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

Opus V1.2 7B by dreamgen

 »  All LLMs  »  dreamgen  »  Opus V1.2 7B   URL Share it on

  51   
  Autotrain compatible   Axolotl   Conversational   En   Endpoints compatible   Instruct   Mistral   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/dreamgen/opus-v1.2-7b 

Opus V1.2 7B Benchmarks

ARC: 58.45 vs 96.7 (so35)-39.6%
HellaSwag: 82.55 vs 95.3 (gpt4)-13.4%
MMLU: 61.79 vs 88.3 (so35)-30%
TruthfulQA: 60.27 vs 59 (gpt4)2.2%
WinoGrande: 77.11 vs 87.5 (gpt4)-11.9%
GSM8K: 40.56 vs 96.4 (so35)-57.9%
LLME Score: 0.15607
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Opus V1.2 7B (dreamgen/opus-v1.2-7b)
🌟 Advertise your project 🚀

Opus V1.2 7B Parameters and Internals

Model Type 
text generation, story-writing, role-playing
Use Cases 
Areas:
story-writing, role-playing
Applications:
steerable story-writing, role-playing, writing-assistance
Primary Use Cases:
story-writing, role-playing
Training Details 
Data Volume:
~100M tokens
Context Length:
31000
Input Output 
Input Format:
Extended version of ChatML
LLM NameOpus V1.2 7B
Repository 🤗https://huggingface.co/dreamgen/opus-v1.2-7b 
Model Size7b
Required VRAM14.4 GB
Updated2025-09-23
Maintainerdreamgen
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3   4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-nd-4.0
Context Length32768
Model Max Length32768
Transformers Version4.38.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32002
Torch Data Typebfloat16

Quantized Models of the Opus V1.2 7B

Model
Likes
Downloads
VRAM
... Opus V1.2 7B AWQ 4bit Smashed054 GB
Opus V1.2 7B AWQ074 GB

Best Alternatives to Opus V1.2 7B

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB14118
SpydazWeb AI HumanAI RP512K / 14.4 GB171
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB60
...1 Summarize 64K LoRANET Merged128K / 14.4 GB60
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB1533091797
Seed X Instruct 7B32K / 15 GB1510123
Mixtral AI CyberCoder32K / 14.3 GB00
Note: green Score (e.g. "73.2") means that the model is better than dreamgen/opus-v1.2-7b.

Rank the Opus V1.2 7B 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? 51547 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