Downloads · 30 days
278
13% of all-time downloads
NebulaNet-v2-4x7B-moe
davideuler/NebulaNet-v2-4x7B-moe
NebulaNet-v2-4x7B-moe is a text generation model from davideuler. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
NebulaNet-v2: An MOE of 4 7b expert models. It is good at coding and multi language translation. It should be fluent at chat and math too.
All-time downloads
2.2K
Public
Repo size
54.3 GB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.gguf54.3 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mit
- Model type
- mixtral
- Access
- Public
- Created
- Mar 24, 2024
- Updated
- Mar 25, 2024
- SHA
- ad80d219
Base models
Model card
From the Hugging Face model README
Usage
NebulaNet-v2: An MOE of 4 7b expert models. It is good at coding and multi language translation. It should be fluent at chat and math too.
The 4x7b merged model performs much better than the original Contextual_KTO_Mistral_PairRM on both coding and multilingual text generation in my observation.
mergekit config
base_model: ContextualAI/Contextual_KTO_Mistral_PairRM
experts:
- source_model: ContextualAI/Contextual_KTO_Mistral_PairRM
positive_prompts:
- "chat"
- "assistant"
- "tell me"
- "explain"
- "I want"
- source_model: Nexusflow/Starling-LM-7B-beta
positive_prompts:
- "code"
- "python"
- "javascript"
- "programming"
- "algorithm"
- source_model: snorkelai/Snorkel-Mistral-PairRM-DPO
positive_prompts:
- ""
- source_model: mlabonne/NeuralDaredevil-7B
positive_prompts:
- "reason"
- "math"
- "mathematics"
- "solve"
- "count"
- Task
- Text Generation
- Library
- transformers
- Type
- mixtral
- License
- mit
- Languages
- multilingual
- Created
- Mar 24, 2024
- Updated
- Mar 25, 2024