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 AWQ by dannysemi

 »  All LLMs  »  dannysemi  »  Liberated Qwen1.5 72B AWQ   URL Share it on

  19   
  4-bit   Autotrain compatible   Awq   Conversational   Dataset:abacusai/systemchat   Dataset:m-a-p/code-feedback Dataset:m-a-p/codefeedback-fil...   Dataset:teknium/openhermes-2.5   En   Endpoints compatible   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/dannysemi/Liberated-Qwen1.5-72B-awq 

Liberated Qwen1.5 72B AWQ Benchmarks

ARC: 65.7 vs 96.7 (so35)-32.1%
HellaSwag: 84.58 vs 95.3 (gpt4)-11.2%
MMLU: 77.08 vs 88.3 (so35)-12.7%
TruthfulQA: 60.56 vs 59 (gpt4)2.6%
WinoGrande: 83.11 vs 87.5 (gpt4)-5%
GSM8K: 73.62 vs 96.4 (so35)-23.6%
LLME Score: 0.17818
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 AWQ (dannysemi/Liberated-Qwen1.5-72B-awq)

Liberated Qwen1.5 72B AWQ Parameters and Internals

Model Type 
text generation
Additional Notes 
Model is trained to operate over long multiturn conversations without censorship and guardrails.
Training Details 
Data Sources:
teknium/OpenHermes-2.5, m-a-p/Code-Feedback, m-a-p/CodeFeedback-Filtered-Instruction, abacusai/SystemChat
Data Volume:
6000 synthetic conversations
Methodology:
qLoRA, deepspeed zero-2, and Axolotl
Context Length:
8000
Training Time:
3 days
Hardware Used:
8x H100s
Input Output 
Input Format:
ChatML prompt format
Accepted Modalities:
text
Output Format:
JSON object
Performance Tips:
Implement your own alignment layer before exposing the model as a service.
LLM NameLiberated Qwen1.5 72B AWQ
Repository 🤗https://huggingface.co/dannysemi/Liberated-Qwen1.5-72B-awq 
Base Model(s)  abacusai/Liberated-Qwen1.5-72B   abacusai/Liberated-Qwen1.5-72B
Model Size72b
Required VRAM41.3 GB
Updated2025-02-22
Maintainerdannysemi
Model Typeqwen2
Model Files  5.0 GB: 1-of-9   5.0 GB: 2-of-9   5.0 GB: 3-of-9   5.0 GB: 4-of-9   5.0 GB: 5-of-9   5.0 GB: 6-of-9   5.0 GB: 7-of-9   3.8 GB: 8-of-9   2.5 GB: 9-of-9
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Liberated Qwen1.5 72B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Tess V2.5.2 Qwen2 72B AWQ128K / 41.6 GB140
Qwen2.5 72B Instruct AWQ32K / 41.6 GB74072157
Qwen2 72B Instruct AWQ32K / 41.6 GB8295138
Athene V2 Chat AWQ32K / 41.6 GB734
Qwen2 72B Instruct AWQ GEMM32K / 41.6 GB80
Qwen1.5 72B Chat AWQ32K / 41.3 GB54323
Qwen1.5 72B AWQ32K / 41.3 GB111
Typhoon V1.5 72B Instruct AWQ32K / 41.3 GB193
Ao Karasu 72B AWQ 4bit32K / 41.3 GB132
Qwen2 72B Bnb 4bit128K / 41.2 GB1734
Note: green Score (e.g. "73.2") means that the model is better than dannysemi/Liberated-Qwen1.5-72B-awq.

Rank the Liberated Qwen1.5 72B AWQ 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? 43470 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 v20241227
  Support LLM Explorer