AusLegalQA Mixtral 8x7B Instruct V0.1 by adlumal

 ยป  All LLMs  ยป  adlumal  ยป  AusLegalQA Mixtral 8x7B Instruct V0.1   URL Share it on

  Australia   Autotrain compatible   Conversational Dataset:umarbutler/open-austra...   Endpoints compatible   Instruct   Law   Legal   License:apache-2.0   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow

Rank the AusLegalQA Mixtral 8x7B Instruct V0.1 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  
AusLegalQA Mixtral 8x7B Instruct V0.1 (adlumal/AusLegalQA-Mixtral-8x7B-Instruct-v0.1)

Best Alternatives to AusLegalQA Mixtral 8x7B Instruct V0.1

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
Mixtral 8x7B Instruct V0.177.7532K / 93.6 GB5291863945
Mixtral 8x7B Instruct V0.1 FP832K / 47.1 GB2371
...tral 8x7B Instruct V0.1 FP8 V332K / 47.1 GB360
...tral 8x7B Instruct V0.1 FP8 V232K / 47.1 GB110
...tral 8x7B Instruct V0.1 FP8 V132K / 47.1 GB60
Mixtral Instruct ITR 8x7B32K / 91.4 GB11
Maid Yuzu V8 Alter32K / 91.7 GB12
Merge Mixtral Prometheus 8x7B32K / 91.9 GB641
...ELT Mixtral 8x7B Instruct V0.132K / 92 GB23
Yk 8x7b Model V132K / 92 GB3090
Note: green Score (e.g. "73.2") means that the model is better than adlumal/AusLegalQA-Mixtral-8x7B-Instruct-v0.1.

AusLegalQA Mixtral 8x7B Instruct V0.1 Parameters and Internals

LLM NameAusLegalQA Mixtral 8x7B Instruct V0.1
RepositoryOpen on ๐Ÿค— 
Model Size46.7b
Required VRAM43.3 GB
Updated2024-07-07
Maintaineradlumal
Model Typemixtral
Instruction-BasedYes
Model Files  0.9 GB: 1-of-98   0.9 GB: 2-of-98   0.9 GB: 3-of-98   0.9 GB: 4-of-98   0.9 GB: 5-of-98   0.9 GB: 6-of-98   0.9 GB: 7-of-98   0.9 GB: 8-of-98   0.9 GB: 9-of-98   0.9 GB: 10-of-98   0.9 GB: 11-of-98   0.9 GB: 12-of-98   0.9 GB: 13-of-98   0.9 GB: 14-of-98   0.9 GB: 15-of-98   0.9 GB: 16-of-98   0.9 GB: 17-of-98   0.9 GB: 18-of-98   1.0 GB: 19-of-98   1.0 GB: 20-of-98   0.9 GB: 21-of-98   1.0 GB: 22-of-98   1.0 GB: 23-of-98   0.9 GB: 24-of-98   1.0 GB: 25-of-98   1.0 GB: 26-of-98   0.9 GB: 27-of-98   1.0 GB: 28-of-98   1.0 GB: 29-of-98   0.9 GB: 30-of-98   1.0 GB: 31-of-98   1.0 GB: 32-of-98   0.9 GB: 33-of-98   1.0 GB: 34-of-98   1.0 GB: 35-of-98   0.9 GB: 36-of-98   1.0 GB: 37-of-98   1.0 GB: 38-of-98   0.9 GB: 39-of-98   1.0 GB: 40-of-98   1.0 GB: 41-of-98   0.9 GB: 42-of-98   1.0 GB: 43-of-98   1.0 GB: 44-of-98   0.9 GB: 45-of-98   1.0 GB: 46-of-98
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Vocabulary Size32000
Initializer Range0.02
Torch Data Typebfloat16

What open-source LLMs or SLMs are you in search of? 34531 in total.

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