Qwen1.5 32B Chat GPTQ Int8 by study-hjt

 »  All LLMs  »  study-hjt  »  Qwen1.5 32B Chat GPTQ Int8   URL Share it on

  Arxiv:2309.16609   32b   8-bit   Autotrain compatible   Chat   Conversational   En   Endpoints compatible   Gptq   Int8   Quantized   Qwen   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Zh

Qwen1.5 32B Chat 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").
Qwen1.5 32B Chat GPTQ Int8 (study-hjt/Qwen1.5-32B-Chat-GPTQ-Int8)

Qwen1.5 32B Chat GPTQ Int8 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model supports stable 32K context length and has improved multilingual support.
Supported Languages 
en (multilingual), zh (multilingual)
Training Details 
Methodology:
pretrained on a large amount of data with supervised finetuning and direct preference optimization
Model Architecture:
Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, mixture of sliding window attention and full attention
Input Output 
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Use provided hyper-parameters in generation_config.json for better performance in cases like code switching.
LLM NameQwen1.5 32B Chat GPTQ Int8
Repository 🤗https://huggingface.co/study-hjt/Qwen1.5-32B-Chat-GPTQ-Int8 
Model Size32b
Required VRAM34.9 GB
Updated2025-01-01
Maintainerstudy-hjt
Model Typeqwen2
Model Files  10.0 GB: 1-of-4   10.0 GB: 2-of-4   9.9 GB: 3-of-4   5.0 GB: 4-of-4
Supported Languagesen zh
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.39.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen1.5 32B Chat GPTQ Int8

Best Alternatives
Context / RAM
Downloads
Likes
...5 Coder 32B Instruct GPTQ Int832K / 35.1 GB1770115
...5 Coder 32B Instruct GPTQ Int432K / 19.5 GB79228
Qwen2.5 32B Instruct GPTQ Int432K / 19.5 GB1637021
Qwen2.5 32B Instruct GPTQ Int832K / 35.1 GB46388
QwQ 32B Preview GPTQ 4bit32K / 16.1 GB3063
Qwen1.5 32B Chat GPTQ Int432K / 19.5 GB248229
Qwen Qwen1.5 32B 4 Bit Gptq32K / 19.2 GB260
Qwen2.5 32B Bnb 4bit128K / 19.2 GB2264073
EVA Instruct 32B EXL2 4.0128K / 17.7 GB353
PathfinderAI32K / 65.8 GB1020
Note: green Score (e.g. "73.2") means that the model is better than study-hjt/Qwen1.5-32B-Chat-GPTQ-Int8.

Rank the Qwen1.5 32B Chat GPTQ Int8 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? 40649 in total.

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