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

Q2.5 Instruct 1M Harmony by Triangle104

 »  All LLMs  »  Triangle104  »  Q2.5 Instruct 1M Harmony   URL Share it on

  65   
  Merged Model   Autotrain compatible Base model:huihui-ai/qwen2.5-7... Base model:qwen/qwen2.5-7b-ins...   Conversational   Endpoints compatible   Instruct   Model-index   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Triangle104/Q2.5-Instruct-1M_Harmony 

Q2.5 Instruct 1M Harmony Benchmarks

MMLU Pro: 37.4
GPQA: 9.73
MUSR: 18.1
BBH: 33.63
IFEval: 60.38 vs 88 (so35)-31.4%
MATH Lvl 5: 33.23
LLME Score: 0.34594
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Q2.5 Instruct 1M Harmony (Triangle104/Q2.5-Instruct-1M_Harmony)

Q2.5 Instruct 1M Harmony Parameters and Internals

LLM NameQ2.5 Instruct 1M Harmony
Repository 🤗https://huggingface.co/Triangle104/Q2.5-Instruct-1M_Harmony 
Base Model(s)  Qwen/Qwen2.5-7B-Instruct-1M   huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated   Qwen/Qwen2.5-7B-Instruct-1M   huihui-ai/Qwen2.5-7B-Instruct-1M-abliterated
Merged ModelYes
Model Size7b
Required VRAM15.2 GB
Updated2025-03-12
MaintainerTriangle104
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   0.3 GB: 4-of-4
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length1010000
Model Max Length1010000
Transformers Version4.48.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Q2.5 Instruct 1M Harmony

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M986K / 15.4 GB332966262
Hush Qwen2.5 7B RP V1.4 1M986K / 15.2 GB272
Qwen2.5 7B RRP 1M986K / 15.2 GB2086
Qwen2.5 7B CelestialHarmony 1M986K / 14.8 GB1927
COCO 7B Instruct 1M986K / 15.2 GB9013
Impish QWEN 7B 1M986K / 15.2 GB764
Apollo 7B986K / 15.2 GB490
Hush Qwen2.5 7B RP V1.1 1M986K / 15.2 GB301
Qwen2.5 7B Instruct 1M986K / 15.2 GB8802
Qwen2.5 7B Sky R1 Mini986K / 15.2 GB600
Note: green Score (e.g. "73.2") means that the model is better than Triangle104/Q2.5-Instruct-1M_Harmony.

Rank the Q2.5 Instruct 1M Harmony 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? 44887 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