Qwen2.5 1.5B Instruct SFT OpenHermes 2.5 Standard SFT by vectorzhou

 ยป  All LLMs  ยป  vectorzhou  ยป  Qwen2.5 1.5B Instruct SFT OpenHermes 2.5 Standard SFT   URL Share it on

  Arxiv:1910.09700   Autotrain compatible   Conversational   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors

Qwen2.5 1.5B Instruct SFT OpenHermes 2.5 Standard SFT Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

Qwen2.5 1.5B Instruct SFT OpenHermes 2.5 Standard SFT Parameters and Internals

LLM NameQwen2.5 1.5B Instruct SFT OpenHermes 2.5 Standard SFT
Repository ๐Ÿค—https://huggingface.co/vectorzhou/Qwen2.5-1.5B-Instruct-SFT-OpenHermes-2.5-Standard-SFT 
Model Size1.5b
Required VRAM3.1 GB
Updated2025-06-11
Maintainervectorzhou
Model Typeqwen2
Instruction-BasedYes
Model Files  3.1 GB
Model ArchitectureQwen2ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.48.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace
Qwen2.5 1.5B Instruct SFT OpenHermes 2.5 Standard SFT (vectorzhou/Qwen2.5-1.5B-Instruct-SFT-OpenHermes-2.5-Standard-SFT)

Best Alternatives to Qwen2.5 1.5B Instruct SFT OpenHermes 2.5 Standard SFT

Best Alternatives
Context / RAM
Downloads
Likes
AceInstruct 1.5B128K / 3.5 GB358620
Gte Qwen2 1.5B Instruct128K / 7.1 GB171702219
GCIRS Reasoning 1.5B R1128K / 3.5 GB191
... Abliterated TIES Qwen2.5 1.5B128K / 3.5 GB200
...illed Scout 1.5B Instruct Gen1128K / 3.5 GB490
Saba1 1.8B128K / 3.6 GB581
WiroAI Finance Qwen 1.5B128K / 3.5 GB99219
Bellatrix 1.5B XElite128K / 3.5 GB263
Miniclaus Qw1.5B UNAMGS128K / 3.5 GB258
...pmath Competitive 1.5B Preview128K / 7.1 GB350
Note: green Score (e.g. "73.2") means that the model is better than vectorzhou/Qwen2.5-1.5B-Instruct-SFT-OpenHermes-2.5-Standard-SFT.

Rank the Qwen2.5 1.5B Instruct SFT OpenHermes 2.5 Standard SFT 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? 48079 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124