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

Yi 9B 200K by 01-ai

 »  All LLMs  »  01-ai  »  Yi 9B 200K   URL Share it on

  10026   
  Arxiv:2311.16502   Arxiv:2401.11944   Arxiv:2403.04652   Autotrain compatible   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow

Yi 9B 200K Benchmarks

MMLU Pro: 29.13
GPQA: 8.72
MUSR: 12.11
BBH: 26.49
IFEval: 23.27 vs 88 (so35)-73.6%
ARC: 58.02 vs 96.7 (so35)-40%
HellaSwag: 78.58 vs 95.3 (gpt4)-17.5%
MMLU: 70.34 vs 88.3 (so35)-20.3%
TruthfulQA: 40.63 vs 59 (gpt4)-31.1%
WinoGrande: 76.48 vs 87.5 (gpt4)-12.6%
GSM8K: 47.61 vs 96.4 (so35)-50.6%
MATH Lvl 5: 6.72
LLME Score: 0.32213
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Yi 9B 200K Parameters and Internals

Model Type 
Chat model, Text generation
Use Cases 
Areas:
Chat applications, Creative content generation
Applications:
Commercial applications, Research, Educational tools
Primary Use Cases:
Chatbots, Virtual assistants, Story generation
Limitations:
Potential for hallucination, May produce inconsistent outputs
Considerations:
Adjust generation parameters for desired output qualities.
Additional Notes 
Models do not directly use Llama's weights; unique datasets and training infrastructure emphasize Yi's independent development.
Supported Languages 
English (Fluent), Chinese (Fluent)
Training Details 
Data Sources:
Trainer Multilingual Corpora, 3T Tokens
Data Volume:
3T Multilingual Corpus
Methodology:
Transformer-based architecture
Context Length:
200000
Training Time:
Not specified
Hardware Used:
NVIDIA A800 (80GB), 4090 GPU
Model Architecture:
Based on Llama's architecture
Responsible Ai Considerations 
Fairness:
Addressed during model development.
Transparency:
Standard Transformer architecture; detailed in tech report.
Accountability:
01.AI
Mitigation Strategies:
Use of Supervised Fine-Tuning for better accuracy.
Input Output 
Input Format:
Interactive prompt conversation
Accepted Modalities:
Text
Output Format:
Text responses or follow-ups
Performance Tips:
Calibrate temperature, top_p, top_k settings for desired response diversity.
Release Notes 
Version:
1.0
Date:
2023-11-23
Notes:
Initial open-source release of chat model, supporting both 4-bit and 8-bit quantizations.
Version:
2.0
Date:
2023-12-19
Notes:
Improved performance in coding, math, and reasoning with larger context capabilities.
LLM NameYi 9B 200K
Repository 🤗https://huggingface.co/01-ai/Yi-9B-200K 
Model Size9b
Required VRAM17.7 GB
Updated2024-11-21
Maintainer01-ai
Model Typellama
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   2.8 GB: 4-of-4
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typebfloat16
Yi 9B 200K (01-ai/Yi-9B-200K)

Quantized Models of the Yi 9B 200K

Model
Likes
Downloads
VRAM
Yi 9B 200K GGUF51663 GB

Best Alternatives to Yi 9B 200K

Best Alternatives
Context / RAM
Downloads
Likes
BigYi 15.75B 200K256K / 30.3 GB310
Yi Coder 9B128K / 17.7 GB686139
Yi Coder 9B Chat128K / 17.7 GB6448190
CursorCore Yi 9B128K / 17.7 GB191
Yi Coder 9B Chat Instruct TIES128K / 17.7 GB170
Yi 1.5 9B 32K32K / 17.7 GB1037118
Faro Yi 9B DPO32K / 17.7 GB565729
EVA Yi 1.5 9B 32K V132K / 17.7 GB1412
Faro Yi 9B32K / 17.7 GB573317
Openbuddy Yi1.5 9B V21.1 32K32K / 17.8 GB11261
Note: green Score (e.g. "73.2") means that the model is better than 01-ai/Yi-9B-200K.

Rank the Yi 9B 200K 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? 38199 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 v20241110
  Support LLM Explorer