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

Liberated Qwen1.5 72B EXL2 3.5bpw by JackCloudman

 »  All LLMs  »  JackCloudman  »  Liberated Qwen1.5 72B EXL2 3.5bpw   URL Share it on

  3   
  Autotrain compatible   Conversational   Dataset:abacusai/systemchat   Dataset:m-a-p/code-feedback Dataset:m-a-p/codefeedback-fil...   Dataset:teknium/openhermes-2.5   En   Endpoints compatible   Exl2   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/JackCloudman/Liberated-Qwen1.5-72B-exl2-3.5bpw 

Liberated Qwen1.5 72B EXL2 3.5bpw Benchmarks

LLME Score: 0.14268
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Liberated Qwen1.5 72B EXL2 3.5bpw (JackCloudman/Liberated-Qwen1.5-72B-exl2-3.5bpw)
🌟 Advertise your project 🚀

Liberated Qwen1.5 72B EXL2 3.5bpw Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, commercial applications
Limitations:
No guardrails or censorship
Considerations:
You are advised to implement your own alignment layer before exposing the model as a service.
Additional Notes 
Future releases will focus on mixing this dataset with datasets used to train Smaug to combine properties of both models.
Training Details 
Data Sources:
teknium/OpenHermes-2.5, m-a-p/Code-Feedback, m-a-p/CodeFeedback-Filtered-Instruction, abacusai/SystemChat
Methodology:
It took 3 days to train 3 epochs on 8x H100s using qLoRA, deepspeed zero-2, and Axolotl. learning rate 2e-4.
Context Length:
8000
Training Time:
3 days
Hardware Used:
8x H100 GPUs
Model Architecture:
Based on Qwen1.5 with sequence length fine-tuning
Input Output 
Input Format:
ChatML prompt format
Output Format:
JSON object
LLM NameLiberated Qwen1.5 72B EXL2 3.5bpw
Repository 🤗https://huggingface.co/JackCloudman/Liberated-Qwen1.5-72B-exl2-3.5bpw 
Model Size72b
Required VRAM34.1 GB
Updated2025-07-28
MaintainerJackCloudman
Model Typeqwen2
Model Files  8.6 GB: 1-of-4   8.6 GB: 2-of-4   8.6 GB: 3-of-4   8.3 GB: 4-of-4
Supported Languagesen
Quantization Typeexl2
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.39.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Liberated Qwen1.5 72B EXL2 3.5bpw

Best Alternatives
Context / RAM
Downloads
Likes
Kimi Dev 72B 4bit DWQ128K / 40.9 GB195918
Kimi Dev 72B 8bit128K / 77.1 GB11462
Kimi Dev 72B 5bit128K / 50.1 GB973
Qwen2 72B Bnb 4bit128K / 41.2 GB15954
...in 2.9.2 Qwen2 72B 6.0bpw EXL2128K / 56.1 GB31
...Qwen2 72B 4 0bpw H6 EXL2 Pippa128K / 38.6 GB51
...phin 292 Qwen2 72b EXL2 4 0bpw128K / 38.6 GB41
...n 2.9.2 Qwen72b 8.0bpw H8 EXL2128K / 66.8 GB82
Qwen2 72B 4bit128K / 40.9 GB50
...B Instruct 2.0bpw H Novel EXL2125K / 23 GB41
Note: green Score (e.g. "73.2") means that the model is better than JackCloudman/Liberated-Qwen1.5-72B-exl2-3.5bpw.

Rank the Liberated Qwen1.5 72B EXL2 3.5bpw 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? 51368 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