Qwen2 0.5B Instruct GPTQ Int8 by Qwen

 ยป  All LLMs  ยป  Qwen  ยป  Qwen2 0.5B Instruct GPTQ Int8   URL Share it on

  8-bit   Autotrain compatible   Chat   Conversational   En   Endpoints compatible   Gptq   Instruct   License:apache-2.0   Quantized   Qwen2   Region:us   Safetensors

Rank the Qwen2 0.5B Instruct GPTQ Int8 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  
Qwen2 0.5B Instruct GPTQ Int8 (Qwen/Qwen2-0.5B-Instruct-GPTQ-Int8)

Best Alternatives to Qwen2 0.5B Instruct GPTQ Int8

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
Qwen2 0.5B Instruct GPTQ Int432K / 0.7 GB8077
Qwen2Vanilla GPTQ 4bits32K / 0.7 GB460
Qwen2Vanilla GPTQ 8bits32K / 0.9 GB200
Qwen2 0.5B Instruct 4bit32K / 0.3 GB170
Qwen2 0.5B Instruct Bnb 4bit32K / 0.5 GB20851
...struct Bnb 4bit Merged 4bit 2E32K / 0.5 GB60
Qwen2 0.5B Instruct Sorah32K / 1 GB2200
Newqwen1e32K / 1 GB540
New16b3e32K / 1 GB120
Qwen2 0.5B 8 Int8.ov32K / 0 GB210

Qwen2 0.5B Instruct GPTQ Int8 Parameters and Internals

LLM NameQwen2 0.5B Instruct GPTQ Int8
RepositoryOpen on ๐Ÿค— 
Model Size0.5b
Required VRAM1.5 GB
Updated2024-06-24
MaintainerQwen
Model Typeqwen2
Instruction-BasedYes
Model Files  1.5 GB
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 Size151936
Initializer Range0.02
Torch Data Typefloat16
Errorsreplace

What open-source LLMs or SLMs are you in search of? 34902 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801