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

L MChat Small by Artples

 »  All LLMs  »  Artples  »  L MChat Small   URL Share it on

  2928   
  Merged Model   Autotrain compatible Base model:rhysjones/phi-2-ora... Base model:weyaxi/einstein-v4-...   Conversational   Endpoints compatible   Model-index   Phi   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Artples/L-MChat-Small 

L MChat Small Benchmarks

MMLU Pro: 16.27
GPQA: 2.35
MUSR: 9.27
BBH: 26.86
IFEval: 32.87 vs 88 (so35)-62.6%
ARC: 61.6 vs 96.7 (so35)-36.3%
HellaSwag: 75.9 vs 95.3 (gpt4)-20.4%
MMLU: 57.41 vs 88.3 (so35)-35%
TruthfulQA: 49.94 vs 59 (gpt4)-15.4%
WinoGrande: 74.98 vs 87.5 (gpt4)-14.3%
GSM8K: 58.98 vs 96.4 (so35)-38.8%
MATH Lvl 5: 1.74
LLME Score: 0.27301
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
L MChat Small (Artples/L-MChat-Small)

L MChat Small Parameters and Internals

Model Type 
text-generation
Additional Notes 
This was a test to evaluate the performance of smaller merges, focusing on 2 billion parameter models compared to larger 7 billion parameter models and higher.
Training Details 
Methodology:
SLERP merge method
Input Output 
Input Format:
ChatML format
Accepted Modalities:
text
Output Format:
text
Release Notes 
Notes:
This model explores the performance of smaller (2 billion parameter) model merges in the L-MChat series using the SLERP merge method.
LLM NameL MChat Small
Repository 🤗https://huggingface.co/Artples/L-MChat-Small 
Base Model(s)  Phi 2 Orange V2   Einstein V4 Phi2   rhysjones/phi-2-orange-v2   Weyaxi/Einstein-v4-phi2
Merged ModelYes
Model Size2.8b
Required VRAM5.6 GB
Updated2025-02-05
MaintainerArtples
Model Typephi
Model Files  5.6 GB: 1-of-1
Model ArchitecturePhiForCausalLM
Licensemit
Context Length2048
Model Max Length2048
Transformers Version4.39.3
Tokenizer ClassCodeGenTokenizer
Padding Token<|endoftext|>
Vocabulary Size51200
Torch Data Typebfloat16

Best Alternatives to L MChat Small

Best Alternatives
Context / RAM
Downloads
Likes
MFANN3bv0.24128K / 11.1 GB50
MFANN3b128K / 11.1 GB1160
MFANN3bv1.3128K / 11.1 GB130
MFANN3bv1.1128K / 11.1 GB160
MFANN3bv0.23128K / 11.1 GB60
MFANN3b SFT128K / 5.6 GB1690
MFANN3b Rebase128K / 11.1 GB100
MFANN3bv1.2126K / 11.1 GB320
MFANN Phigments Slerp V232K / 5.6 GB1340
MFANN3bv0.2232K / 11.1 GB50
Note: green Score (e.g. "73.2") means that the model is better than Artples/L-MChat-Small.

Rank the L MChat Small 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? 42577 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