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 AEZAKMI V2 by adamo1139

 »  All LLMs  »  adamo1139  »  Yi 34B 200K AEZAKMI V2   URL Share it on

  181   
  Autotrain compatible   Conversational   Dataset:adamo1139/aezakmi v2   Endpoints compatible   Finetuned   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow   Yi
Model Card on HF 🤗: https://huggingface.co/adamo1139/Yi-34B-200K-AEZAKMI-v2 

Yi 34B 200K AEZAKMI V2 Benchmarks

MMLU Pro: 39.03
GPQA: 10.96
MUSR: 6.48
BBH: 35.28
IFEval: 45.55 vs 88 (so35)-48.2%
ARC: 67.92 vs 96.7 (so35)-29.8%
HellaSwag: 85.61 vs 95.3 (gpt4)-10.2%
MMLU: 75.22 vs 88.3 (so35)-14.8%
TruthfulQA: 56.74 vs 59 (gpt4)-3.8%
WinoGrande: 81.61 vs 87.5 (gpt4)-6.7%
GSM8K: 58.91 vs 96.4 (so35)-38.9%
MATH Lvl 5: 5.66
LLME Score: 0.22381
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 AEZAKMI V2 (adamo1139/Yi-34B-200K-AEZAKMI-v2)

Yi 34B 200K AEZAKMI V2 Parameters and Internals

Model Type 
text-generation
Use Cases 
Limitations:
Don't expect it to be good at math, riddles or be crazy smart.
Additional Notes 
Fine-tuned to avoid using typical language from RLHFed models such as 'It's important to remember.'
Training Details 
Data Sources:
AEZAKMI_v2
Methodology:
Fine-tuning
Context Length:
24000
Training Time:
25 hours
Hardware Used:
single local RTX 3090 Ti
Input Output 
Input Format:
ChatML format
Performance Tips:
Set repetition penalty to ~1.05; temperature 1.2 recommended.
LLM NameYi 34B 200K AEZAKMI V2
Repository 🤗https://huggingface.co/adamo1139/Yi-34B-200K-AEZAKMI-v2 
Model Size34b
Required VRAM69.2 GB
Updated2025-04-28
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 Length200000
Model Max Length200000
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typebfloat16

Quantized Models of the Yi 34B 200K AEZAKMI V2

Model
Likes
Downloads
VRAM
Yi 34B 200K AEZAKMI V2 GGUF3111214 GB
Yi 34B 200K AEZAKMI V2 GPTQ2418 GB
Yi 34B 200K AEZAKMI V2 AWQ2219 GB

Best Alternatives to Yi 34B 200K AEZAKMI V2

Best Alternatives
Context / RAM
Downloads
Likes
Yi 34B 200K195K / 68.9 GB40324317
Casual Magnum 34B195K / 68.8 GB21
Bagel Hermes 34B Slerp195K / 68.9 GB3501
34B Beta195K / 69.2 GB13763
Bagel 34B V0.2195K / 68.7 GB49341
Smaug 34B V0.1195K / 69.2 GB15060
Mergekit Slerp Anaazls195K / 69.2 GB60
Yi 34B 200K HESOYAM 0905195K / 69.2 GB60
Merged RP Stew V2 34B195K / 68.9 GB18649
Faro Yi 34B195K / 69.2 GB1936
Note: green Score (e.g. "73.2") means that the model is better than adamo1139/Yi-34B-200K-AEZAKMI-v2.

Rank the Yi 34B 200K AEZAKMI V2 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? 46763 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