Arxiv:2403.07691 Base model:finetune:vikhrmodel... Base model:vikhrmodels/vikhr-n... Dataset:40umov/dostoevsky Instruct Mistral Region:us Ru Safetensors Sharded Tensorflow Unsloth
Model Card on HF 🤗: https://huggingface.co/IlyaGusev/vikhr_nemo_orpo_dostoevsky_12b
Vikhr Nemo Orpo Dostoevsky 12b Benchmarks
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)
Vikhr Nemo Orpo Dostoevsky 12B Parameters and Internals
| LLM Name | Vikhr Nemo Orpo Dostoevsky 12b |
| Repository 🤗 | https://huggingface.co/IlyaGusev/vikhr_nemo_orpo_dostoevsky_12b |
| Base Model(s) | |
| Model Size | 12b |
| Required VRAM | 24.5 GB |
| Updated | 2025-03-12 |
| Maintainer | IlyaGusev |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | ru |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 1024000 |
| Model Max Length | 1024000 |
| Transformers Version | 4.45.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <s> |
| Vocabulary Size | 131074 |
| Torch Data Type | bfloat16 |
Best Alternatives to Vikhr Nemo Orpo Dostoevsky 12B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...r Nemo 12B Instruct R 21 09 24 | 1000K / 24.5 GB | 6838 | 114 |
| SauerkrautLM Nemo 12B Instruct | 1000K / 24.5 GB | 5263 | 22 |
| MN Slush | 1000K / 24.5 GB | 252 | 21 |
| Mistral Nemo Wissenschaft 12B | 1000K / 24.5 GB | 2359 | 8 |
| Magnum V4 12B | 1000K / 24.5 GB | 489 | 39 |
| ChatWaifu V1.4 | 1000K / 24.5 GB | 69 | 19 |
| ChatWaifu 12B V2.0 | 1000K / 24.5 GB | 62 | 20 |
| Mistral Nemo Bophades 12B | 1000K / 24.5 GB | 246 | 9 |
| ...tral Nemo Gutenberg Doppel 12B | 1000K / 24.5 GB | 39 | 5 |
| Astra V1 12B | 1000K / 24.5 GB | 125 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than IlyaGusev/vikhr_nemo_orpo_dostoevsky_12b .
Rank the Vikhr Nemo Orpo Dostoevsky 12B 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? 44887 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227