LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Instruct Mixtral 8x7B V0.1 Dolly15K AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Instruct Mixtral 8x7B V0.1 Dolly15K AWQ   URL Share it on

  6   
  4-bit   Autotrain compatible   Awq Base model:brillibits/instruct... Base model:quantized:brillibit...   Conversational Dataset:databricks/databricks-...   Instruct   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/Instruct_Mixtral-8x7B-v0.1_Dolly15K-AWQ 

Instruct Mixtral 8x7B V0.1 Dolly15K AWQ Benchmarks

LLME Score: 0.12473
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Instruct Mixtral 8x7B V0.1 Dolly15K AWQ (TheBloke/Instruct_Mixtral-8x7B-v0.1_Dolly15K-AWQ)
🌟 Advertise your project 🚀

Instruct Mixtral 8x7B V0.1 Dolly15K AWQ Parameters and Internals

Model Type 
mixtral
Additional Notes 
The model offers efficient, accurate, and fast low-bit weight quantization methods with AWQ, specifically supporting 4-bit quantization.
Supported Languages 
English (fluent)
Training Details 
Data Sources:
databricks/databricks-dolly-15k
Methodology:
Fine-tuned using QLora
Context Length:
1024
Training Time:
1.0 epochs
Model Architecture:
Llama 2 transformer architecture
Input Output 
Input Format:
{prompt} Output:
Accepted Modalities:
text
Output Format:
Text generation output
Release Notes 
Version:
0.1
Notes:
Initial release of Instruct Mixtral 8X7B V0.1 Dolly15K.
LLM NameInstruct Mixtral 8x7B V0.1 Dolly15K AWQ
Repository 🤗https://huggingface.co/TheBloke/Instruct_Mixtral-8x7B-v0.1_Dolly15K-AWQ 
Model NameInstruct Mixtral 8X7B V0.1 Dolly15K
Model CreatorBrillibits
Base Model(s)  Brillibits/Instruct_Mixtral-8x7B-v0.1_Dolly15K   Brillibits/Instruct_Mixtral-8x7B-v0.1_Dolly15K
Model Size6.5b
Required VRAM24.7 GB
Updated2025-09-23
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
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Instruct Mixtral 8x7B V0.1 Dolly15K AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB1181458
Dolphin 2.7 Mixtral 8x7b AWQ32K / 24.7 GB736323
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB60
Mixtral Instruct AWQ32K / 24.7 GB175043
...xtral Instruct AWQ Clone Dec2332K / 24.7 GB60
...0.1 LimaRP ZLoss DARE TIES AWQ32K / 24.7 GB73
...Instruct V0.1 LimaRP ZLoss AWQ32K / 24.7 GB141
Dolphin 2.5 Mixtral 8x7b AWQ32K / 24.7 GB616
Dolphin 2.6 Mixtral 8x7b AWQ32K / 24.7 GB912
...1 Mixtral 8x7b Instruct V3 AWQ32K / 24.7 GB61
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Instruct_Mixtral-8x7B-v0.1_Dolly15K-AWQ.

Rank the Instruct Mixtral 8x7B V0.1 Dolly15K AWQ Capabilities

🆘 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! 🌟

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? 51623 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer