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

Notus 7B V1 AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Notus 7B V1 AWQ   URL Share it on

  56   
  4-bit   Autotrain compatible   Awq   Base model:argilla/notus-7b-v1 Base model:quantized:argilla/n...   Conversational Dataset:argilla/ultrafeedback-...   Dpo   En   Mistral   Model-index   Preference   Quantized   Region:us   Rlaif   Safetensors   Ultrafeedback
Model Card on HF 🤗: https://huggingface.co/TheBloke/notus-7B-v1-AWQ 

Notus 7B V1 AWQ Benchmarks

LLME Score: 0.15885
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Notus 7B V1 AWQ (TheBloke/notus-7B-v1-AWQ)

Notus 7B V1 AWQ Parameters and Internals

Model Type 
GPT-like, 7B, DPO fine-tuned
Use Cases 
Areas:
assistant applications, chat-like applications
Additional Notes 
Using preference ratings, instead of critiques scores, led to a new dataset with better outcomes.
Supported Languages 
en (Proficient)
Training Details 
Data Sources:
openbmb/UltraFeedback, argilla/ultrafeedback-binarized-preferences
Methodology:
Direct Preference Optimization (DPO)
Hardware Used:
VM with 8 x A100 40GB
Model Architecture:
fine-tuned with DPO over zephyr-7b-sft-full
Input Output 
Input Format:
<|system|> ~~ <|user|> {prompt}~~ <|assistant|>
Accepted Modalities:
text
LLM NameNotus 7B V1 AWQ
Repository 🤗https://huggingface.co/TheBloke/notus-7B-v1-AWQ 
Model NameNotus 7B v1
Model CreatorArgilla
Base Model(s)  Notus 7B V1   argilla/notus-7b-v1
Model Size7b
Required VRAM4.2 GB
Updated2024-12-22
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMistralForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Notus 7B V1 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB100
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB634062
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB9815741
Mistral 7B Instruct V0.1 AWQ32K / 4.2 GB17633437
Ghost 7B Alpha AWQ32K / 4.2 GB160
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB3481
Breeze 7B Instruct V1.0 AWQ32K / 4.6 GB250
...reeze 7B 32K Instruct V1.0 AWQ32K / 4.7 GB90
Mahou 1.3a Mistral 7B AWQ32K / 4.2 GB111
Tess 7B V2.0 AWQ32K / 4.2 GB181
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/notus-7B-v1-AWQ.

Rank the Notus 7B V1 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? 40066 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 v20241217
  Support LLM Explorer