Miqu Limarp 70B by NobodyExistsOnTheInternet

 ยป  All LLMs  ยป  NobodyExistsOnTheInternet  ยป  Miqu Limarp 70B   URL Share it on

  4-bit   Adapter   Axolotl Base model:152334h/miqu-1-70b-... Base model:adapter:152334h/miq...   Bitsandbytes   Finetuned   Generated from trainer   Llama   Lora   Peft   Region:us   Safetensors

Miqu Limarp 70B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Miqu Limarp 70B (NobodyExistsOnTheInternet/miqu-limarp-70b)

Miqu Limarp 70B Parameters and Internals

Model Type 
AutoModelForCausalLM
Training Details 
Data Sources:
NobodyExistsOnTheInternet/LimaRP, Doctor-Shotgun/no-robots-sharegpt
Methodology:
The model was fine-tuned with PEFT version 0.6.0 using the Axolotl library
Context Length:
8192
Hardware Used:
multi-GPU, 8 devices
LLM NameMiqu Limarp 70B
Repository ๐Ÿค—https://huggingface.co/NobodyExistsOnTheInternet/miqu-limarp-70b 
Base Model(s)  Miqu 1 70B Sf   152334H/miqu-1-70b-sf
Model Size70b
Required VRAM4.4 GB
Updated2024-12-22
MaintainerNobodyExistsOnTheInternet
Model Files  4.4 GB   0.0 GB
Model ArchitectureAdapter
Licensemit
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|up_proj|k_proj|q_proj|down_proj|o_proj|gate_proj
LoRA Alpha128
LoRA Dropout0.05
R Param64

Best Alternatives to Miqu Limarp 70B

Best Alternatives
Context / RAM
Downloads
Likes
...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 GB50
Xwin LM 70B V0.1 LORA0K / 1.7 GB01
Euryale 1.3 L2 70B LORA0K / 1.7 GB31
Miqu 1 70B Hermes2.5 Qlora0K / 4.8 GB04
Limarp Miqu 1 70B Qlora0K / 1.7 GB54
Miqu Limarp 70B DPO Safefile0K / 38.4 GB01
Waxwing Storytelling 70B LoRA0K / 0.8 GB124
Note: green Score (e.g. "73.2") means that the model is better than NobodyExistsOnTheInternet/miqu-limarp-70b.

Rank the Miqu Limarp 70B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217