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 AEZAKMI V1 LoRA by adamo1139

 »  All LLMs  »  adamo1139  »  Yi 34B AEZAKMI V1 LoRA   URL Share it on

  4   
  4-bit   Autotrain compatible   Bitsandbytes   Endpoints compatible   Generated from trainer   Llama   Lora   Region:us
Model Card on HF 🤗: https://huggingface.co/adamo1139/Yi-34B-AEZAKMI-v1-LoRA 

Yi 34B AEZAKMI V1 LoRA Benchmarks

LLME Score: 0.14727
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Yi 34B AEZAKMI V1 LoRA (adamo1139/Yi-34B-AEZAKMI-v1-LoRA)

Yi 34B AEZAKMI V1 LoRA Parameters and Internals

Model Type 
chatbot
Use Cases 
Areas:
research, chatbot development
Limitations:
not suitable for math or riddles, known tendency to repeat responses in multi-turn conversations
Considerations:
Repetition penalty around 1.05 and temperature 1.2 recommended for better experience.
Additional Notes 
Adapter files for merging LoRA with base model. First attempt at training with AEZAKMI dataset.
Training Details 
Data Sources:
AEZAKMI v1 dataset
Methodology:
fine-tuning using LoRA adapters
Context Length:
4000
Training Time:
33 hours
Hardware Used:
single local RTX 3090 Ti
Input Output 
Input Format:
ChatML format
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Set repetition penalty around 1.05 and temperature 1.2 for optimal performance.
LLM NameYi 34B AEZAKMI V1 LoRA
Repository 🤗https://huggingface.co/adamo1139/Yi-34B-AEZAKMI-v1-LoRA 
Model Size34b
Required VRAM0.5 GB
Updated2025-02-22
Maintaineradamo1139
Model Files  0.5 GB
Model ArchitectureAutoModelForCausalLM
Model Max Length4096
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesk_proj|q_proj|down_proj|gate_proj|v_proj|o_proj|up_proj
LoRA Alpha32
LoRA Dropout0.05
R Param16

Best Alternatives to Yi 34B AEZAKMI V1 LoRA

Best Alternatives
Context / RAM
Downloads
Likes
...awrr1 LORA DPO Experimental R30K / 0.5 GB16551
Yi 34B Qlora E10K / 5.8 GB18460
Yi 34B 200K AEZAKMI V2 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
Note: green Score (e.g. "73.2") means that the model is better than adamo1139/Yi-34B-AEZAKMI-v1-LoRA.

Rank the Yi 34B AEZAKMI V1 LoRA 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? 43508 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