LLM Explorer: A Curated Large Language Model Directory and Analytics  // 

Proximus 2x7B V1 by preemware

What open-source LLMs or SLMs are you in search of? 18870 in total.

 ยป  All LLMs  ยป  preemware  ยป  Proximus 2x7B V1   URL Share it on

Anthonylx/prox-mistralhermes-7...   Autotrain compatible Beowolx/mistralhermes-codepro-...   Conversational   Endpoints compatible   Lazymergekit   License:apache-2.0   Merge   Mergekit   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow

Rank the Proximus 2x7B V1 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  
Proximus 2x7B V1 (preemware/Proximus-2x7B-v1)

Best Alternatives to Proximus 2x7B V1

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
LHK DPO V177.6232K / 25.8 GB120515
... TomGrc FusionNet 7Bx2 MoE 13B77.4432K / 25.8 GB344738
LogoS 7Bx2 MoE 13B V0.277.1432K / 25.9 GB23214
DARE TIES 13B77.132K / 25.7 GB6729
13B MATH DPO77.0832K / 25.8 GB9720
MoE 13B DPO77.0532K / 25.8 GB9102
Megatron 2.1 MoE 2x7B76.6432K / 25.8 GB01
MixTAO 7Bx2 MoE Instruct V7.076.5532K / 25.7 GB191612
FusionNet 7Bx2 MoE V0.176.1632K / 25.8 GB12315
...7Bx2 MoE Ko DPO Adapter Attach76.0932K / 25.8 GB2290
Note: green Score (e.g. "73.2") means that the model is better than preemware/Proximus-2x7B-v1.

Proximus 2x7B V1 Parameters and Internals

LLM NameProximus 2x7B V1
RepositoryOpen on ๐Ÿค— 
Model Size12.9b
Required VRAM25.8 GB
Updated2024-02-29
Maintainerpreemware
Model Typemixtral
Model Files  9.9 GB: 1-of-3   10.0 GB: 2-of-3   5.9 GB: 3-of-3
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32002
Initializer Range0.02
Torch Data Typefloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003