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

Yi 34B 200K Aezakmi Raw Toxic 2702 4.65bpw EXL2 by adamo1139

 »  All LLMs  »  adamo1139  »  Yi 34B 200K Aezakmi Raw Toxic 2702 4.65bpw EXL2   URL Share it on

  7   

Yi 34B 200K Aezakmi Raw Toxic 2702 4.65bpw EXL2 is an open-source language model by adamo1139. Features: 34b LLM, VRAM: 20.8GB, Context: 195K, License: apache-2.0, Quantized, LLM Explorer Score: 0.12.

  Endpoints compatible   Exl2   Llama   Quantized   Region:us   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/adamo1139/yi-34b-200k-aezakmi-raw-toxic-2702-4.65bpw-exl2 

Yi 34B 200K Aezakmi Raw Toxic 2702 4.65bpw EXL2 Benchmarks

LLME Score: 0.11919
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 Raw Toxic 2702 4.65bpw EXL2 (adamo1139/yi-34b-200k-aezakmi-raw-toxic-2702-4.65bpw-exl2)
🌟 Advertise your project 🚀

Yi 34B 200K Aezakmi Raw Toxic 2702 4.65bpw EXL2 Parameters and Internals

Model Type 
chat model
Use Cases 
Areas:
chat
Primary Use Cases:
cozy free chatbot
Additional Notes 
Model has a tendency to talk about stocks a lot, resembling chat on the WSB forum.
Training Details 
Data Sources:
RAWrr v2 dataset, AEZAKMI v3-3 dataset, unalignment/toxic-dpo-v0.1, WSB dataset
Methodology:
Fine-tuned via DPO, then fine-tuned on AEZAKMI v3-3 via SFT, and DPO tuned on unalignment/toxic-dpo-v0.1.
Context Length:
200000
Training Time:
40-50 hours
Input Output 
Input Format:
ChatML
Performance Tips:
Temp setting around 0.3-0.5 works well. Temp at 1.2 is unstable.
LLM NameYi 34B 200K Aezakmi Raw Toxic 2702 4.65bpw EXL2
Repository 🤗https://huggingface.co/adamo1139/yi-34b-200k-aezakmi-raw-toxic-2702-4.65bpw-exl2 
Model Size34b
Required VRAM20.8 GB
Updated2026-05-26
Maintaineradamo1139
Model Typellama
Model Files  4.3 GB: 1-of-5   4.2 GB: 2-of-5   4.2 GB: 3-of-5   4.3 GB: 4-of-5   3.8 GB: 5-of-5
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length200000
Model Max Length200000
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typefloat16

Best Alternatives to Yi 34B 200K Aezakmi Raw Toxic 2702 4.65bpw EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...34B 200K Aezakmi Raw 1902 EXL2195K / 20.7 GB41
Yi 34B 200K MAR2024 EXL2 4bpw195K / 18 GB41
Yi 34B 200K RPMerge195K / 68.9 GB9160
...B 200K RPMerge 4.65bpw H6 EXL2195K / 10.5 GB82
Opus V1 34B 5.0bpw H6 EXL2195K / 22.3 GB92
Opus V1 34B 4.0bpw H6 EXL2195K / 18 GB51
Opus V1 34B 8.0bpw H8 EXL2195K / 34.8 GB11
34B Beta 4.0bpw H6 EXL2195K / 18.1 GB61
34B Beta 5.0bpw H6 EXL2195K / 22.3 GB31
Yi 34B 200K RPMerge EXL2 40bpw195K / 18.1 GB820
Note: green Score (e.g. "73.2") means that the model is better than adamo1139/yi-34b-200k-aezakmi-raw-toxic-2702-4.65bpw-exl2.

Rank the Yi 34B 200K Aezakmi Raw Toxic 2702 4.65bpw EXL2 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? 53999 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer