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

Fusedyi by pharaouk

 »  All LLMs  »  pharaouk  »  Fusedyi   URL Share it on

  28   
  Autotrain compatible   Chatml   Conversational   Distillation   Dpo   En   Endpoints compatible   Finetuned   Gpt4   Instruct   Llama   Mixtral   Region:us   Rlhf   Safetensors   Sharded   Synthetic data   Tensorflow
Model Card on HF 🤗: https://huggingface.co/pharaouk/fusedyi 

Fusedyi Benchmarks

ARC: 55.03 vs 96.7 (so35)-43.1%
HellaSwag: 76.6 vs 95.3 (gpt4)-19.6%
MMLU: 63.43 vs 88.3 (so35)-28.2%
TruthfulQA: 49.29 vs 59 (gpt4)-16.5%
WinoGrande: 72.69 vs 87.5 (gpt4)-16.9%
GSM8K: 2.05 vs 96.4 (so35)-97.9%
LLME Score: 0.1885
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Fusedyi (pharaouk/fusedyi)

Fusedyi Parameters and Internals

Model Type 
chatbot, instruction-based
Additional Notes 
Fused Yi is a composite model formed by merging two instances of Yi-6B, described as 'Yi-ceptionized'.
Supported Languages 
en (full)
Training Details 
Methodology:
Fine-tuned with techniques including Mixtral, instruct finetuning, chatml, DPO, RLHF, utilizing synthetic data and distillation.
LLM NameFusedyi
Repository 🤗https://huggingface.co/pharaouk/fusedyi 
Model Size10.9b
Required VRAM43.3 GB
Updated2025-02-22
Maintainerpharaouk
Model Typellama
Model Files  4.8 GB: 1-of-9   4.8 GB: 2-of-9   4.8 GB: 3-of-9   4.8 GB: 4-of-9   4.8 GB: 5-of-9   4.8 GB: 6-of-9   4.8 GB: 7-of-9   4.8 GB: 8-of-9   4.9 GB: 9-of-9
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typefloat32

Best Alternatives to Fusedyi

Best Alternatives
Context / RAM
Downloads
Likes
Solar10B Eugeneparkthebestv24K / 21.7 GB20120
KoSOLAR 10.9B V1.04K / 43.4 GB20110
KoSoLAR 1way 1k 10epoch GPT44K / 43.4 GB60
DND V0.0 E14K / 43.4 GB360
Free Solar Instrunction V0.34K / 43.4 GB340
Free Solar Instrunction V0.24K / 43.4 GB380
Free Solar Instrunction V0.14K / 43.4 GB410
T3Q Merge SOLAR124K / 43.4 GB320
T3Q Merge SOLAR4K / 43.4 GB280
Kosolra SFT DPO V04K / 43.4 GB410
Note: green Score (e.g. "73.2") means that the model is better than pharaouk/fusedyi.

Rank the Fusedyi 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