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 8.0bpw H8 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Qwen2 7B Instruct 8.0bpw H8 EXL2   URL Share it on

  12   
  Arxiv:2309.00071   8-bit   Autotrain compatible   Chat   Conversational   En   Endpoints compatible   Exl2   Instruct   Quantized   Qwen2   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/LoneStriker/Qwen2-7B-Instruct-8.0bpw-h8-exl2 

Qwen2 7B Instruct 8.0bpw H8 EXL2 Benchmarks

LLME Score: 0.19081
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 8.0bpw H8 EXL2 (LoneStriker/Qwen2-7B-Instruct-8.0bpw-h8-exl2)

Qwen2 7B Instruct 8.0bpw H8 EXL2 Parameters and Internals

Model Type 
instruction-tuned, language model
Use Cases 
Areas:
text generation
Primary Use Cases:
language understanding, language generation, multilingual capability, coding, mathematics, reasoning
Additional Notes 
Model supports long contexts up to 131072 tokens with YARN for large text processing.
Supported Languages 
en (native)
Training Details 
Data Volume:
large amount
Methodology:
supervised finetuning and direct preference optimization
Context Length:
131072
Model Architecture:
Transformer with SwiGLU activation, attention QKV bias, group query attention
Input Output 
Accepted Modalities:
text
Output Format:
text
LLM NameQwen2 7B Instruct 8.0bpw H8 EXL2
Repository 🤗https://huggingface.co/LoneStriker/Qwen2-7B-Instruct-8.0bpw-h8-exl2 
Model Size7b
Required VRAM7.7 GB
Updated2025-02-22
MaintainerLoneStriker
Model Typeqwen2
Instruction-BasedYes
Model Files  7.7 GB
Supported Languagesen
Quantization Typeexl2
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2 7B Instruct 8.0bpw H8 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M 4bit986K / 4.3 GB7306
...B Instruct 1M Unsloth Bnb 4bit986K / 7.5 GB3541
...5 7B Instruct Unsloth Bnb 4bit32K / 7.2 GB342211
Mini QwQ32K / 15.2 GB271
AetherSett32K / 15.2 GB261
Qwen2.5 7B Instruct Bnb 4bit32K / 5.5 GB67479511
SphinX32K / 15.2 GB321
ReasonTest32K / 15.2 GB110
Kyro N1 7B32K / 15.2 GB1875
UIGEN 7B 16bit32K / 15.2 GB795
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Qwen2-7B-Instruct-8.0bpw-h8-exl2.

Rank the Qwen2 7B Instruct 8.0bpw H8 EXL2 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? 43470 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