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

Ypotryll 22B Epoch2 Qlora by chargoddard

 »  All LLMs  »  chargoddard  »  Ypotryll 22B Epoch2 Qlora   URL Share it on

  5   
  Merged Model   Adapter Base model:adapter:chargoddard... Base model:chargoddard/llama2-...   Dataset:ehartford/dolphin Dataset:ehartford/wizard vicun... Dataset:ehartford/wizardlm evo... Dataset:jondurbin/airoboros-gp... Dataset:openai/summarize from ...   Finetuned   Instruct   Llama   Lora   Peft   Region:us
Model Card on HF 🤗: https://huggingface.co/chargoddard/ypotryll-22b-epoch2-qlora 

Ypotryll 22B Epoch2 Qlora Benchmarks

ARC: 59.22 vs 96.7 (so35)-38.8%
HellaSwag: 80.66 vs 95.3 (gpt4)-15.4%
MMLU: 54.52 vs 88.3 (so35)-38.3%
TruthfulQA: 40.42 vs 59 (gpt4)-31.5%
WinoGrande: 76.32 vs 87.5 (gpt4)-12.8%
GSM8K: 5.38 vs 96.4 (so35)-94.4%
LLME Score: 0.13034
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ypotryll 22B Epoch2 Qlora (chargoddard/ypotryll-22b-epoch2-qlora)
🌟 Advertise your project 🚀

Ypotryll 22B Epoch2 Qlora Parameters and Internals

Additional Notes 
A little bit dumb, but good for creative scenarios. Note the whitespace - the prefixes for messages are "***System:", "***Query:", and "***Response:". This is important as "***" and " ***" are two entirely different tokens.
Training Details 
Data Sources:
jondurbin/airoboros-gpt4-1.4.1, ehartford/wizard_vicuna_70k_unfiltered, ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split, openai/summarize_from_feedback, ehartford/dolphin
Methodology:
trained for an additional epoch
Input Output 
Input Format:
***System:[system instructions] ***Query:[user prompt]
Output Format:
***Response:[model response]
LLM NameYpotryll 22B Epoch2 Qlora
Repository 🤗https://huggingface.co/chargoddard/ypotryll-22b-epoch2-qlora 
Base Model(s)  Llama2 22B Blocktriangular   chargoddard/llama2-22b-blocktriangular
Merged ModelYes
Model Size22b
Required VRAM2.6 GB
Updated2025-07-16
Maintainerchargoddard
Instruction-BasedYes
Model Files  2.6 GB
Model ArchitectureAdapter
Is Biasednone
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|gate_proj|down_proj|k_proj|q_proj|o_proj|up_proj
LoRA Alpha16
LoRA Dropout0.001
R Param128

Best Alternatives to Ypotryll 22B Epoch2 Qlora

Best Alternatives
Context / RAM
Downloads
Likes
MS 22B RP Ink Adpt0K / 0.4 GB50
Ypotryll 22B Qlora0K / 2.6 GB01
Note: green Score (e.g. "73.2") means that the model is better than chargoddard/ypotryll-22b-epoch2-qlora.

Rank the Ypotryll 22B Epoch2 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? 51022 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