Arxiv Assistant Merged Peft Model by amrachraf

 ยป  All LLMs  ยป  amrachraf  ยป  Arxiv Assistant Merged Peft Model   URL Share it on

  Merged Model   Arxiv:1910.09700   Autotrain compatible   Conversational   Endpoints compatible   Instruct   Mistral   Region:us   Safetensors   Sharded   Tensorflow

Rank the Arxiv Assistant Merged Peft Model 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  
Arxiv Assistant Merged Peft Model (amrachraf/arxiv-assistant-merged_peft_model)

Best Alternatives to Arxiv Assistant Merged Peft Model

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
Calme 7B Instruct V0.376.532K / 14.4 GB14435
Mistral CatMacaroni Slerp 7B69.0832K / 14.5 GB4310
Neural Una Cybertron 7B69.0532K / 14.4 GB4702
Pic 7B Mistral Full V0.268.7232K / 15 GB8759
Mixtral Instruct67.0732K / 14.4 GB13280
Mistral Turkish65.6332K / 14.4 GB4376
...dusa2 Mistral 7B Instruct V0.265.4632K / 15.9 GB16080
Tiger 7B V0.165.0232K / 14.5 GB15997
Gabriel 7B Instruct V0.264.9732K / 14.4 GB4481
Hermes Instruct 7B 100K64.9632K / 14.4 GB15212
Note: green Score (e.g. "73.2") means that the model is better than amrachraf/arxiv-assistant-merged_peft_model.

Arxiv Assistant Merged Peft Model Parameters and Internals

LLM NameArxiv Assistant Merged Peft Model
RepositoryOpen on ๐Ÿค— 
Merged ModelYes
Model Size7b
Required VRAM28.9 GB
Updated2024-06-24
Maintaineramrachraf
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-6   4.9 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   4.8 GB: 5-of-6   4.2 GB: 6-of-6
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.42.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Initializer Range0.02
Torch Data Typefloat32

What open-source LLMs or SLMs are you in search of? 34902 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801