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

NeuralBeagle14 7B by mlabonne

 »  All LLMs  »  mlabonne  »  NeuralBeagle14 7B   URL Share it on

  116   
  Autotrain compatible Base model:finetune:mlabonne/b... Base model:mlabonne/beagle14-7...   Conversational   Dpo   Endpoints compatible   Lazymergekit   Merge   Mergekit   Mistral   Model-index   Region:us   Rlhf   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlabonne/NeuralBeagle14-7B 

NeuralBeagle14 7B Benchmarks

MMLU Pro: 17.79
GPQA: 4.25
MUSR: 12.89
BBH: 23.96
IFEval: 49.35 vs 88 (so35)-43.9%
ARC: 72.95 vs 96.7 (so35)-24.6%
HellaSwag: 88.34 vs 95.3 (gpt4)-7.3%
MMLU: 64.55 vs 88.3 (so35)-26.9%
TruthfulQA: 69.93 vs 59 (gpt4)18.5%
WinoGrande: 82.4 vs 87.5 (gpt4)-5.8%
GSM8K: 70.28 vs 96.4 (so35)-27.1%
MATH Lvl 5: 5.21
LLME Score: 0.21753
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
NeuralBeagle14 7B (mlabonne/NeuralBeagle14-7B)

NeuralBeagle14 7B Parameters and Internals

Model Type 
text generation
Use Cases 
Primary Use Cases:
Instruction following, Reasoning tasks, Roleplay (RP), Storytelling
Additional Notes 
NeuralBeagle14-7B is considered one of the best models in its parameter size category due to its strong performance in benchmarks.
Training Details 
Data Sources:
argilla/distilabel-intel-orca-dpo-pairs
Methodology:
Direct Preference Optimization (DPO) fine-tuning
Context Length:
8000
LLM NameNeuralBeagle14 7B
Repository 🤗https://huggingface.co/mlabonne/NeuralBeagle14-7B 
Base Model(s)  Beagle14 7B   mlabonne/Beagle14-7B
Model Size7b
Required VRAM14.4 GB
Updated2025-05-30
Maintainermlabonne
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the NeuralBeagle14 7B

Model
Likes
Downloads
VRAM
NeuralBeagle14 7B GGUF268132 GB
NeuralBeagle14 7B GGUF01822 GB
NeuralBeagle14 7B GGUF1752 GB
NeuralBeagle14 7B GPTQ5404 GB
NeuralBeagle14 7B AWQ3414 GB

Best Alternatives to NeuralBeagle14 7B

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB122616
MegaBeam Mistral 7B 512K512K / 14.4 GB369050
SpydazWeb AI HumanAI RP512K / 14.4 GB121
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB377916
MegaBeam Mistral 7B 300K282K / 14.4 GB341316
Hebrew Mistral 7B 200K256K / 30 GB317815
Astral 256K 7B V2250K / 14.4 GB110
Astral 256K 7B250K / 14.4 GB100
Note: green Score (e.g. "73.2") means that the model is better than mlabonne/NeuralBeagle14-7B.

Rank the NeuralBeagle14 7B 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? 47715 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