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

Starling LM 7B Beta by Nexusflow

 »  All LLMs  »  Nexusflow  »  Starling LM 7B Beta   URL Share it on

  1713   

Starling LM 7B Beta is an open-source language model by Nexusflow. Features: 7b LLM, VRAM: 14.4GB, Context: 8K, License: apache-2.0, LLM Explorer Score: 0.27, ELO: 1134, Arc: 67.2, HellaSwag: 83.5, MMLU: 65.1, GSM8K: 66.6.

  Arxiv:1909.08593   Conversational   Dataset:berkeley-nest/nectar   Deploy:azure   En   Endpoints compatible   Mistral   Region:us   Reward model   Rlaif   Rlhf   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Nexusflow/Starling-LM-7B-beta 

Starling LM 7B Beta Benchmarks

LMSys ELO: 1134 vs 1272 (so35)-10.8%
LLME Score: 0.27118
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 Beta (Nexusflow/Starling-LM-7B-beta)

Starling LM 7B Beta Parameters and Internals

Model Type 
Language Model, finetuned with RLHF / RLAIF
Use Cases 
Considerations:
Please use the provided chat template to ensure optimal performance. The model can occasionally produce verbose outputs. Setting temperature to 0 can mitigate verbosity.
Additional Notes 
The model is hosted on LMSYS Chatbot Arena for free testing.
Supported Languages 
en (Proficient)
Training Details 
Data Sources:
berkeley-nest/Nectar
Methodology:
Trained by Reinforcement Learning from AI Feedback (RLAIF) with policy optimization method PPO.
Input Output 
Input Format:
Chat templates following Openchat-3.5-0106.
Accepted Modalities:
text
Output Format:
Text output based on input templates.
Performance Tips:
Follow the exact chat template for improved performance.
LLM NameStarling LM 7B Beta
Repository 🤗https://huggingface.co/Nexusflow/Starling-LM-7B-beta 
Model Size7b
Required VRAM14.4 GB
Updated2026-05-28
MaintainerNexusflow
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.37.1
Tokenizer ClassLlamaTokenizer
Padding Token<|end_of_turn|>
Vocabulary Size32002
Torch Data Typebfloat16

Quantized Models of the Starling LM 7B Beta

Model
Likes
Downloads
VRAM
Starling LM 7B Beta 4bit4444 GB
Starling LM 7B Beta 8bit277 GB
Starling LM 7B Beta AWQ3734 GB
Starling LM 7B Beta GPTQ424 GB

Best Alternatives to Starling LM 7B Beta

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB22020
MegaBeam Mistral 7B 512K512K / 14.4 GB819454
SpydazWeb AI HumanAI RP512K / 14.4 GB111
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB377916
MegaBeam Mistral 7B 300K282K / 14.4 GB804617
Hebrew Mistral 7B 200K256K / 30 GB2215
Astral 256K 7B250K / 14.4 GB90
Astral 256K 7B V2250K / 14.4 GB80

Rank the Starling LM 7B Beta 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? 55446 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer