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

Starling LM 7B Alpha AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Starling LM 7B Alpha AWQ   URL Share it on

  120   
  Arxiv:2306.02231   4-bit   Autotrain compatible   Awq Base model:berkeley-nest/starl... Base model:quantized:berkeley-...   Conversational   Dataset:berkeley-nest/nectar   En   Mistral   Quantized   Region:us   Reward model   Rlaif   Rlhf   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Starling-LM-7B-alpha-AWQ 

Starling LM 7B Alpha AWQ Benchmarks

LLME Score: 0.16044
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Starling LM 7B Alpha AWQ (TheBloke/Starling-LM-7B-alpha-AWQ)

Starling LM 7B Alpha AWQ Parameters and Internals

Model Type 
mistral, language model, reward model, RLHF, RLAIF
Use Cases 
Primary Use Cases:
Language modeling, Chatbot applications
Limitations:
Non-commercial use only
Additional Notes 
Compatible with text-generation-webui using Loader: AutoAWQ. Starling-7B-alpha scores well in multiple performance benchmarks including MT Bench.
Supported Languages 
en (proficient)
Training Details 
Data Sources:
berkeley-nest/Nectar, openchat/openchat_3.5
Methodology:
Advantage-induced policy alignment (APA), C-RLFT, RLHF/RLAIF
Context Length:
4096
Model Architecture:
Derived from Mistral-7B-v0.1
Input Output 
Input Format:
GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:
Accepted Modalities:
text
Output Format:
Text
Performance Tips:
Make sure to use the latest versions of compatibility software for optimal performance.
LLM NameStarling LM 7B Alpha AWQ
Repository 🤗https://huggingface.co/TheBloke/Starling-LM-7B-alpha-AWQ 
Model NameStarling LM 7B Alpha
Model CreatorBerkeley-Nest
Base Model(s)  Starling LM 7B Alpha   berkeley-nest/Starling-LM-7B-alpha
Model Size7b
Required VRAM4.2 GB
Updated2024-12-21
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length8192
Model Max Length8192
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token<|end_of_turn|>
Vocabulary Size32002
Torch Data Typefloat16

Best Alternatives to Starling LM 7B Alpha AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB100
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB698312
Mistral 7B Instruct V0.2 AWQ32K / 4.2 GB9935741
Mistral 7B Instruct V0.1 AWQ32K / 4.2 GB17688237
Ghost 7B Alpha AWQ32K / 4.2 GB160
Mistral 7B Instruct V0.3 AWQ32K / 4.2 GB3291
Breeze 7B Instruct V1.0 AWQ32K / 4.6 GB240
...reeze 7B 32K Instruct V1.0 AWQ32K / 4.7 GB90
Mahou 1.3a Mistral 7B AWQ32K / 4.2 GB101
Tess 7B V2.0 AWQ32K / 4.2 GB181
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Starling-LM-7B-alpha-AWQ.

Rank the Starling LM 7B Alpha 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? 40013 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