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

Aurelian V0.5 70B Rope8 32K Fp16 by grimulkan

 »  All LLMs  »  grimulkan  »  Aurelian V0.5 70B Rope8 32K Fp16   URL Share it on

  3   
  Autotrain compatible   Endpoints compatible   Fp16   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/grimulkan/aurelian-v0.5-70b-rope8-32K-fp16 

Aurelian V0.5 70B Rope8 32K Fp16 Benchmarks

LLME Score: 0.13363
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Aurelian V0.5 70B Rope8 32K Fp16 (grimulkan/aurelian-v0.5-70b-rope8-32K-fp16)
🌟 Advertise your project 🚀

Aurelian V0.5 70B Rope8 32K Fp16 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
Story writing, Roleplaying, Document Q&A and Summarization, Interactive World Exploration
Primary Use Cases:
Multi-Round Story Writing, Oneshot Story-writing, Multi-Round Story Planning/Brainstorming, Document Q&A and Summarization, Roleplaying (RP), Interactive World Exploration
Limitations:
No guarantees that the model won't generate NSFW content.
Considerations:
This model is capable of producing offensive and NSFW content. Please use with caution.
Training Details 
Data Sources:
Human-written stories from forums, fanfic websites, The Pile, Summaries of Wikipedia articles, Physical/Spatial Reasoning, Relational Reasoning, Theory of Mind problems, Document Editing Tasks, Sections of Airoboros 2.2.1/3.1, Sections of Surge Instruct, Proxy RP Logs, A fully re-generated version of Floyd Text Adventures, A fully re-generated version of the CYS dataset, NART synthetic therapy logs, Augmental-Stenisgate-Augmented, bluemoon_Karen_cleaned, PIPPA-augmented-dedup, LimaRP-augmented, Erotic Analysis used in reverse, Reading Comprehension, Unnatural Instructions, passkey-retrieval, Long Instructions, OpenORCA GPT4 outputs, Ultrachat Uncensored, ShareGPT Hyper Filtered, Claude Multiround, Wizard Vicuna Unfiltered, SODA Synthetic Dialogue
Methodology:
Fine-tuned with Llama-2 chat format
Input Output 
Accepted Modalities:
text
Performance Tips:
Treat the first prompt like you normally would the system prompt. Describe in detail, even if obvious, and bias the length of the output with your prompt.
Release Notes 
Version:
v0.5
Notes:
Greatly minimizes 'chatGPTisms'. Increased diversity of NSFW prose.
LLM NameAurelian V0.5 70B Rope8 32K Fp16
Repository 🤗https://huggingface.co/grimulkan/aurelian-v0.5-70b-rope8-32K-fp16 
Model Size70b
Required VRAM138.3 GB
Updated2025-09-13
Maintainergrimulkan
Model Typellama
Model Files  4.1 GB: 1-of-35   4.1 GB: 2-of-35   3.9 GB: 3-of-35   4.1 GB: 4-of-35   4.0 GB: 5-of-35   3.9 GB: 6-of-35   4.1 GB: 7-of-35   4.0 GB: 8-of-35   3.9 GB: 9-of-35   4.1 GB: 10-of-35   4.0 GB: 11-of-35   3.9 GB: 12-of-35   4.1 GB: 13-of-35   4.0 GB: 14-of-35   3.9 GB: 15-of-35   4.1 GB: 16-of-35   4.0 GB: 17-of-35   3.9 GB: 18-of-35   4.1 GB: 19-of-35   4.0 GB: 20-of-35   3.9 GB: 21-of-35   4.1 GB: 22-of-35   4.0 GB: 23-of-35   3.9 GB: 24-of-35   4.1 GB: 25-of-35   4.0 GB: 26-of-35   3.9 GB: 27-of-35   4.1 GB: 28-of-35   4.0 GB: 29-of-35   3.9 GB: 30-of-35   4.1 GB: 31-of-35   4.0 GB: 32-of-35   3.9 GB: 33-of-35   4.1 GB: 34-of-35   2.1 GB: 35-of-35
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Licenseunknown
Context Length4096
Model Max Length4096
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Aurelian V0.5 70B Rope8 32K Fp16

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB205
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB73
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB132
...0B Instruct Gradient 262K 4bit256K / 39.7 GB133
...0B Instruct Gradient 262K 8bit256K / 75 GB72
...0B Instruct Gradient 262K 2bit256K / 21.9 GB91
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB70
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB51
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB50
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB50
Note: green Score (e.g. "73.2") means that the model is better than grimulkan/aurelian-v0.5-70b-rope8-32K-fp16.

Rank the Aurelian V0.5 70B Rope8 32K Fp16 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? 51352 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 v20241124
  Support LLM Explorer