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

Hercules Qwen1.5 14B by M4-ai

 »  All LLMs  »  M4-ai  »  Hercules Qwen1.5 14B   URL Share it on

  6   
  Autotrain compatible   Conversational Dataset:locutusque/hercules-v4...   En   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/M4-ai/Hercules-Qwen1.5-14B 

Hercules Qwen1.5 14B Benchmarks

ARC: 56.23 vs 96.7 (so35)-41.9%
HellaSwag: 80.6 vs 95.3 (gpt4)-15.4%
MMLU: 68.73 vs 88.3 (so35)-22.2%
TruthfulQA: 52.03 vs 59 (gpt4)-11.8%
WinoGrande: 73.88 vs 87.5 (gpt4)-15.6%
GSM8K: 65.96 vs 96.4 (so35)-31.6%
LLME Score: 0.1604
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Hercules Qwen1.5 14B (M4-ai/Hercules-Qwen1.5-14B)
🌟 Advertise your project 🚀

Hercules Qwen1.5 14B Parameters and Internals

Model Type 
NLP, code generation
Use Cases 
Applications:
General purpose assistant, question answering, chain-of-thought
Considerations:
Users should be made aware of the risks, biases, and limitations of the model.
Additional Notes 
The model is fine-tuned using 700,000 examples from the Hercules-v4 dataset. It employs bf16 non-mixed precision training regime. Contributions were made by @Tonic, @aloobun, @fhai50032, and @Locutusque.
Supported Languages 
en (high proficiency), zh (unknown proficiency)
Training Details 
Data Sources:
https://huggingface.co/datasets/Locutusque/hercules-v4.0
Context Length:
1024
Hardware Used:
8 Kaggle TPUs
LLM NameHercules Qwen1.5 14B
Repository 🤗https://huggingface.co/M4-ai/Hercules-Qwen1.5-14B 
Model Size14b
Required VRAM28.4 GB
Updated2025-09-23
MaintainerM4-ai
Model Typeqwen2
Model Files  1.9 GB: 1-of-15   1.9 GB: 2-of-15   1.9 GB: 3-of-15   1.9 GB: 4-of-15   1.9 GB: 5-of-15   1.9 GB: 6-of-15   1.9 GB: 7-of-15   1.9 GB: 8-of-15   1.9 GB: 9-of-15   1.9 GB: 10-of-15   1.9 GB: 11-of-15   1.9 GB: 12-of-15   1.9 GB: 13-of-15   1.9 GB: 14-of-15   1.8 GB: 15-of-15
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.39.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Hercules Qwen1.5 14B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B Instruct 1M986K / 29.6 GB27690323
T3Q Qwen2.5 14B V1.0 E3986K / 29.7 GB85228
Qwen2.5 14B 1M YOYO V3986K / 29.7 GB2544
ZYH LLM Qwen2.5 14B V4986K / 29.7 GB418
Qwen2.5 14B YOYO Latest V2986K / 29.7 GB1290
Qwen2.5 14B YOYO V4986K / 29.7 GB65
ZYH LLM Qwen2.5 14B V3986K / 29.7 GB148
Etr1o V1.2986K / 29.7 GB60
...14B Instruct 1M GRPO Reasoning986K / 29.7 GB34
Impish QWEN 14B 1M986K / 29.7 GB918
Note: green Score (e.g. "73.2") means that the model is better than M4-ai/Hercules-Qwen1.5-14B.

Rank the Hercules Qwen1.5 14B 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? 51535 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 v20241124
  Support LLM Explorer