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 by adamo1139

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

  1992   
  Autotrain compatible   Endpoints compatible   Finetuned   Llama   Region:us   Safetensors   Sharded   Tensorflow   Yi
Model Card on HF 🤗: https://huggingface.co/adamo1139/Yi-34B-AEZAKMI-v1 

Yi 34B AEZAKMI V1 Benchmarks

ARC: 64.33 vs 96.7 (so35)-33.5%
HellaSwag: 84.31 vs 95.3 (gpt4)-11.5%
MMLU: 73.91 vs 88.3 (so35)-16.3%
TruthfulQA: 55.73 vs 59 (gpt4)-5.5%
WinoGrande: 80.82 vs 87.5 (gpt4)-7.6%
GSM8K: 52.92 vs 96.4 (so35)-45.1%
LLME Score: 0.18139
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 (adamo1139/Yi-34B-AEZAKMI-v1)

Yi 34B AEZAKMI V1 Parameters and Internals

Model Type 
llm
Use Cases 
Areas:
research, personal use
Limitations:
Doesn't handle long contexts above 6k-8k well, Issues with handling long system messages
Additional Notes 
The model is like airoboros but with less gptslop, no refusals, and less typical language used by RLHFed OpenAI models.
Training Details 
Data Sources:
AEZAKMI v1 dataset
Methodology:
fine-tuning
Context Length:
4000
Training Time:
33 hours
Hardware Used:
single local RTX 3090 Ti
Input Output 
Input Format:
standard chatml
Performance Tips:
Set repetition penalty to 1.05 and temperature to 1.2 for optimal performance. "A chat with uncensored assistant" system prompt is recommended.
LLM NameYi 34B AEZAKMI V1
Repository 🤗https://huggingface.co/adamo1139/Yi-34B-AEZAKMI-v1 
Model Size34b
Required VRAM69.2 GB
Updated2025-02-22
Maintaineradamo1139
Model Typellama
Model Files  4.8 GB: 1-of-15   4.8 GB: 2-of-15   5.0 GB: 3-of-15   4.8 GB: 4-of-15   4.8 GB: 5-of-15   5.0 GB: 6-of-15   4.8 GB: 7-of-15   4.8 GB: 8-of-15   5.0 GB: 9-of-15   4.8 GB: 10-of-15   4.8 GB: 11-of-15   5.0 GB: 12-of-15   4.8 GB: 13-of-15   4.8 GB: 14-of-15   1.2 GB: 15-of-15
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.35.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typefloat16

Best Alternatives to Yi 34B AEZAKMI V1

Best Alternatives
Context / RAM
Downloads
Likes
Casual Magnum 34B195K / 68.8 GB141
34B Beta195K / 69.2 GB372963
Bagel 34B V0.2195K / 68.7 GB679040
Bagel Hermes 34B Slerp195K / 68.9 GB38941
Smaug 34B V0.1195K / 69.2 GB367260
Yi 34B 200K195K / 68.9 GB6015318
Yi 34B 200K AEZAKMI V2195K / 69.2 GB200712
Faro Yi 34B195K / 69.2 GB36126
Smaug 34B V0.1 ExPO195K / 69.2 GB19720
Mergekit Slerp Anaazls195K / 69.2 GB90
Note: green Score (e.g. "73.2") means that the model is better than adamo1139/Yi-34B-AEZAKMI-v1.

Rank the Yi 34B AEZAKMI V1 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