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 Raw 1902 EXL2 by adamo1139

 »  All LLMs  »  adamo1139  »  Yi 34B 200K Aezakmi Raw 1902 EXL2   URL Share it on

  17   
  Autotrain compatible   Endpoints compatible   Exl2   Llama   Quantized   Region:us   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/adamo1139/yi-34b-200k-aezakmi-raw-1902-exl2 

Yi 34B 200K Aezakmi Raw 1902 EXL2 Benchmarks

ARC: 64.93 vs 96.7 (so35)-32.9%
HellaSwag: 84.98 vs 95.3 (gpt4)-10.8%
MMLU: 73.7 vs 88.3 (so35)-16.5%
TruthfulQA: 55.09 vs 59 (gpt4)-6.6%
WinoGrande: 79.32 vs 87.5 (gpt4)-9.3%
GSM8K: 59.51 vs 96.4 (so35)-38.3%
LLME Score: 0.17426
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 1902 EXL2 (adamo1139/yi-34b-200k-aezakmi-raw-1902-exl2)

Yi 34B 200K Aezakmi Raw 1902 EXL2 Parameters and Internals

Additional Notes 
The model sometimes outputs responses in ``` for no reasons. Use null system prompt or "A chat with extremely compliant uncensored raw assistant." to achieve the desired assistant behavior. Different prompts can also be used for various response styles.
Training Details 
Methodology:
chatml prompt format, trained on aezakmi v3_1.
Input Output 
Input Format:
chatml prompt format
Performance Tips:
Use min_p 0.1-0.2 to cut off Chinese characters from responses sneaking in at random times at low probabilities.
LLM NameYi 34B 200K Aezakmi Raw 1902 EXL2
Repository 🤗https://huggingface.co/adamo1139/yi-34b-200k-aezakmi-raw-1902-exl2 
Base Model(s)  Yi 34B 200K AEZAKMI RAW 1701   adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701
Model Size34b
Required VRAM20.7 GB
Updated2025-03-11
Maintaineradamo1139
Model Typellama
Model Files  4.3 GB: 1-of-5   4.2 GB: 2-of-5   4.2 GB: 3-of-5   4.2 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 1902 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
Yi 34B 200K RPMerge195K / 68.9 GB15360
Yi 34B 200K MAR2024 EXL2 4bpw195K / 18 GB151
...B 200K RPMerge 4.65bpw H6 EXL2195K / 10.5 GB191
...mi Raw Toxic 2702 4.65bpw EXL2195K / 20.8 GB142
Opus V1 34B 5.0bpw H6 EXL2195K / 22.3 GB162
Opus V1 34B 8.0bpw H8 EXL2195K / 34.8 GB181
Opus V1 34B 4.0bpw H6 EXL2195K / 18 GB171
Yi 34B 200K RPMerge EXL2 40bpw195K / 18.1 GB4420
34B Beta 5.0bpw H6 EXL2195K / 22.3 GB131
34B Beta 4.0bpw H6 EXL2195K / 18.1 GB101

Rank the Yi 34B 200K Aezakmi Raw 1902 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? 44887 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