NebulaNet V2 4x7B MoE by davideuler

 ยป  All LLMs  ยป  davideuler  ยป  NebulaNet V2 4x7B MoE   URL Share it on

  Autotrain compatible Base model:contextualai/contex... Base model:quantized:contextua...   Coding   Conversational   Endpoints compatible   Gguf   Mixtral   Moe   Multilingual   Quantized   Region:us   Safetensors

NebulaNet V2 4x7B MoE Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
NebulaNet V2 4x7B MoE (davideuler/NebulaNet-v2-4x7B-moe)

NebulaNet V2 4x7B MoE Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
coding, multi language translation, chat, math
Additional Notes 
NebulaNet-v2 is an MOE (Mixture of Experts) model consisting of 4 expert models, each with 7 billion parameters.
Supported Languages 
multilingual ()
LLM NameNebulaNet V2 4x7B MoE
Repository ๐Ÿค—https://huggingface.co/davideuler/NebulaNet-v2-4x7B-moe 
Base Model(s)  Contextual KTO Mistral PairRM   ContextualAI/Contextual_KTO_Mistral_PairRM
Required VRAM8.8 GB
Updated2025-02-05
Maintainerdavideuler
Model Typemixtral
Model Files  8.8 GB   19.8 GB   25.7 GB
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureMixtralForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.39.1
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to NebulaNet V2 4x7B MoE

Best Alternatives
Context / RAM
Downloads
Likes
WizardLM2 2bit64K / 4.8 GB1550
Cerebrum 1.0 8x7b GGUF32K / 17.3 GB141
Dolphin 2.7 Mixtral 8x7b GGUF32K / 15.6 GB2625
...Hermes 2 Mixtral 8x7B DPO GGUF32K / 17.3 GB2082
...Hermes 2 Mixtral 8x7B SFT GGUF32K / 17.3 GB1614
...ixtral 8x7B Instruct V0.1 GGUF32K / 17.3 GB2085
...oE V0.1 DPO F16 4.0bpw H6 EXL2195K / 31.3 GB60
...oE V0.1 DPO F16 5.0bpw H6 EXL2195K / 38.8 GB50
...2 Mixtral 8x22b 6.0bpw H8 EXL264K / 105.8 GB61
WizardLM 2 8x22 EXL2 4.0bpw64K / 70.9 GB71
Note: green Score (e.g. "73.2") means that the model is better than davideuler/NebulaNet-v2-4x7B-moe.

Rank the NebulaNet V2 4x7B MoE 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? 42577 in total.

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