Results by farshadafx

 ยป  All LLMs  ยป  farshadafx  ยป  Results   URL Share it on

  Adapter Base model:adapter:microsoft/p... Base model:microsoft/phi-3-vis...   Finetuned   Generated from trainer   Instruct   Lora   Peft   Region:us   Safetensors   Sft   Trl   Vision
Model Card on HF ๐Ÿค—: https://huggingface.co/farshadafx/results 

Results Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Results (farshadafx/results)

Results Parameters and Internals

LLM NameResults
Repository ๐Ÿค—https://huggingface.co/farshadafx/results 
Base Model(s)  Phi 3 Vision 128K Instruct   microsoft/Phi-3-vision-128k-instruct
Required VRAM0 GB
Updated2024-11-07
Maintainerfarshadafx
Instruction-BasedYes
Model Files  0.0 GB   0.0 GB
Model ArchitectureAdapter
Licensemit
Model Max Length131072
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesgate_proj|v_proj|down_proj|o_proj|k_proj|up_proj|q_proj
LoRA Alpha32
LoRA Dropout0.05
R Param16

Best Alternatives to Results

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3 Mini 4K Instruct Sa V0.10K / 0 GB90
Mistral Small Fujin Qlora0K / 0.8 GB151
Test0K / 0 GB50
Vfgf0K / 0 GB60
Phi 3 Mini QLoRA0K / 0 GB1800
Results Phi3 Medium 4k0K / 0.1 GB50
Results0K / 0.1 GB50
Phi3AdapterModel0K / 0.1 GB50
Phi 3 Mini 4K Instruct Sft CoT0K / 0.1 GB50
Phi 3 Mini 4K Instruct Sft0K / 0 GB60
Note: green Score (e.g. "73.2") means that the model is better than farshadafx/results.

Rank the Results Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217