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

Zephyr Danube Sft Qlora by Ritvik19

 »  All LLMs  »  Ritvik19  »  Zephyr Danube Sft Qlora   URL Share it on

  6   
  Adapter   Alignment-handbook Base model:adapter:h2oai/h2o-d... Base model:h2oai/h2o-danube-1.... Dataset:huggingfaceh4/ultracha...   Finetuned   Generated from trainer   Lora   Mistral   Peft   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Ritvik19/zephyr-danube-sft-qlora 

Zephyr Danube Sft Qlora Benchmarks

ARC: 40.44 vs 96.7 (so35)-58.2%
HellaSwag: 69.4 vs 95.3 (gpt4)-27.2%
MMLU: 27 vs 88.3 (so35)-69.4%
TruthfulQA: 37.08 vs 59 (gpt4)-37.2%
WinoGrande: 64.72 vs 87.5 (gpt4)-26%
GSM8K: 2.05 vs 96.4 (so35)-97.9%
LLME Score: 0.22358
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Zephyr Danube Sft Qlora (Ritvik19/zephyr-danube-sft-qlora)

Zephyr Danube Sft Qlora Parameters and Internals

Additional Notes 
This model card has been generated automatically according to the information the Trainer had access to.
Training Details 
Data Sources:
HuggingFaceH4/ultrachat_200k
Methodology:
Fine-tuning
LLM NameZephyr Danube Sft Qlora
Repository 🤗https://huggingface.co/Ritvik19/zephyr-danube-sft-qlora 
Base Model(s)  h2oai/h2o-danube-1.8b-base   h2oai/h2o-danube-1.8b-base
Model Size1.8b
Required VRAM0 GB
Updated2025-01-04
MaintainerRitvik19
Model Files  0.0 GB   0.0 GB
Model ArchitectureAdapter
Licenseapache-2.0
Model Max Length2048
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token</s>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesdown_proj|gate_proj|q_proj|v_proj|up_proj|o_proj|k_proj
LoRA Alpha16
LoRA Dropout0.05
R Param16

Best Alternatives to Zephyr Danube Sft Qlora

Best Alternatives
Context / RAM
Downloads
Likes
Openhermes Danube Sft Qlora0K / 0 GB60
Openhermes Danube2 Sft Qlora0K / 0 GB60
Zephyr Danube2 Sft Qlora0K / 0 GB51
Qwen Qwen1.5 1.8B 17198823620K / 0 GB60
Qwen Qwen1.5 1.8B 17198810060K / 0 GB60
Qwen Qwen1.5 1.8B 17198802010K / 0 GB60
Qwen Qwen1.5 1.8B 17198986030K / 0 GB50
Qwen Qwen1.5 1.8B 17198602830K / 0 GB60
Qwen Qwen1.5 1.8B 17198615910K / 0 GB60
Qwen Qwen1.5 1.8B 17198351170K / 0 GB50
Note: green Score (e.g. "73.2") means that the model is better than Ritvik19/zephyr-danube-sft-qlora.

Rank the Zephyr Danube Sft 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? 42577 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