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

Rogue Rose 103B V0.2 AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Rogue Rose 103B V0.2 AWQ   URL Share it on

  2344   
  Arxiv:2307.11760   4-bit   Autotrain compatible   Awq Base model:quantized:sophosymp... Base model:sophosympatheia/rog...   En   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/Rogue-Rose-103b-v0.2-AWQ 

Rogue Rose 103B V0.2 AWQ Benchmarks

LLME Score: 0.1639
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Rogue Rose 103B V0.2 AWQ (TheBloke/Rogue-Rose-103b-v0.2-AWQ)

Rogue Rose 103B V0.2 AWQ Parameters and Internals

Model Type 
llama
Use Cases 
Primary Use Cases:
roleplaying, storytelling
Limitations:
It still struggles with scene logic sometimes.
Considerations:
The model roleplays and tells stories well but may perform variably on other tasks.
Additional Notes 
A frankenmerge model inspired by or descended from the xwin-stellarbright-erp-70b-v2 model. Performs well at 8192 context length with 120 layers and an approximate size of 103 billion parameters.
Supported Languages 
en (English)
Training Details 
Context Length:
8192
Model Architecture:
frankenmerge of two custom 70b merges
Input Output 
Input Format:
'This is very important to my career' is from [this paper](https://arxiv.org/abs/2307.11760).
Accepted Modalities:
text
Output Format:
Generates text as a creative and attentive AI assistant roleplaying different characters.
Performance Tips:
Use the Min-P sampler method. Supports high temperatures and benefits from higher repetition and presence penalties.
LLM NameRogue Rose 103B V0.2 AWQ
Repository 🤗https://huggingface.co/TheBloke/Rogue-Rose-103b-v0.2-AWQ 
Model NameRogue Rose 103B v0.2
Model CreatorSophosympatheia
Base Model(s)  sophosympatheia/Rogue-Rose-103b-v0.2   sophosympatheia/Rogue-Rose-103b-v0.2
Model Size103b
Required VRAM54.4 GB
Updated2025-05-14
MaintainerTheBloke
Model Typellama
Model Files  9.9 GB: 1-of-6   9.9 GB: 2-of-6   9.9 GB: 3-of-6   10.0 GB: 4-of-6   9.9 GB: 5-of-6   4.8 GB: 6-of-6
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Rogue Rose 103B V0.2 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Aurora Nights 103B V1.0 AWQ4K / 54.4 GB41
Lila 103B L2 AWQ4K / 54.4 GB51
... Dark Miqu 103B 5.0bpw H8 EXL231K / 65.1 GB50
...qu 103B V1.5 EXL2 5.0bpw Rpcal31K / 64.9 GB371
...qu 103B V1.5 EXL2 4.0bpw Rpcal31K / 52.1 GB121
... Miqu 103B V1.5 3.5bpw H6 EXL231K / 45.6 GB41
...qu 103B V1.5 EXL2 3.0bpw Rpcal31K / 39.3 GB61
...ht Miqu 103B V1.0 EXL2 4.25bpw31K / 55.3 GB71
...ght Miqu 103B V1.0 EXL2 4.0bpw31K / 52.2 GB51
...ght Miqu 103B V1.0 EXL2 4.5bpw31K / 58.7 GB51
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Rogue-Rose-103b-v0.2-AWQ.

Rank the Rogue Rose 103B V0.2 AWQ 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? 47340 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