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

Limarp Miqu 1 70B Qlora by Doctor-Shotgun

 »  All LLMs  »  Doctor-Shotgun  »  Limarp Miqu 1 70B Qlora   URL Share it on

  2   
  4-bit   Adapter   Bitsandbytes   Dataset:lemonilia/limarp   En   Finetuned   Generated from trainer   Llama   Llama 2   Lora   Peft   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Doctor-Shotgun/limarp-miqu-1-70b-qlora 

Limarp Miqu 1 70B Qlora Benchmarks

LLME Score: 0.1321
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Limarp Miqu 1 70B Qlora (Doctor-Shotgun/limarp-miqu-1-70b-qlora)
🌟 Advertise your project 🚀

Limarp Miqu 1 70B Qlora Parameters and Internals

Model Type 
LlamaForCausalLM
Use Cases 
Areas:
Roleplay, Chatbot
Applications:
Roleplaying scenarios, Character interactions
Primary Use Cases:
Roleplay chatbots
Limitations:
Biases similar to niche roleplaying
Additional Notes 
This isn't the most polished version. It's released "as-is" for experimentation, and results may vary.
Supported Languages 
en (English)
Training Details 
Data Sources:
lemonilia/LimaRP, train-all-max-alpaca-llama.jsonl
Methodology:
Completion
Context Length:
16384
Model Architecture:
Llama For Causal Language Model
Input Output 
Input Format:
Alpaca instruction format of LimaRP v3
Accepted Modalities:
text
Output Format:
Character responses in dialogue format
Performance Tips:
Optimize by selecting appropriate response lengths as described.
LLM NameLimarp Miqu 1 70B Qlora
Repository 🤗https://huggingface.co/Doctor-Shotgun/limarp-miqu-1-70b-qlora 
Model Size70b
Required VRAM1.7 GB
Updated2025-10-21
MaintainerDoctor-Shotgun
Model Files  1.7 GB
Supported Languagesen
Model ArchitectureAdapter
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesup_proj|v_proj|down_proj|k_proj|gate_proj|q_proj|o_proj
LoRA Alpha16
LoRA Dropout0.05
R Param32

Best Alternatives to Limarp Miqu 1 70B Qlora

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.1 70B Abliterated Lora0K / 1.7 GB267573
...aiga Llama3 70b Sft M1 D5 Lora0K / 5.9 GB01
Llama 3 70B Instruct Spider0K / 141.9 GB60
Airoboros 70B 3.3 Peft0K / 0.4 GB02
Llama3v10K / 0.1 GB60
Xwin LM 70B V0.1 LORA0K / 1.7 GB41
Euryale 1.3 L2 70B LORA0K / 1.7 GB41
Miqu 1 70B Hermes2.5 Qlora0K / 4.8 GB74
Miqu Limarp 70B DPO Safefile0K / 38.4 GB31
Miqu Limarp 70B0K / 4.4 GB62
Note: green Score (e.g. "73.2") means that the model is better than Doctor-Shotgun/limarp-miqu-1-70b-qlora.

Rank the Limarp Miqu 1 70B Qlora 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? 51567 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