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

Barely Regal 10.7B DPO by sydonayrex

 »  All LLMs  »  sydonayrex  »  Barely Regal 10.7B DPO   URL Share it on

  0   
  Autotrain compatible   Axolotl Base model:sydonayrex/barely-r...   Conversational Dataset:argilla/ultrafeedback-...   En   Endpoints compatible   License:apache-2.0   Lora   Mistral   Region:us   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/sydonayrex/Barely-Regal-10.7B-DPO 
Barely Regal 10.7B DPO (sydonayrex/Barely-Regal-10.7B-DPO)

Barely Regal 10.7B DPO Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model performs better with task arithmetic layer merging compared to passthrough merging.
Training Details 
Data Sources:
argilla/ultrafeedback-binarized-preferences-cleaned, Axolotl, Unsloth
Methodology:
Continuation training using Axolotl for DPO, fine-tuned with SFT and task arithmetic for layer merging
Model Architecture:
Supersized using task arithmetic, layer merging and fine-tuning
LLM NameBarely Regal 10.7B DPO
Repository 🤗https://huggingface.co/sydonayrex/Barely-Regal-10.7B-DPO 
Base Model(s)  sydonayrex/Barely-Regal-10.7B   sydonayrex/Barely-Regal-10.7B
Model Size10.7b
Required VRAM21.5 GB
Updated2024-07-04
Maintainersydonayrex
Model Files  0.3 GB   5.0 GB: 1-of-5   5.0 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   1.7 GB: 5-of-5
Supported Languagesen
Model ArchitectureAutoModelForCausalLM
Licenseapache-2.0
Model Max Length32768
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token[control_768]
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesgate_proj|v_proj|k_proj|down_proj|up_proj|q_proj|o_proj
LoRA Alpha16
LoRA Dropout0.05
R Param32

Best Alternatives to Barely Regal 10.7B DPO

Best Alternatives
Context / RAM
Downloads
Likes
Peft Solar 10.7B V1.00K / 21.4 GB760
Note: green Score (e.g. "73.2") means that the model is better than sydonayrex/Barely-Regal-10.7B-DPO.

Rank the Barely Regal 10.7B DPO 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? 43470 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 v20241227
  Support LLM Explorer