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

Starling Low Tune by nlpguy

 »  All LLMs  »  nlpguy  »  Starling Low Tune   URL Share it on

  5   
  Adapter Base model:adapter:chujiezheng... Base model:chujiezheng/starlin...   Finetuned   Generated from trainer   Llama-factory   Lora   Peft   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/nlpguy/Starling-low-tune 

Starling Low Tune Benchmarks

ARC: 62.12 vs 96.7 (so35)-35.8%
HellaSwag: 83.06 vs 95.3 (gpt4)-12.8%
MMLU: 64.24 vs 88.3 (so35)-27.2%
TruthfulQA: 42.58 vs 59 (gpt4)-27.8%
WinoGrande: 81.14 vs 87.5 (gpt4)-7.3%
GSM8K: 61.87 vs 96.4 (so35)-35.8%
LLME Score: 0.19813
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Starling Low Tune (nlpguy/Starling-low-tune)

Starling Low Tune Parameters and Internals

Additional Notes 
This model is a fine-tuned version of Starling-LM-7B-alpha-ExPO on the no_robots dataset. More information is needed on its description, intended uses, limitations, and training evaluation data.
Training Details 
Methodology:
Fine-tuning
LLM NameStarling Low Tune
Repository 🤗https://huggingface.co/nlpguy/Starling-low-tune 
Base Model(s)  Starling LM 7B Alpha ExPO   chujiezheng/Starling-LM-7B-alpha-ExPO
Model Size7b
Required VRAM0 GB
Updated2024-11-15
Maintainernlpguy
Model Files  0.0 GB   0.0 GB
Model ArchitectureAdapter
Licenseapache-2.0
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<|end_of_turn|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|q_proj
LoRA Alpha16
LoRA Dropout0
R Param8

Best Alternatives to Starling Low Tune

Best Alternatives
Context / RAM
Downloads
Likes
Qwen Megumin0K / 0.1 GB130
...s 25 Mistral 7B Irca DPO Pairs0K / 0.1 GB50
Qwen1.5 7B Chat Sa V0.10K / 0 GB90
Zephyr 7B Ipo 0K 15K I10K / 0.7 GB90
Deepthink Reasoning Adapter0K / 0.2 GB278
Deepseek Llm 7B Chat Sa V0.10K / 0 GB50
... Days Of Sodom LoRA Mistral 7B0K / 0.2 GB50
Mistral 7B Instruct Sa V0.10K / 0 GB60
CodeAstra 7B0K / 0 GB63910
...eze Embed Tokens Q V Proj Lora0K / 0.1 GB41
Note: green Score (e.g. "73.2") means that the model is better than nlpguy/Starling-low-tune.

Rank the Starling Low Tune 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