | 84 | 19 |
| Mistral Nemo Bophades 12B | 1000K / 24.5 GB | 109 | 9 |
| SAINEMO ReMIX | 1000K / 24.5 GB | 1930 | 33 |
| MN Anathema 12B | 1000K / 24.5 GB | 42 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than spow12/ChatWaifu_12B_v2.0 .
Rank the ChatWaifu 12B V2.0 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? 45351 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227