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

Mixtral AI CyberCoder by LeroyDyer

 »  All LLMs  »  LeroyDyer  »  Mixtral AI CyberCoder   URL Share it on

  0   

Mixtral AI CyberCoder is an open-source language model by LeroyDyer. Features: 7b LLM, VRAM: 14.3GB, Context: 32K, License: apache-2.0, Instruction-Based, Merged, HF Score: 51.3, LLM Explorer Score: 0.28, Arc: 56.1, HellaSwag: 74.9, MMLU: 49.5, TruthfulQA: 40.4, WinoGrande: 71.4, GSM8K: 15.3.

  Merged Model   Arxiv:2306.01708   Art   Autotrain compatible Base model:leroydyer/mixtral a... Base model:leroydyer/mixtral a... Base model:leroydyer/mixtral a... Base model:mistralai/mistral-7...   Code   Conversational   Cyber-series Dataset:cybernative/code vulne... Dataset:whiterabbitneo/wrn-cha... Dataset:whiterabbitneo/wrn-cha...   Endpoints compatible   Instruct   License:apache-2.0   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LeroyDyer/Mixtral_AI_CyberCoder 

Mixtral AI CyberCoder Benchmarks

ARC: 56.06 vs 96.7 (so35)-42%
HellaSwag: 74.85 vs 95.3 (gpt4)-21.5%
MMLU: 49.51 vs 88.3 (so35)-43.9%
TruthfulQA: 40.42 vs 59 (gpt4)-31.5%
WinoGrande: 71.43 vs 87.5 (gpt4)-18.4%
GSM8K: 15.31 vs 96.4 (so35)-84.1%
LLME Score: 0.27821
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mixtral AI CyberCoder (LeroyDyer/Mixtral_AI_CyberCoder)
🌟 Advertise your project 🚀

Mixtral AI CyberCoder Parameters and Internals

Model Type 
text generation, code generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
Code generation, UML diagrams, Object-oriented planning
Additional Notes 
This model is under development and is being constantly retuned and updated for its use in producing code, functions, and applications. It has been fine-tuned on datasets dedicated to coding problems and other code-related tasks.
Training Details 
Data Sources:
CyberNative/Code_Vulnerability_Security_DPO, WhiteRabbitNeo/WRN-Chapter-1, WhiteRabbitNeo/WRN-Chapter-2
Methodology:
Merge using TIES merge method
Model Architecture:
This is a merge of pre-trained language models created using mergekit.
LLM NameMixtral AI CyberCoder
Repository 🤗https://huggingface.co/LeroyDyer/Mixtral_AI_CyberCoder 
Base Model(s)  mistralai/Mistral-7B-Instruct-v0.2   LeroyDyer/Mixtral_AI_Cyber_3.0   LeroyDyer/Mixtral_AI_MultiToken   LeroyDyer/Mixtral_AI_Multi_TEST   mistralai/Mistral-7B-Instruct-v0.2   LeroyDyer/Mixtral_AI_Cyber_3.0   LeroyDyer/Mixtral_AI_MultiToken   LeroyDyer/Mixtral_AI_Multi_TEST
Merged ModelYes
Model Size7b
Required VRAM14.3 GB
Updated2024-07-04
MaintainerLeroyDyer
Model Typemistral
Instruction-BasedYes
Model Files  1.9 GB: 1-of-8   1.9 GB: 2-of-8   2.0 GB: 3-of-8   1.9 GB: 4-of-8   1.9 GB: 5-of-8   1.9 GB: 6-of-8   1.9 GB: 7-of-8   0.9 GB: 8-of-8
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Mixtral AI CyberCoder

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB25420
SpydazWeb AI HumanAI RP512K / 14.4 GB141
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB60
...1 Summarize 64K LoRANET Merged128K / 14.4 GB60
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB4038841832
Mistral 7B Instruct V0.232K / 14.4 GB57590
Mistral Stargate32K / 14.4 GB83
Note: green Score (e.g. "73.2") means that the model is better than LeroyDyer/Mixtral_AI_CyberCoder.

Rank the Mixtral AI CyberCoder 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? 53151 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer