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 EXL2 4.65bpw by adamo1139

 »  All LLMs  »  adamo1139  »  Yi 34B 200K AEZAKMI V2 EXL2 4.65bpw   URL Share it on

  12   
  Autotrain compatible   Endpoints compatible   Exl2   Llama   Quantized   Region:us   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/adamo1139/Yi-34B-200K-AEZAKMI-v2-exl2-4.65bpw 

Yi 34B 200K AEZAKMI V2 EXL2 4.65bpw Benchmarks

LLME Score: 0.14996
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 EXL2 4.65bpw (adamo1139/Yi-34B-200K-AEZAKMI-v2-exl2-4.65bpw)

Yi 34B 200K AEZAKMI V2 EXL2 4.65bpw Parameters and Internals

Model Type 
Chatbot, Assistant
Use Cases 
Primary Use Cases:
Free cozy chatbot
Limitations:
Not intended for math, riddles or complex problem solving, Repetition issues at low repetition penalty values, Contaminated base model with refusal artifacts
Considerations:
Repetition penalty suggested around 1.05, temperature 1.2 recommended
Additional Notes 
Adaptation of the Yi-34B model to reduce refusal behavior and create a more 'cozy' chatbot.
Training Details 
Data Sources:
AEZAKMI v2 dataset
Methodology:
Fine-tuning, LoRA and qlora adapter used, flash attention enabled
Context Length:
24000
Training Time:
25 hours
Hardware Used:
Single local RTX 3090 Ti
Model Architecture:
Modified config with max_positional_embeddings set to 4096
Input Output 
Input Format:
ChatML format
Accepted Modalities:
Text
Output Format:
Chatbot response
Performance Tips:
Modify prompts to help with uncensored performance
LLM NameYi 34B 200K AEZAKMI V2 EXL2 4.65bpw
Repository 🤗https://huggingface.co/adamo1139/Yi-34B-200K-AEZAKMI-v2-exl2-4.65bpw 
Model Size34b
Required VRAM20.8 GB
Updated2025-02-22
Maintaineradamo1139
Model Typellama
Model Files  4.3 GB: 1-of-5   4.3 GB: 2-of-5   4.3 GB: 3-of-5   4.3 GB: 4-of-5   3.6 GB: 5-of-5
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length200000
Model Max Length200000
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to Yi 34B 200K AEZAKMI V2 EXL2 4.65bpw

Best Alternatives
Context / RAM
Downloads
Likes
...34B 200K Aezakmi Raw 1902 EXL2195K / 20.7 GB61
Yi 34B 200K RPMerge195K / 68.9 GB13860
Yi 34B 200K MAR2024 EXL2 4bpw195K / 18 GB41
...mi Raw Toxic 2702 4.65bpw EXL2195K / 20.8 GB82
...B 200K RPMerge 4.65bpw H6 EXL2195K / 10.5 GB101
Opus V1 34B 5.0bpw H6 EXL2195K / 22.3 GB52
Opus V1 34B 8.0bpw H8 EXL2195K / 34.8 GB81
Opus V1 34B 4.0bpw H6 EXL2195K / 18 GB61
Yi 34B 200K RPMerge EXL2 40bpw195K / 18.1 GB3020
34B Beta 5.0bpw H6 EXL2195K / 22.3 GB71
Note: green Score (e.g. "73.2") means that the model is better than adamo1139/Yi-34B-200K-AEZAKMI-v2-exl2-4.65bpw.

Rank the Yi 34B 200K AEZAKMI V2 EXL2 4.65bpw 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