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

NeuralReyna Mini 1.8B V0.2 by M4-ai

 »  All LLMs  »  M4-ai  »  NeuralReyna Mini 1.8B V0.2   URL Share it on

  112   
  Autotrain compatible   Conversational   Dataset:intel/orca dpo pairs Dataset:locutusque/hercules-v3...   En   Endpoints compatible   Model-index   Qwen2   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/M4-ai/NeuralReyna-Mini-1.8B-v0.2 

NeuralReyna Mini 1.8B V0.2 Benchmarks

ARC: 37.8 vs 96.7 (so35)-60.9%
HellaSwag: 60.51 vs 95.3 (gpt4)-36.5%
MMLU: 45.04 vs 88.3 (so35)-49%
TruthfulQA: 37.75 vs 59 (gpt4)-36%
WinoGrande: 60.93 vs 87.5 (gpt4)-30.4%
GSM8K: 27.07 vs 96.4 (so35)-71.9%
LLME Score: 0.20377
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
NeuralReyna Mini 1.8B V0.2 (M4-ai/NeuralReyna-Mini-1.8B-v0.2)

NeuralReyna Mini 1.8B V0.2 Parameters and Internals

Model Type 
text-generation
Use Cases 
Primary Use Cases:
coding, math, science, roleplay, function calling
Additional Notes 
The model may have overfitted to the DPO training data, potentially affecting performance.
Training Details 
Data Sources:
Intel/orca_dpo_pairs
Methodology:
Fine-tuned using DPO
Model Architecture:
Trained on OpenAI's ChatML prompt format
LLM NameNeuralReyna Mini 1.8B V0.2
Repository 🤗https://huggingface.co/M4-ai/NeuralReyna-Mini-1.8B-v0.2 
Model Size1.8b
Required VRAM3.7 GB
Updated2025-02-22
MaintainerM4-ai
Model Typeqwen2
Model Files  3.7 GB
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to NeuralReyna Mini 1.8B V0.2

Best Alternatives
Context / RAM
Downloads
Likes
Dhanishtha128K / 3.5 GB822
Qwen1.5 1.8B32K / 3.7 GB13018647
Qwen1.5 1.8B Chat32K / 3.7 GB1215949
MiniPLM Qwen 200M32K / 0.8 GB2772
MiniPLM Qwen 500M32K / 1.9 GB2215
Qwen1.5 1.8B Seed Sft32K / 3.7 GB1560
Orca 2.0 Tau 1.8B32K / 3.7 GB4069
Neural Chat Mini V2.2 1.8B32K / 3.7 GB666
Qwen1.5 Wukong 1.8B32K / 3.7 GB724
Coder1.8 ORPO TEST32K / 3.7 GB1412
Note: green Score (e.g. "73.2") means that the model is better than M4-ai/NeuralReyna-Mini-1.8B-v0.2.

Rank the NeuralReyna Mini 1.8B V0.2 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