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

RoleBeagle 11B by vicgalle

 »  All LLMs  »  vicgalle  »  RoleBeagle 11B   URL Share it on

  96   
  Autotrain compatible   Conversational Dataset:vicgalle/openhermespre...   Endpoints compatible   Mistral   Model-index   Region:us   Roleplay   Rp   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/vicgalle/RoleBeagle-11B 

RoleBeagle 11B Benchmarks

ARC: 72.35 vs 96.7 (so35)-25.2%
HellaSwag: 89.77 vs 95.3 (gpt4)-5.8%
MMLU: 66.35 vs 88.3 (so35)-24.9%
TruthfulQA: 77.92 vs 59 (gpt4)32.1%
WinoGrande: 84.06 vs 87.5 (gpt4)-3.9%
GSM8K: 65.88 vs 96.4 (so35)-31.7%
LLME Score: 0.18796
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
RoleBeagle 11B (vicgalle/RoleBeagle-11B)

RoleBeagle 11B Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
roleplay, text generation
Additional Notes 
RoleBeagle-11B is a DPO-finetuned model designed for improved role-playing capabilities, derived from CarbonBeagle-11B.
Training Details 
Data Sources:
vicgalle/OpenHermesPreferences-roleplay
LLM NameRoleBeagle 11B
Repository 🤗https://huggingface.co/vicgalle/RoleBeagle-11B 
Model Size11b
Required VRAM21.4 GB
Updated2024-12-26
Maintainervicgalle
Model Typemistral
Model Files  4.9 GB: 1-of-5   5.0 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   1.7 GB: 5-of-5
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to RoleBeagle 11B

Best Alternatives
Context / RAM
Downloads
Likes
Starling LM 11B Alpha32K / 21.4 GB107912
...elik V2.3 Instruct MedIT Merge32K / 22.3 GB18231
...elik V2.3 Instruct Llama Prune32K / 15.4 GB20640
CarbonBeagle 11B Truthy32K / 21.4 GB1524010
ConfigurableBeagle 11B32K / 21.4 GB76363
CarbonBeagle 11B32K / 21.4 GB87869
Alphacode MALI 11B Slowtest32K / 21.8 GB47430
Alphacode MALI 11B32K / 21.8 GB47571
Mistral 11B Miniplatypus32K / 21.5 GB130
MistralLite 11B32K / 21.4 GB13372
Note: green Score (e.g. "73.2") means that the model is better than vicgalle/RoleBeagle-11B.

Rank the RoleBeagle 11B 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? 40248 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 v20241217
  Support LLM Explorer