Magic 8B by jeiku

 ยป  All LLMs  ยป  jeiku  ยป  Magic 8B   URL Share it on

  Autotrain compatible Base model:dans-discountmodels... Base model:finetune:dans-disco...   Conversational   Endpoints compatible   Generated from trainer   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/jeiku/Magic_8B 

Magic 8B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Magic 8B (jeiku/Magic_8B)

Magic 8B Parameters and Internals

Model Type 
AutoModelForCausalLM
Additional Notes 
More information needed for model description, intended uses & limitations, and training and evaluation data.
Training Details 
Data Sources:
PocketDoc/Dans-MemoryCore-CoreCurriculum-Small, NewEden/Kalo-Opus-Instruct-22k-Refusal-Murdered, Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned, NewEden/Gryphe-Sonnet-3.5-35k-Subset, jeiku/Nitral_Medical_Dialog_Fixed
Context Length:
8192
Hardware Used:
multi-GPU, 2 devices
LLM NameMagic 8B
Repository ๐Ÿค—https://huggingface.co/jeiku/Magic_8B 
Base Model(s)  ...l NeMo Minitron 8B Base ChatML   Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML
Model Size8b
Required VRAM16.8 GB
Updated2024-09-18
Maintainerjeiku
Model Typemistral
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   2.0 GB: 4-of-4
Model ArchitectureMistralForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.45.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Magic 8B

Best Alternatives
Context / RAM
Downloads
Likes
Ministral 8B Instruct 2410 HF32K / 32 GB67010
...2G8kOm2Ag40kIpsdpIter1T02 B0.132K / 16.1 GB14460
Ministrations 8B V132K / 16.1 GB5616
...m2G8kOm2Ag40kIpsdpIter1T1 B1.032K / 16.1 GB4940
...ic Mini8bT0GtT1MstllrgT2 SftT232K / 16.1 GB2960
...ct Mini8B MistlrgOrcl460kSftT232K / 16.1 GB1650
...inistral8Bit Om2 Sft T2 Lr.5 632K / 16.1 GB9471
...ct Mini8B MistlrgOrcl460kSftT132K / 16.1 GB740
...Om2SftT2 Om2IpsdpIter1T02 B0.532K / 16.1 GB1700
Ministral 8B Slerp32K / 29.2 GB50
Note: green Score (e.g. "73.2") means that the model is better than jeiku/Magic_8B.

Rank the Magic 8B 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? 41817 in total.

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