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

Qwen1.5 1.8B Chat AWQ by Qwen

 »  All LLMs  »  Qwen  »  Qwen1.5 1.8B Chat AWQ   URL Share it on

  121   
  Arxiv:2309.16609   4-bit   Autotrain compatible   Awq   Chat   Conversational   En   Endpoints compatible   Quantized   Qwen2   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat-AWQ 

Qwen1.5 1.8B Chat AWQ Benchmarks

ARC: 38.74 vs 96.7 (so35)-59.9%
HellaSwag: 60.02 vs 95.3 (gpt4)-37%
MMLU: 45.87 vs 88.3 (so35)-48.1%
TruthfulQA: 40.62 vs 59 (gpt4)-31.2%
WinoGrande: 59.67 vs 87.5 (gpt4)-31.8%
GSM8K: 19.03 vs 96.4 (so35)-80.3%
LLME Score: 0.18531
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Qwen1.5 1.8B Chat AWQ Parameters and Internals

Model Type 
transformer-based, decoder-only, language model
Training Details 
Methodology:
pretrained on a large amount of data using both supervised finetuning and direct preference optimization
Context Length:
32000
Model Architecture:
Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention
LLM NameQwen1.5 1.8B Chat AWQ
Repository 🤗https://huggingface.co/Qwen/Qwen1.5-1.8B-Chat-AWQ 
Base Model(s)  deltawi/Qwen-1.5-1.8B-SQL   deltawi/Qwen-1.5-1.8B-SQL
Model Size1.8b
Required VRAM1.9 GB
Updated2025-06-09
MaintainerQwen
Model Typeqwen2
Model Files  1.9 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.37.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace
Qwen1.5 1.8B Chat AWQ (Qwen/Qwen1.5-1.8B-Chat-AWQ)

Best Alternatives to Qwen1.5 1.8B Chat AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Qwen1.5 1.8B AWQ W4 G12832K / 1.9 GB290
Qwen1.5 1.8B Chat 4bit32K / 1.5 GB432
Nano Q232K / 3.5 GB130
Dhanishtha128K / 3.5 GB822
LaConfiance PRYMMAL ECE TW3128K / 7.1 GB100
Qwen1.5 1.8B Chat32K / 3.7 GB6154851
Qwen1.5 1.8B32K / 3.7 GB3473150
Qwen1.5 1.8B Chat GGUF32K / 0.9 GB1751572
MiniPLM Qwen 200M32K / 0.8 GB5715
Qwen1.5 1.8B Seed Sft32K / 3.7 GB160
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen1.5-1.8B-Chat-AWQ.

Rank the Qwen1.5 1.8B Chat 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? 48046 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