| license: mit | |
| datasets: | |
| - Vikhrmodels/GrandMaster-PRO-MAX | |
| language: | |
| - en | |
| - ru | |
| tags: | |
| - mistral | |
| - chat | |
| - conversational | |
| - transformers | |
| inference: | |
| parameters: | |
| temperature: 0 | |
| pipeline_tag: text-generation | |
| base_model: | |
| - mistralai/Mistral-Small-24B-Instruct-2501 | |
| - ZeroAgency/Zero-Mistral-Small-24B-Instruct-2501 | |
| library_name: vllm | |
| # Zero-Mistral-Small-24B-Instruct-2501 Q8_0 GGUF version | |
| Zero-Mistral-Small is an improved version of [mistralai/Mistral-Small-24B-Instruct-2501](https://huggingface.co./mistralai/Mistral-Small-24B-Instruct-2501), primarily adapted for Russian and English languages. | |
| The training involved SFT stage on [GrandMaster-PRO-MAX](https://huggingface.co./datasets/Vikhrmodels/GrandMaster-PRO-MAX) dataset. | |
| ## 📚 Model versions | |
| - [Merged 16-bit](https://huggingface.co./ZeroAgency/Zero-Mistral-Small-24B-Instruct-2501) - original 16bit merged version. | |
| - [LoRa adapter](https://huggingface.co./ZeroAgency/Zero-Mistral-Small-24B-Instruct-2501-lora) for mistralai/Mistral-Small-24B-Instruct-2501 | |
| - [F16 GGUF](https://huggingface.co./ZeroAgency/Zero-Mistral-Small-24B-Instruct-2501-F16) | |
| - [BF16 GGUF](https://huggingface.co./ZeroAgency/Zero-Mistral-Small-24B-Instruct-2501-BF16) | |
| - [Q8_0 GGUF](https://huggingface.co./ZeroAgency/Zero-Mistral-Small-24B-Instruct-2501-Q8_0) | |
| - [Q4_K_M GGUF](https://huggingface.co./ZeroAgency/Zero-Mistral-Small-24B-Instruct-2501-Q4_K_M) |