Loki V5.2 is an open-source language model by MrRobotoAI. Features: 7.2b LLM, VRAM: 14.5GB, Context: 32K, MoE, Instruction-Based, Merged, LLM Explorer Score: 0.15.
Merged Model Arxiv:2403.19522 Autotrain compatible Base model:azazelle/l3-daybrea... Base model:azazelle/llama-3-8b... Base model:azazelle/llama-3-in... Base model:azazelle/llama-3-li... Base model:azazelle/llama-3-lo... Base model:azazelle/nimue-8b Base model:azazelle/smarts lla... Base model:blackroot/llama-3-l... Base model:mrrobotoai/loki-v5.... Base model:nicce/story-mixtral... Base model:omnicromsbrain/eros... Base model:resplendentai/aura ... Base model:resplendentai/bluem... Base model:resplendentai/llama... Base model:resplendentai/llama... Base model:resplendentai/luna ... Base model:resplendentai/nowar... Base model:resplendentai/theor... Base model:vincentyandex/lora ... Conversational Endpoints compatible Instruct Lora Mistral Moe Region:us Safetensors Sharded Tensorflow
Loki V5.2 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Loki V5.2 Parameters and Internals
LLM Name Loki V5.2 Repository ๐ค https://huggingface.co/MrRobotoAI/Loki-v5.2 Base Model(s) Eros Scribe 7B MrRobotoAI/Loki-v5.1 Story Mixtral 8x7b Lora MrRobotoAI/Loki-v5.1 BlueMoon Llama3 MrRobotoAI/Loki-v5.1 Luna Llama3 MrRobotoAI/Loki-v5.1 vincentyandex/lora_llama3_chunked_novel_bs128 MrRobotoAI/Loki-v5.1 Llama 3 Instruct LiPPA LoRA 8B MrRobotoAI/Loki-v5.1 Theory Of Mind Llama3 MrRobotoAI/Loki-v5.1 Aura Llama3 MrRobotoAI/Loki-v5.1 Llama3 RP ORPO LoRA MrRobotoAI/Loki-v5.1 Llama 3 LongStory LORA MrRobotoAI/Loki-v5.1 L3 Daybreak 8B Lora MrRobotoAI/Loki-v5.1 Azazelle/Llama-3-8B-Abomination-LORA MrRobotoAI/Loki-v5.1 ...lama 3 LimaRP Instruct LoRA 8B MrRobotoAI/Loki-v5.1 Azazelle/Llama-3-LongStory-LORA MrRobotoAI/Loki-v5.1 Llama3 Aesir Preview LoRA 128 MrRobotoAI/Loki-v5.1 Azazelle/Smarts_Llama3 MrRobotoAI/Loki-v5.1 NoWarning Llama3 MrRobotoAI/Loki-v5.1 Nimue 8B OmnicromsBrain/Eros_Scribe-7b MrRobotoAI/Loki-v5.1 nicce/story-mixtral-8x7b-lora MrRobotoAI/Loki-v5.1 ResplendentAI/BlueMoon_Llama3 MrRobotoAI/Loki-v5.1 ResplendentAI/Luna_Llama3 MrRobotoAI/Loki-v5.1 vincentyandex/lora_llama3_chunked_novel_bs128 MrRobotoAI/Loki-v5.1 Azazelle/Llama-3-Instruct-LiPPA-LoRA-8B MrRobotoAI/Loki-v5.1 ResplendentAI/Theory_of_Mind_Llama3 MrRobotoAI/Loki-v5.1 ResplendentAI/Aura_Llama3 MrRobotoAI/Loki-v5.1 ResplendentAI/Llama3_RP_ORPO_LoRA MrRobotoAI/Loki-v5.1 Blackroot/Llama-3-LongStory-LORA MrRobotoAI/Loki-v5.1 Azazelle/L3-Daybreak-8b-lora MrRobotoAI/Loki-v5.1 Azazelle/Llama-3-8B-Abomination-LORA MrRobotoAI/Loki-v5.1 Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B MrRobotoAI/Loki-v5.1 Azazelle/Llama-3-LongStory-LORA MrRobotoAI/Loki-v5.1 ResplendentAI/Llama3_Aesir_Preview_LoRA_128 MrRobotoAI/Loki-v5.1 Azazelle/Smarts_Llama3 MrRobotoAI/Loki-v5.1 ResplendentAI/NoWarning_Llama3 MrRobotoAI/Loki-v5.1 Azazelle/Nimue-8B Merged Model Yes Model Size 7.2b Required VRAM 14.5 GB Updated 2024-11-11 Maintainer MrRobotoAI Model Type mistral Instruction-Based Yes Model Files 4.9 GB: 1-of-3 4.9 GB: 2-of-3 4.7 GB: 3-of-3 Model Architecture MistralForCausalLM Context Length 32768 Model Max Length 32768 Transformers Version 4.44.1 Tokenizer Class LlamaTokenizer Padding Token <unk> Vocabulary Size 32000 LoRA Model Yes Torch Data Type float16
Best Alternatives to Loki V5.2
Note: green Score (e.g. "73.2 ") means that the model is better than MrRobotoAI/Loki-v5.2 .
Expand
Rank the Loki V5.2 Capabilities
๐ 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! ๐
Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation
Expand
Check out
Ag3ntum โ our secure, self-hosted AI agent for server management.
Release v20260328a