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

Casperhansen Mixtral Instruct AWQ Clone Feb24 by RivatLabs

What open-source LLMs or SLMs are you in search of? 18857 in total.

  4-bit   Autotrain compatible   Awq   Conversational   Endpoints compatible   Instruct   License:apache-2.0   Mixtral   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Rank the Casperhansen Mixtral Instruct AWQ Clone Feb24 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  
Casperhansen Mixtral Instruct AWQ Clone Feb24 (RivatLabs/casperhansen-mixtral-instruct-awq-clone-feb24)

Best Alternatives to Casperhansen Mixtral Instruct AWQ Clone Feb24

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
...utLM Mixtral 8x7B Instruct AWQ63.832K / 24.7 GB7342
Mixtral 8x7B Instruct V0.1 AWQ63.732K / 24.7 GB2271041
Mixtral 8x7B Instruct V0.1 AWQ63.732K / 24.7 GB2740
...Mixtral 8x7B V0.1 Dolly15K AWQ63.532K / 24.7 GB421
Mixtral Instruct AWQ32K / 24.7 GB1020330
Dolphin 2.7 Mixtral 8x7b AWQ32K / 24.7 GB856916
Dolphin 2.6 Mixtral 8x7b AWQ32K / 24.7 GB41812
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB36626
Dolphin 2.5 Mixtral 8x7b AWQ32K / 24.7 GB4475
...0.1 LimaRP ZLoss DARE TIES AWQ32K / 24.7 GB943
Note: green Score (e.g. "73.2") means that the model is better than RivatLabs/casperhansen-mixtral-instruct-awq-clone-feb24.

Casperhansen Mixtral Instruct AWQ Clone Feb24 Parameters and Internals

LLM NameCasperhansen Mixtral Instruct AWQ Clone Feb24
RepositoryOpen on ๐Ÿค— 
Model Size6.5b
Required VRAM24.7 GB
Updated2024-02-28
MaintainerRivatLabs
Model Typemixtral
Instruction-BasedYes
Model Files  10.0 GB: 1-of-3   10.0 GB: 2-of-3   4.7 GB: 3-of-3
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Initializer Range0.02
Torch Data Typefloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003