LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Oumuamua 7B Instruct V2 RP by Aratako

 »  All LLMs  »  Aratako  »  Oumuamua 7B Instruct V2 RP   URL Share it on

  14   
  Autotrain compatible   Conversational Dataset:aratako/bluemoon top50... Dataset:aratako/limarp-augment... Dataset:aratako/rosebleu-1on1-... Dataset:grimulkan/limarp-augme... Dataset:omniaicreator/japanese... Dataset:omniaicreator/japanese... Dataset:sicariussicariistuff/b...   Endpoints compatible   Instruct   Ja   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Aratako/Oumuamua-7b-instruct-v2-RP 

Oumuamua 7B Instruct V2 RP Benchmarks

LLME Score: 0.17699
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Oumuamua 7B Instruct V2 RP Parameters and Internals

Model Type 
text generation, instruction following, role-play
Supported Languages 
ja (Japanese)
Training Details 
Data Sources:
Aratako/Rosebleu-1on1-Dialogues, Aratako/LimaRP-augmented-ja-karakuri, Aratako/Bluemoon_Top50MB_Sorted_Fixed_ja, grimulkan/LimaRP-augmented, SicariusSicariiStuff/Bluemoon_Top50MB_Sorted_Fixed, OmniAICreator/Japanese-Roleplay, OmniAICreator/Japanese-Roleplay-Dialogues
Methodology:
The model was fine-tuned using LoRA on role-play datasets. The training is conducted in two stages, first with lower-quality datasets and then with higher-quality datasets.
Context Length:
4096
Hardware Used:
A6000x4
Input Output 
Input Format:
Chat with role-play instructions and context.
Accepted Modalities:
text
Output Format:
Role-play responses
Performance Tips:
End each turn of assistant response with an EOS token for multi-turn dialogues.
LLM NameOumuamua 7B Instruct V2 RP
Repository 🤗https://huggingface.co/Aratako/Oumuamua-7b-instruct-v2-RP 
Model Size7b
Required VRAM14.6 GB
Updated2025-06-09
MaintainerAratako
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   4.9 GB: 2-of-3   4.8 GB: 3-of-3
Supported Languagesja
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size42800
Torch Data Typebfloat16
Oumuamua 7B Instruct V2 RP (Aratako/Oumuamua-7b-instruct-v2-RP)

Best Alternatives to Oumuamua 7B Instruct V2 RP

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB168216
SpydazWeb AI HumanAI RP512K / 14.4 GB161
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB100
...1 Summarize 64K LoRANET Merged128K / 14.4 GB200
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB2442401711
Mixtral AI CyberCoder32K / 14.3 GB00
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB15745
Note: green Score (e.g. "73.2") means that the model is better than Aratako/Oumuamua-7b-instruct-v2-RP.

Rank the Oumuamua 7B Instruct V2 RP 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! 🌟

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  

What open-source LLMs or SLMs are you in search of? 48046 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer