Qwen2.5 1.5B Instruct AWQ by Qwen

 ยป  All LLMs  ยป  Qwen  ยป  Qwen2.5 1.5B Instruct AWQ   URL Share it on

  Arxiv:2407.10671   4-bit   Autotrain compatible   Awq Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-1.5b-i...   Chat   Conversational   En   Endpoints compatible   Instruct   Quantized   Qwen2   Region:us   Safetensors

Qwen2.5 1.5B Instruct AWQ Benchmarks

nn.n% โ€” How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2.5 1.5B Instruct AWQ (Qwen/Qwen2.5-1.5B-Instruct-AWQ)

Qwen2.5 1.5B Instruct AWQ Parameters and Internals

Model Type 
Causal Language Models
Additional Notes 
Supports long-context input up to 128K tokens and can generate output up to 8K tokens. Multilingual support for over 29 languages.
Supported Languages 
languages_supported (en), proficiency_level (English and Multilingual Support)
Training Details 
Methodology:
Pretraining & Post-training
Context Length:
32768
Model Architecture:
transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
Input Output 
Input Format:
apply_chat_template
Accepted Modalities:
text
Output Format:
text
LLM NameQwen2.5 1.5B Instruct AWQ
Repository ๐Ÿค—https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct-AWQ 
Base Model(s)  Qwen/Qwen2.5-1.5B-Instruct   Qwen/Qwen2.5-1.5B-Instruct
Model Size1.5b
Required VRAM1.6โ€ฏGB
Updated2025-03-14
MaintainerQwen
Model Typeqwen2
Instruction-BasedYes
Model Files  1.6 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen2.5 1.5B Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...wen2.5 Coder 1.5B Instruct AWQ32K / 1.6โ€‰GB231423
Qwen2 1.5B Instruct AWQ32K / 1.6โ€‰GB119338
...1.5B Instruct Unsloth Bnb 4bit32K / 1.5โ€‰GB532873
Text2SQL 1.5B32K / 3.1โ€‰GB293
Qwen2.5 1.5B Instruct 4bit32K / 0.9โ€‰GB2399940
Zirel 1.532K / 3.1โ€‰GB430
FastApply 1.5B V1.032K / 3.1โ€‰GB2041122
....5 1.5B Instruct SMPO MLX 4bit32K / 0.9โ€‰GB3202
....5 1.5B Instruct SMPO MLX 8bit32K / 1.6โ€‰GB3012
BAI Qwen 2.5 1.5B Reasoning32K / 3.1โ€‰GB250
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-1.5B-Instruct-AWQ.

Rank the Qwen2.5 1.5B Instruct AWQ 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  
โ—โ—โ—โ—
Factuality and Completeness of Knowledge  
โ—โ—โ—โ—
Censorship and Alignment  
โ—โ—โ—โ—
Data Analysis and Insight Generation  
โ—โ—โ—โ—
Text Generation  
โ—โ—โ—โ—
Text Summarization and Feature Extraction  
โ—โ—โ—โ—
Code Generation  
โ—โ—โ—โ—
Multi-Language Support and Translation  
โ—โ—โ—โ—

What open-source LLMs or SLMs are you in search of? 45019 in total.

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