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

Yi 34B 200K Rawrr1 LORA DPO Experimental R3 by adamo1139

 »  All LLMs  »  adamo1139  »  Yi 34B 200K Rawrr1 LORA DPO Experimental R3   URL Share it on

  1655   
  4-bit   Autotrain compatible   Bitsandbytes   Dataset:adamo1139/rawrr v1   Dpo   Endpoints compatible   Llama   Lora   Qlora   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3 

Yi 34B 200K Rawrr1 LORA DPO Experimental R3 Benchmarks

ARC: 64.85 vs 96.7 (so35)-32.9%
HellaSwag: 84.77 vs 95.3 (gpt4)-11%
MMLU: 76 vs 88.3 (so35)-13.9%
TruthfulQA: 45.35 vs 59 (gpt4)-23.1%
WinoGrande: 83.11 vs 87.5 (gpt4)-5%
GSM8K: 61.64 vs 96.4 (so35)-36.1%
LLME Score: 0.19251
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Yi 34B 200K Rawrr1 LORA DPO Experimental R3 (adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3)

Yi 34B 200K Rawrr1 LORA DPO Experimental R3 Parameters and Internals

Model Type 
QLoRA, DPO
Additional Notes 
Trained with stronger parameters of lora_r 16, lora alpha 32 compared with previous ones with lora_r 4, lora_alpha 8.
Training Details 
Data Sources:
adamo1139/rawrr_v1
Methodology:
QLoRA DPO training with Unsloth
Context Length:
500
LLM NameYi 34B 200K Rawrr1 LORA DPO Experimental R3
Repository 🤗https://huggingface.co/adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r3 
Model Size34b
Required VRAM0.5 GB
Updated2025-02-22
Maintaineradamo1139
Model Files  0.5 GB
Model ArchitectureAutoModelForCausalLM
Licenseapache-2.0
Model Max Length200000
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesgate_proj|q_proj|o_proj|down_proj|v_proj|up_proj|k_proj
LoRA Alpha32
LoRA Dropout0
R Param16

Best Alternatives to Yi 34B 200K Rawrr1 LORA DPO Experimental R3

Best Alternatives
Context / RAM
Downloads
Likes
Yi 34B Qlora E10K / 5.8 GB18460
Yi 34B 200K AEZAKMI V2 LoRA0K / 0.5 GB41
Yi 34B AEZAKMI V1 LoRA0K / 0.5 GB41
... 34B Spicyboros 2 2 Run3 QLoRA0K / 0.5 GB71
Yi 34B Spicyboros 3.1 2 LoRA0K / 2 GB51
Limarpv3 Yi Llama 34B Lora0K / 1 GB1410
Yi 34B Spicyboros 3.1 LoRA0K / 2 GB64
Yi 34B GiftedConvo0K / 5.8 GB212

Rank the Yi 34B 200K Rawrr1 LORA DPO Experimental R3 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