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

Midnight Rose 70B V2.0.3 GPTQ by sambarnes

 »  All LLMs  »  sambarnes  »  Midnight Rose 70B V2.0.3 GPTQ   URL Share it on

  9   
  4-bit   4bit   Autotrain compatible Base model:quantized:sophosymp... Base model:sophosympatheia/mid...   En   Endpoints compatible   Gptq   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/sambarnes/Midnight-Rose-70B-v2.0.3-GPTQ 

Midnight Rose 70B V2.0.3 GPTQ Benchmarks

LLME Score: 0.14331
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Midnight Rose 70B V2.0.3 GPTQ (sambarnes/Midnight-Rose-70B-v2.0.3-GPTQ)
🌟 Advertise your project 🚀

Midnight Rose 70B V2.0.3 GPTQ Parameters and Internals

Model Type 
quantized
Additional Notes 
A second attempt at quantizing a pre-trained model with AutoGPTQ using a VMWare calibration dataset. Quantization took ~1.5hrs costing roughly .
Supported Languages 
en (Proficient)
Training Details 
Data Sources:
https://huggingface.co/datasets/VMware/open-instruct
Methodology:
Quantization with AutoGPTQ
Hardware Used:
H100 on modal.com
LLM NameMidnight Rose 70B V2.0.3 GPTQ
Repository 🤗https://huggingface.co/sambarnes/Midnight-Rose-70B-v2.0.3-GPTQ 
Model NameMidnight Rose 70B v2.0.3
Model Creatorsophosympatheia
Base Model(s)  sophosympatheia/Midnight-Rose-70B-v2.0.3   sophosympatheia/Midnight-Rose-70B-v2.0.3
Model Size70b
Required VRAM35.3 GB
Updated2025-09-21
Maintainersambarnes
Model Typellama
Model Files  35.3 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Midnight Rose 70B V2.0.3 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB12776
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB10380
...ama 3.1 70B Instruct Gptq 4bit128K / 39.9 GB284
Opus V1.2 70B Marlin32K / 36.4 GB50
MoMo 70B Lora 1.8.4 DPO GPTQ32K / 41.3 GB81
MoMo 70B Lora 1.8.6 DPO GPTQ32K / 41.3 GB51
Midnight Miqu 70B V1.5 GPTQ32G31K / 40.7 GB1894
Tess 70B V1.6 Marlin31K / 36.3 GB71
...Midnight Miqu 70B V1.0 GPTQ32G31K / 40.7 GB72
Senku 70B GPTQ 4bit31K / 36.7 GB61
Note: green Score (e.g. "73.2") means that the model is better than sambarnes/Midnight-Rose-70B-v2.0.3-GPTQ.

Rank the Midnight Rose 70B V2.0.3 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? 51507 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