STEMerald 2B 4bit by matsant01

 ยป  All LLMs  ยป  matsant01  ยป  STEMerald 2B 4bit   URL Share it on

  Arxiv:2403.08295   4-bit   4bit   Autotrain compatible   Biology   Bitsandbytes   Chemistry   Computer science   Conversational   Data science   Dataset:allenai/ai2 arc   Dataset:derek-thomas/scienceqa   Education   En   Endpoints compatible   Engineering   Gemma   Quantized   Region:us   Safetensors   Stem

STEMerald 2B 4bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
STEMerald 2B 4bit (matsant01/STEMerald-2b-4bit)

STEMerald 2B 4bit Parameters and Internals

Model Type 
Decoder-only Language Model (Causal)
Use Cases 
Primary Use Cases:
Answering university-level multiple-choice STEM questions., Providing detailed explanations and reasoning for answers., Enhancing student engagement and learning efficiency during independent studies.
Limitations:
The model's performance may vary based on the specific context and nature of the questions., Quantization reduces memory footprint but may slightly affect accuracy.
Additional Notes 
STEMerald-2b is a fine-tuned version of the Gemma-2b model, aimed at answering university-level STEM multiple-choice questions.
Training Details 
Data Sources:
EPFL Preference Pairs Dataset, Stack Exchange Dataset, Orca-Math, EPFL MCQA Dataset, ScienceQA, AI2 Reasoning Challenge (ARC)
Methodology:
Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO)
Model Architecture:
Decoder-only Language Model (Causal)
Responsible Ai Considerations 
Fairness:
The model may provide incorrect answers; teacher supervision is crucial.
Input Output 
Input Format:
Multiple-choice STEM questions.
Accepted Modalities:
text
Output Format:
Text response with detailed explanations.
LLM NameSTEMerald 2B 4bit
Repository ๐Ÿค—https://huggingface.co/matsant01/STEMerald-2b-4bit 
Model Size2b
Required VRAM2.2 GB
Updated2025-02-15
Maintainermatsant01
Model Typegemma
Model Files  2.2 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureGemmaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.41.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typefloat16

Best Alternatives to STEMerald 2B 4bit

Best Alternatives
Context / RAM
Downloads
Likes
... 2B It Hermes Function Calling8K / 5.1 GB80
Gemma 1.1 2B It Bnb 4bit8K / 2.1 GB38895
Vi Gemma 2B RAG8K / 5.1 GB17813
Codegemma 2B Bnb 4bit8K / 2.1 GB24651
Gemma 2B Bnb 4bit8K / 2.1 GB393216
My AwesomeFinance Model8K / 2.1 GB910
Emo AI 3B8K / 5.1 GB1091
Jenna V3 QGemma 2B8K / 5.1 GB1090
Gemma 2B FT 500 Orca Maths8K / 5.1 GB1530
... 2.8 Gemma 2B Bnb 4bit Smashed8K / 2.2 GB880
Note: green Score (e.g. "73.2") means that the model is better than matsant01/STEMerald-2b-4bit.

Rank the STEMerald 2B 4bit 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? 43137 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227