SauerkrautLM Mixtral 8x7B Instruct AWQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  SauerkrautLM Mixtral 8x7B Instruct AWQ   URL Share it on

  4-bit   Augmentation   Autotrain compatible   Awq Base model:quantized:vagosolut... Base model:vagosolutions/sauer...   Conversational Dataset:argilla/distilabel-mat...   De   Dpo   En   Es   Finetuned   Fr   German   Instruct   It   Mistral   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow

SauerkrautLM Mixtral 8x7B Instruct AWQ Benchmarks

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

SauerkrautLM Mixtral 8x7B Instruct AWQ Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Applications:
business, text augmentation, language translation
Primary Use Cases:
text generation, instruction following
Limitations:
Does not guarantee consistently appropriate behavior
Additional Notes 
AWQ is an efficient, low-bit weight quantization method for fast inference. Consider using GGUF models for macOS.
Supported Languages 
en (proficient), de (proficient), fr (proficient), it (proficient), es (proficient)
Training Details 
Data Sources:
argilla/distilabel-math-preference-dpo, SauerkrautLM-7b-HerO, HuggingFaceH4/ultrafeedback_binarized
Data Volume:
Not specified
Methodology:
Mixture of Experts (MoE) Model
Context Length:
8192
Training Time:
Not specified
Model Architecture:
Based on Mixtral-8x7B-Instruct
Input Output 
Input Format:
[INST] {prompt} [/INST]
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Ensure latest version of text-generation-webui is used.
LLM NameSauerkrautLM Mixtral 8x7B Instruct AWQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/SauerkrautLM-Mixtral-8x7B-Instruct-AWQ 
Model NameSauerkrautLM Mixtral 8X7B Instruct
Model CreatorVAGO solutions
Base Model(s)  ...rkrautLM Mixtral 8x7B Instruct   VAGOsolutions/SauerkrautLM-Mixtral-8x7B-Instruct
Model Size6.5b
Required VRAM24.7 GB
Updated2024-11-22
MaintainerTheBloke
Model Typemixtral
Instruction-BasedYes
Model Files  10.0 GB: 1-of-3   10.0 GB: 2-of-3   4.7 GB: 3-of-3
Supported Languagesen de fr it es
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16
SauerkrautLM Mixtral 8x7B Instruct AWQ (TheBloke/SauerkrautLM-Mixtral-8x7B-Instruct-AWQ)

Best Alternatives to SauerkrautLM Mixtral 8x7B Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral Instruct AWQ32K / 24.7 GB1058043
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB170
Dolphin 2.7 Mixtral 8x7b AWQ32K / 24.7 GB252221
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB87658
...xtral Instruct AWQ Clone Dec2332K / 24.7 GB70
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB41815
...ixtral Instruct 8x7b Zloss AWQ32K / 24.7 GB132
...0.1 LimaRP ZLoss DARE TIES AWQ32K / 24.7 GB133
...Instruct V0.1 LimaRP ZLoss AWQ32K / 24.7 GB101
Dolphin 2.6 Mixtral 8x7b AWQ32K / 24.7 GB3613
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/SauerkrautLM-Mixtral-8x7B-Instruct-AWQ.

Rank the SauerkrautLM Mixtral 8x7B Instruct AWQ 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? 38200 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110