Qwen2 7B Int4 Inc by Intel

 ยป  All LLMs  ยป  Intel  ยป  Qwen2 7B Int4 Inc   URL Share it on

  Arxiv:2309.05516   4-bit   Autotrain compatible   Conversational   Dataset:neelnanda/pile-10k   Endpoints compatible   Intel/auto-round   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/Intel/Qwen2-7B-int4-inc 

Qwen2 7B Int4 Inc 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 Int4 Inc (Intel/Qwen2-7B-int4-inc)

Qwen2 7B Int4 Inc Parameters and Internals

Model Type 
quantized, causal, int4, lm-head
Use Cases 
Areas:
research, commercial applications
Limitations:
factually incorrect output, generate offensive content
Considerations:
Users should be informed about the risks and biases of the model.
Additional Notes 
Larger accuracy drop observed in Chinese tasks.
Responsible Ai Considerations 
Fairness:
The model could generate biased or lewd content.
Mitigation Strategies:
Developers should conduct safety testing before deployment.
Input Output 
Accepted Modalities:
text
Performance Tips:
Use Intel Gaudi-2 for INT4 inference to boost performance.
LLM NameQwen2 7B Int4 Inc
Repository ๐Ÿค—https://huggingface.co/Intel/Qwen2-7B-int4-inc 
Model Size7b
Required VRAM5.6 GB
Updated2025-02-22
MaintainerIntel
Model Typeqwen2
Model Files  4.5 GB: 1-of-2   1.1 GB: 2-of-2
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen2 7B Int4 Inc

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M986K / 15.4 GB289038236
Qwen2.5 7B MixStock V0.1986K / 15.2 GB6823
Qwen2.5 7B RRP 1M986K / 15.2 GB2944
Qwen2.5 7B CelestialHarmony 1M986K / 14.8 GB1535
Qwen 2.5 7B Exp Sce986K / 15.2 GB282
COCO 7B Instruct 1M986K / 15.2 GB1059
SJT 7B V1.1986K / 14.8 GB1521
Q2.5 Instruct 1M Harmony986K / 15.2 GB611
Impish QWEN 7B 1M986K / 15.2 GB701
Qwen 2.5 7B Deep Stock V5986K / 15.2 GB302
Note: green Score (e.g. "73.2") means that the model is better than Intel/Qwen2-7B-int4-inc.

Rank the Qwen2 7B Int4 Inc 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? 43470 in total.

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