LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen2 7B Instruct AWQ by Qwen

 »  All LLMs  »  Qwen  »  Qwen2 7B Instruct AWQ   URL Share it on

  821   
  Arxiv:2309.00071   4-bit   Autotrain compatible   Awq Base model:quantized:qwen/qwen... Base model:qwen/qwen2-7b-instr...   Chat   Conversational   En   Endpoints compatible   Instruct   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2-7B-Instruct-AWQ 

Qwen2 7B Instruct AWQ Benchmarks

LLME Score: 0.22203
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 AWQ (Qwen/Qwen2-7B-Instruct-AWQ)

Qwen2 7B Instruct AWQ Parameters and Internals

Model Type 
language generation, multilingual capability, coding, mathematics, reasoning
Use Cases 
Areas:
Research, Commercial applications
Additional Notes 
Supports context length up to 131,072 tokens using YARN technique.
Supported Languages 
en (high proficiency)
Training Details 
Methodology:
Supervised finetuning and direct preference optimization
Context Length:
131072
Model Architecture:
Transformer with SwiGLU activation, attention QKV bias, group query attention, and improved tokenizer.
Input Output 
Input Format:
Chat prompts
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Add the rope_scaling configuration only when processing long contexts is required.
LLM NameQwen2 7B Instruct AWQ
Repository 🤗https://huggingface.co/Qwen/Qwen2-7B-Instruct-AWQ 
Base Model(s)  Qwen2 7B Instruct   Qwen/Qwen2-7B-Instruct
Model Size7b
Required VRAM5.6 GB
Updated2025-01-22
MaintainerQwen
Model Typeqwen2
Instruction-BasedYes
Model Files  4.0 GB: 1-of-2   1.6 GB: 2-of-2
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen2 7B Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Samantha Qwen2 7B AWQ128K / 5.6 GB910
Qwen2.5 7B Instruct AWQ32K / 5.6 GB1243617
Qwen2.5 Coder 7B Instruct AWQ32K / 5.6 GB323410
Mini QwQ32K / 15.2 GB201
AetherSett32K / 15.2 GB431
Qwen2.5 7B Instruct 4bit32K / 4.3 GB2394197
SphinX32K / 15.2 GB321
Qwen2.5 7B Instruct Bnb 4bit32K / 5.5 GB11756110
ReasonTest32K / 15.2 GB110
Qwen2.5 Coder 7B Instruct 4bit32K / 4.3 GB913082
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2-7B-Instruct-AWQ.

Rank the Qwen2 7B Instruct AWQ 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? 41728 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer