Qwen2 7B Instruct GPTQ Int4 by Qwen

 ยป  All LLMs  ยป  Qwen  ยป  Qwen2 7B Instruct GPTQ Int4   URL Share it on

  Arxiv:2309.00071   4-bit   Autotrain compatible Base model:quantized:qwen/qwen... Base model:qwen/qwen2-7b-instr...   Chat   Conversational   En   Endpoints compatible   Gptq   Instruct   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow

Qwen2 7B Instruct GPTQ Int4 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2 7B Instruct GPTQ Int4 (Qwen/Qwen2-7B-Instruct-GPTQ-Int4)

Qwen2 7B Instruct GPTQ Int4 Parameters and Internals

Model Type 
text generation, instruction-tuned
Additional Notes 
For processing long texts exceeding 32,768 tokens, the model uses YARN for enhancing model length extrapolation.
Supported Languages 
en (English)
Training Details 
Methodology:
Pretrained with a large amount of data, post-trained with both supervised finetuning and direct preference optimization.
Context Length:
131072
Model Architecture:
Transformer architecture with SwiGLU activation, attention QKV bias, group query attention.
LLM NameQwen2 7B Instruct GPTQ Int4
Repository ๐Ÿค—https://huggingface.co/Qwen/Qwen2-7B-Instruct-GPTQ-Int4 
Base Model(s)  Qwen2 7B Instruct   Qwen/Qwen2-7B-Instruct
Model Size7b
Required VRAM5.6 GB
Updated2025-02-15
MaintainerQwen
Model Typeqwen2
Instruction-BasedYes
Model Files  4.0 GB: 1-of-2   1.6 GB: 2-of-2
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen2 7B Instruct GPTQ Int4

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct GPTQ Int432K / 5.6 GB1151114
....5 Coder 7B Instruct GPTQ Int832K / 8.9 GB131533
Qwen2.5 7B Instruct GPTQ Int832K / 8.9 GB1036512
....5 Coder 7B Instruct GPTQ Int432K / 5.6 GB86654
Qwen2 7B Instruct GPTQ Int832K / 8.9 GB17316
Qwen2.5 7B Instruct 1M 4bit986K / 4.3 GB6266
...5 7B Instruct Unsloth Bnb 4bit32K / 7.2 GB144891
Mini QwQ32K / 15.2 GB401
AetherSett32K / 15.2 GB211
SphinX32K / 15.2 GB321
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2-7B-Instruct-GPTQ-Int4.

Rank the Qwen2 7B Instruct GPTQ Int4 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 43137 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227