Llama 3 8B Abomination LORA by Blackroot

 ยป  All LLMs  ยป  Blackroot  ยป  Llama 3 8B Abomination LORA   URL Share it on

  Adapter   Finetuned   Lora   Region:us   Safetensors

Llama 3 8B Abomination LORA Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 8B Abomination LORA (Blackroot/Llama-3-8B-Abomination-LORA)

Llama 3 8B Abomination LORA Parameters and Internals

Model Type 
RP, storytelling
Additional Notes 
This method attempts to bring some of the intrigue and style of the base model back into the instruct model.
Training Details 
Data Sources:
semi-structured pretraining data, structured story-instruct data
Methodology:
Trained in four stages with specific tuning phases
Context Length:
8192
LLM NameLlama 3 8B Abomination LORA
Repository ๐Ÿค—https://huggingface.co/Blackroot/Llama-3-8B-Abomination-LORA 
Model Size8b
Required VRAM0.7 GB
Updated2024-12-21
MaintainerBlackroot
Model Files  0.7 GB
Model ArchitectureAdapter
Is Biasednone
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesk_proj|v_proj|down_proj|q_proj|o_proj|up_proj|gate_proj
LoRA Alpha32
LoRA Dropout0.05
R Param64

Best Alternatives to Llama 3 8B Abomination LORA

Best Alternatives
Context / RAM
Downloads
Likes
... 3 8B Instruct Bvr Finetune V38K / 16.1 GB50
Flippa V60K / 0 GB111
Llama 3 Korean 8B R V 0.10K / 0 GB90
...ultiModal Llama 3 8B Finetuned0K / 0 GB201
...lama 3 1 8B Instruct Orca ORPO0K / 0.1 GB1312
FatDPOv2LoRA0K / 0.8 GB01
...ight AGI Llama3.1 8B UC200k V20K / 0.2 GB882
Adapter Test0K / 0.1 GB60
Llama3 C1 Full0K / 0.2 GB130
Vortex20K / 4.4 GB80
Note: green Score (e.g. "73.2") means that the model is better than Blackroot/Llama-3-8B-Abomination-LORA.

Rank the Llama 3 8B Abomination LORA 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? 40013 in total.

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