Mistral V0.3 13B 32K Base V1 by win10

 ยป  All LLMs  ยป  win10  ยป  Mistral V0.3 13B 32K Base V1   URL Share it on

  Merged Model   Autotrain compatible   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow   Win10/breeze-13b-32k-base-v1 0 Win10/mistral-v0.3-13b-32k-bas...

Mistral V0.3 13B 32K Base V1 Benchmarks

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

Mistral V0.3 13B 32K Base V1 Parameters and Internals

LLM NameMistral V0.3 13B 32K Base V1
Repository ๐Ÿค—https://huggingface.co/win10/Mistral-v0.3-13B-32k-Base-v1 
Merged ModelYes
Model Size13b
Required VRAM25.2 GB
Updated2024-09-06
Maintainerwin10
Model Typemistral
Model Files  1.0 GB: 1-of-26   0.9 GB: 2-of-26   1.0 GB: 3-of-26   1.0 GB: 4-of-26   1.0 GB: 5-of-26   0.9 GB: 6-of-26   1.0 GB: 7-of-26   1.0 GB: 8-of-26   1.0 GB: 9-of-26   1.0 GB: 10-of-26   1.0 GB: 11-of-26   1.0 GB: 12-of-26   1.0 GB: 13-of-26   1.0 GB: 14-of-26   1.0 GB: 15-of-26   1.0 GB: 16-of-26   1.0 GB: 17-of-26   0.9 GB: 18-of-26   1.0 GB: 19-of-26   1.0 GB: 20-of-26   1.0 GB: 21-of-26   1.0 GB: 22-of-26   1.0 GB: 23-of-26   1.0 GB: 24-of-26   1.0 GB: 25-of-26   0.5 GB: 26-of-26   0.5 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   0.9 GB   0.9 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB   1.0 GB
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.2
Vocabulary Size32768
Torch Data Typebfloat16
Mistral V0.3 13B 32K Base V1 (win10/Mistral-v0.3-13B-32k-Base-v1)

Best Alternatives to Mistral V0.3 13B 32K Base V1

Best Alternatives
Context / RAM
Downloads
Likes
LuminRP 13B 128K V0.5128K / 25.1 GB62
Breeze 13B 32K Instruct V1.032K / 25.6 GB110
Power WizardLM 2 13B32K / 25 GB92
Breeze 13B 32K Base V1.032K / 25.6 GB60
Pandora 13B V132K / 24.9 GB6750
Pandora V1 13B32K / 24.9 GB103
BigMistral 13B GLUED32K / 26.6 GB81
BigMistral 13B32K / 26.7 GB82
...stral 13B DARE Blended FAILURE32K / 26.7 GB80
...stral 13B DARE Blended FAILURE32K / 26.7 GB80
Note: green Score (e.g. "73.2") means that the model is better than win10/Mistral-v0.3-13B-32k-Base-v1.

Rank the Mistral V0.3 13B 32K Base 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  

What open-source LLMs or SLMs are you in search of? 35693 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803