OpenCrystal 12B L3 by Darkknight535

 ยป  All LLMs  ยป  Darkknight535  ยป  OpenCrystal 12B L3   URL Share it on

  Autotrain compatible   Conversational   Endpoints compatible   Instruct   Llama   Model-index   Not-for-all-audiences   Region:us   Safetensors   Sharded   Tensorflow

OpenCrystal 12B L3 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
OpenCrystal 12B L3 (Darkknight535/OpenCrystal-12B-L3)

OpenCrystal 12B L3 Parameters and Internals

Model Type 
text generation, roleplay, storytelling
Additional Notes 
This model can speak as other NPCs automatically, follows prompts better, and can summarize and generate image prompts well. It sometimes outputs suggestive content and is inspired by the Llama-3 instruct base's capabilities.
Input Output 
Performance Tips:
You can uncheck 'Include Names' option in sillytavern, to force it to speak as others dynamically.
LLM NameOpenCrystal 12B L3
Repository ๐Ÿค—https://huggingface.co/Darkknight535/OpenCrystal-12B-L3 
Base Model(s)  Darkknight6742/L3-12B-Niitama-v1   Darkknight6742/L3-12B-Celeste-V1.2   Darkknight6742/llama-3-12b-Instruct   Darkknight6742/L3-12B-Niitama-v1   Darkknight6742/L3-12B-Celeste-V1.2   Darkknight6742/llama-3-12b-Instruct
Model Size12b
Required VRAM23 GB
Updated2025-02-22
MaintainerDarkknight535
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-5   5.0 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   3.2 GB: 5-of-5
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.44.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_250|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to OpenCrystal 12B L3

Best Alternatives
Context / RAM
Downloads
Likes
OpenCrystal 12B L3.1 128K128K / 23 GB143
Meta Llama 3 12B Instruct AWQ8K / 7.5 GB830

Rank the OpenCrystal 12B L3 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227