Qwen2.5 14B Instruct GPTQ Int8 by Qwen

 ยป  All LLMs  ยป  Qwen  ยป  Qwen2.5 14B Instruct GPTQ Int8   URL Share it on

  Arxiv:2309.00071   8-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-14b-in...   Chat   Conversational   En   Gptq   Instruct   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow

Qwen2.5 14B Instruct GPTQ Int8 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Qwen2.5 14B Instruct GPTQ Int8 Parameters and Internals

LLM NameQwen2.5 14B Instruct GPTQ Int8
Repository ๐Ÿค—https://huggingface.co/Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8 
Base Model(s)  Qwen/Qwen2.5-14B-Instruct   Qwen/Qwen2.5-14B-Instruct
Model Size14b
Required VRAM16.8 GB
Updated2024-10-04
MaintainerQwen
Model Typeqwen2
Instruction-BasedYes
Model Files  4.0 GB: 1-of-5   4.0 GB: 2-of-5   4.0 GB: 3-of-5   3.2 GB: 4-of-5   1.6 GB: 5-of-5
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.39.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace
Qwen2.5 14B Instruct GPTQ Int8 (Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8)

Best Alternatives to Qwen2.5 14B Instruct GPTQ Int8

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B Instruct GPTQ Int432K / 10 GB23334
Qwen2.5 14B Instruct Bnb 4bit32K / 9.9 GB39580
EVA Qwen2.5 14B V0.0128K / 29.7 GB868
Qwen2.5 14B Instruct32K / 29.6 GB2695064
Qwen2.5 14B Instruct AWQ32K / 10 GB359196
Replete LLM V2.5 Qwen 14B32K / 29.7 GB21613
Qwen2.5 14B Instruct32K / 29.7 GB2176
Qwen2.5 14B Gutenberg 1e Delta32K / 29.7 GB3673
Qwen2p5 14B Distill Wip32K / 29.7 GB1111
NightyGurps 14B V1.132K / 29.7 GB27
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8.

Rank the Qwen2.5 14B 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  

What open-source LLMs or SLMs are you in search of? 36542 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803