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

Prometheus 7B V2.0 GPTQ by thesven

 »  All LLMs  »  thesven  »  Prometheus 7B V2.0 GPTQ   URL Share it on

  9   

Prometheus 7B V2.0 GPTQ is an open-source language model by thesven. Features: 7b LLM, VRAM: 4.2GB, Context: 32K, License: apache-2.0, Quantized, LLM Explorer Score: 0.14.

  Arxiv:2310.08491   Arxiv:2405.01535   4-bit   Autotrain compatible   Conversational Dataset:prometheus-eval/feedba... Dataset:prometheus-eval/prefer...   En   Endpoints compatible   Gptq   Mistral   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/thesven/prometheus-7b-v2.0-GPTQ 

Prometheus 7B V2.0 GPTQ Benchmarks

LLME Score: 0.13712
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 GPTQ (thesven/prometheus-7b-v2.0-GPTQ)
🌟 Advertise your project 🚀

Prometheus 7B V2.0 GPTQ Parameters and Internals

Model Type 
Language model, text2text-generation
Use Cases 
Areas:
Research, Evaluation of Language Models
Applications:
Fine-grained evaluation of LLM, Reward model for Reinforcement Learning from Human Feedback (RLHF)
Primary Use Cases:
Absolute grading, Relative grading
Supported Languages 
en (high)
Training Details 
Data Sources:
Feedback-Collection, Preference-Collection
Data Volume:
100K feedback for Feedback Collection and 200K feedback for Preference Collection
Methodology:
Fine-tuned and weight merging
Model Architecture:
GPTQ 4 bit version
Input Output 
Input Format:
An instruction, a response, a score rubric, and a reference answer for Absolute Grading; An instruction, 2 responses, a score rubric, and a reference answer for Relative Grading.
Accepted Modalities:
Text
Output Format:
Feedback and score decision divided by a separating phrase [RESULT]
Performance Tips:
Use the provided conversation template to avoid unexpected behaviors.
LLM NamePrometheus 7B V2.0 GPTQ
Repository 🤗https://huggingface.co/thesven/prometheus-7b-v2.0-GPTQ 
Base Model(s)  prometheus-eval/prometheus-7b-v2.0   prometheus-eval/prometheus-7b-v2.0
Model Size7b
Required VRAM4.2 GB
Updated2025-09-23
Maintainerthesven
Model Typemistral
Model Files  4.2 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.42.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Prometheus 7B V2.0 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...enHermes 2.5 Mistral 7B Marlin32K / 4.1 GB142
Zephyr 7B Beta Marlin32K / 4.1 GB370
Mistral 7B Instruct V0.3 GPTQ32K / 4.2 GB629091
Mistral 7B Instruct V0.2 GPTQ32K / 4.2 GB4736054
...ral 7B Instruct V0.3 GPTQ 4bit32K / 4.2 GB572323
...ral 7B Instruct V0.3 GPTQ 4bit32K / 4.2 GB294618
...istral 7B Pruned50 GPTQ Marlin32K / 4 GB60
Mistral 7B Unsloth Gptq 8bit32K / 7.7 GB70
Cosmosage V232K / 4.2 GB84
...phyr 7B Beta Assistant V1 Gptq32K / 4.2 GB11
Note: green Score (e.g. "73.2") means that the model is better than thesven/prometheus-7b-v2.0-GPTQ.

Rank the Prometheus 7B V2.0 GPTQ 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer