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

NeuralExperiment 7B MagicCoder V7.5 by Kukedlc

 »  All LLMs  »  Kukedlc  »  NeuralExperiment 7B MagicCoder V7.5   URL Share it on

  1609   
  Autotrain compatible Dataset:ise-uiuc/magicoder-evo... Dataset:microsoft/orca-math-wo... Dataset:vezora/tested-22k-pyth...   Endpoints compatible   Instruct   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Kukedlc/NeuralExperiment-7b-MagicCoder-v7.5 

NeuralExperiment 7B MagicCoder V7.5 Benchmarks

MMLU Pro: 20.27
GPQA: 6.15
MUSR: 13.06
BBH: 16.39
IFEval: 45.53 vs 88 (so35)-48.3%
ARC: 71.33 vs 96.7 (so35)-26.2%
HellaSwag: 87.94 vs 95.3 (gpt4)-7.7%
MMLU: 64.62 vs 88.3 (so35)-26.8%
TruthfulQA: 72.11 vs 59 (gpt4)22.2%
WinoGrande: 83.5 vs 87.5 (gpt4)-4.6%
GSM8K: 66.19 vs 96.4 (so35)-31.3%
MATH Lvl 5: 6.65
LLME Score: 0.24702
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
NeuralExperiment 7B MagicCoder V7.5 (Kukedlc/NeuralExperiment-7b-MagicCoder-v7.5)

NeuralExperiment 7B MagicCoder V7.5 Parameters and Internals

Additional Notes 
Users interested in replicating or extending this training can find the Kaggle notebook in my profile or request it for collaborative purposes.
Training Details 
Data Sources:
microsoft/orca-math-word-problems-200k, ise-uiuc/Magicoder-Evol-Instruct-110K, sahil2801/CodeAlpaca-20k
Data Volume:
20,000 data points per dataset
Methodology:
Fine-tuning from the last layer (31) backward with a gradually decreasing learning rate to address the 'INSTINST' bug
Hardware Used:
Kaggle's free GPU environment
LLM NameNeuralExperiment 7B MagicCoder V7.5
Repository 🤗https://huggingface.co/Kukedlc/NeuralExperiment-7b-MagicCoder-v7.5 
Model Size7b
Required VRAM14.4 GB
Updated2025-03-22
MaintainerKukedlc
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to NeuralExperiment 7B MagicCoder V7.5

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB219215
SpydazWeb AI HumanAI RP512K / 14.4 GB131
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB50
...1 Summarize 64K LoRANET Merged128K / 14.4 GB140
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB8030981602
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB36225
...ty Instruct 3M 0625 Mistral 7B32K / 14.4 GB35733
Note: green Score (e.g. "73.2") means that the model is better than Kukedlc/NeuralExperiment-7b-MagicCoder-v7.5.

Rank the NeuralExperiment 7B MagicCoder V7.5 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? 45389 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