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

Prometheus 7B V2.0 by prometheus-eval

 »  All LLMs  »  prometheus-eval  »  Prometheus 7B V2.0   URL Share it on

  23049   
  Arxiv:2310.08491   Arxiv:2405.01535   Autotrain compatible Dataset:prometheus-eval/feedba... Dataset:prometheus-eval/prefer...   En   Endpoints compatible   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/prometheus-eval/prometheus-7b-v2.0 

Prometheus 7B V2.0 Benchmarks

LLME Score: 0.24203
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Prometheus 7B V2.0 (prometheus-eval/prometheus-7b-v2.0)

Prometheus 7B V2.0 Parameters and Internals

Model Type 
Language model
Use Cases 
Areas:
Research
Additional Notes 
Prometheus 2 is an alternative to GPT-4 evaluation for fine-grained evaluation of underlying LLM & Reward model.
Supported Languages 
en (NLP based)
Training Details 
Data Sources:
Feedback Collection, Preference Collection
Data Volume:
100K feedback within Feedback Collection and 200K feedback within Preference Collection
Methodology:
Fine-tuning, weight merging
Model Architecture:
Language model architecture with base Mistral-Instruct
Input Output 
Input Format:
Different prompt formats for absolute and relative grading
Output Format:
Feedback and score decision separated by [RESULT] phrase
LLM NamePrometheus 7B V2.0
Repository 🤗https://huggingface.co/prometheus-eval/prometheus-7b-v2.0 
Model Size7b
Required VRAM14.4 GB
Updated2024-12-06
Maintainerprometheus-eval
Model Typemistral
Model Files  2.0 GB: 1-of-8   1.9 GB: 2-of-8   2.0 GB: 3-of-8   2.0 GB: 4-of-8   1.9 GB: 5-of-8   1.9 GB: 6-of-8   1.9 GB: 7-of-8   0.8 GB: 8-of-8
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the Prometheus 7B V2.0

Model
Likes
Downloads
VRAM
Prometheus 7B V2.0 GPTQ0394 GB

Best Alternatives to Prometheus 7B V2.0

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB27549
MegaBeam Mistral 7B 512K512K / 14.4 GB1502344
SpydazWeb AI HumanAI RP512K / 14.4 GB331
SpydazWeb AI HumanAI 002512K / 14.4 GB141
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB333915
Hebrew Mistral 7B 200K256K / 30 GB340415
Astral 256K 7B V2250K / 14.4 GB140
Astral 256K 7B250K / 14.4 GB120
Boptruth Agatha 7B128K / 14.4 GB6770
Note: green Score (e.g. "73.2") means that the model is better than prometheus-eval/prometheus-7b-v2.0.

Rank the Prometheus 7B V2.0 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? 38920 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