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

TQ2.5 14B Aletheia V1 by allura-org

 »  All LLMs  »  allura-org  »  TQ2.5 14B Aletheia V1   URL Share it on

  128   
  Merged Model   Autotrain compatible Base model:allura-org/tq2.5-14... Base model:allura-org/tq2.5-14...   Conversational   En   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/allura-org/TQ2.5-14B-Aletheia-v1 

TQ2.5 14B Aletheia V1 Benchmarks

MMLU Pro: 47.12
GPQA: 14.99
MUSR: 14.61
BBH: 50.88
IFEval: 75.3 vs 88 (so35)-14.4%
MATH Lvl 5: 33.99
LLME Score: 0.35698
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
TQ2.5 14B Aletheia V1 (allura-org/TQ2.5-14B-Aletheia-v1)

TQ2.5 14B Aletheia V1 Parameters and Internals

LLM NameTQ2.5 14B Aletheia V1
Repository 🤗https://huggingface.co/allura-org/TQ2.5-14B-Aletheia-v1 
Base Model(s)  allura-org/TQ2.5-14B-Neon-v1   allura-org/TQ2.5-14B-Sugarquill-v1   allura-org/TQ2.5-14B-Neon-v1   allura-org/TQ2.5-14B-Sugarquill-v1
Merged ModelYes
Model Size14b
Required VRAM29.7 GB
Updated2025-03-24
Maintainerallura-org
Model Typeqwen2
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   4.8 GB: 6-of-6
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.43.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to TQ2.5 14B Aletheia V1

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B Instruct 1M986K / 29.6 GB57193290
T3Q Qwen2.5 14B V1.0 E3986K / 29.7 GB123413
ZYH LLM Qwen2.5 14B V4986K / 29.7 GB8195
Qwen2.5 14B YOYO V4986K / 29.7 GB4074
Condor Opus 14B Exp986K / 29.7 GB12422
ZYH LLM Qwen2.5 14B V3986K / 29.7 GB3956
Tadpole Opus 14B Exp986K / 29.7 GB14171
Qwen2.5 14B 1M YOYO V3986K / 29.7 GB2544
Lacerta Opus 14B Elite8986K / 29.7 GB3742
Etr1o V1.2986K / 29.7 GB1620
Note: green Score (e.g. "73.2") means that the model is better than allura-org/TQ2.5-14B-Aletheia-v1.

Rank the TQ2.5 14B Aletheia V1 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? 45494 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