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

Minotaur 15B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Minotaur 15B GPTQ   URL Share it on

  23   
  Arxiv:1911.02150   Arxiv:2205.14135   Arxiv:2207.14255   Arxiv:2305.06161   4-bit   Autotrain compatible   Code   Codegen Dataset:bigcode/the-stack-dedu...   Dataset:camel-ai/biology   Dataset:camel-ai/chemistry   Dataset:camel-ai/math   Dataset:camel-ai/physics Dataset:ehartford/wizardlm alp...   Dataset:gsm8k   Dataset:hellaswag Dataset:metaeval/scienceqa tex... Dataset:openai/summarize from ...   Dataset:qingyisi/alpaca-cot   Dataset:riddle sense Dataset:teknium/gpteacher-gene... Dataset:tiiuae/falcon-refinedw...   Dataset:winglian/evals   Gpt bigcode   Gptq   Instruct   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/minotaur-15B-GPTQ 

Minotaur 15B GPTQ Benchmarks

LLME Score: 0.09456
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Minotaur 15B GPTQ (TheBloke/minotaur-15B-GPTQ)
🌟 Advertise your project 🚀

Minotaur 15B GPTQ Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Applications:
text generation, code generation
Primary Use Cases:
instruct fine-tuning, prose generation, code generation
Limitations:
Not suitable for non-English text, potential biases and stereotypes
Considerations:
Use caution with generated code as it may contain errors or inefficiencies.
Additional Notes 
Model utilizes Fill-in-the-Middle objective for more varied generation.
Supported Languages 
English (high)
Training Details 
Data Sources:
ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered, QingyiSi/Alpaca-CoT, teknium/GPTeacher-General-Instruct, metaeval/ScienceQA_text_only, openai/summarize_from_feedback, camel-ai/math, camel-ai/physics, camel-ai/chemistry, camel-ai/biology, winglian/evals, hellaswag, riddle_sense, gsm8k
Methodology:
Fine-tuned from StarCoder on open datasets focusing on instruct fine-tuning. Utilizes QLoRA techniques.
Context Length:
8192
Training Time:
Approx. 30 hours per epoch
Hardware Used:
4XA100 80GB
Model Architecture:
GPT model with multi-query attention and Fill-in-the-Middle objective.
Responsible Ai Considerations 
Fairness:
Not aligned to human preferences; can produce problematic outputs.
Transparency:
Users should apply the proper attribution to generated code.
Accountability:
Users are responsible for complying with licensing requirements.
Input Output 
Input Format:
Prompts following the 'USER:' and 'ASSISTANT:' format.
Accepted Modalities:
text
Output Format:
Text
Performance Tips:
Use latest versions of required software for optimal performance.
Release Notes 
Version:
unknown
Date:
unknown
Notes:
Minotaur 15B trained with Axolotl on 4XA100 80GB over approximately 30 hours per epoch.
LLM NameMinotaur 15B GPTQ
Repository 🤗https://huggingface.co/TheBloke/minotaur-15B-GPTQ 
Model Size15b
Required VRAM9.2 GB
Updated2025-08-17
MaintainerTheBloke
Model Typegpt_bigcode
Instruction-BasedYes
Model Files  9.2 GB
GPTQ QuantizationYes
Quantization Typegptq
Generates CodeYes
Model ArchitectureGPTBigCodeForCausalLM
Transformers Version4.28.1
Tokenizer ClassGPT2Tokenizer
Vocabulary Size49152
Torch Data Typefloat32
Activation Functiongelu

Best Alternatives to Minotaur 15B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
WizardCoderSQL 15B V1.00K / 31.2 GB151
...r Skeleton Wizard Coder Merged0K / 31.2 GB3813
...der Natsql Wizard Coder Merged0K / 32.7 GB191
Minotaur 15B0K / 31.2 GB1615
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/minotaur-15B-GPTQ.

Rank the Minotaur 15B GPTQ 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? 50723 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