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

Minotaur 13B Fixed by openaccess-ai-collective

 »  All LLMs  »  openaccess-ai-collective  »  Minotaur 13B Fixed   URL Share it on

  1979   
  Autotrain compatible   Axolotl   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:winglian/evals   Instruct   Llama   Mpt   Openaccess ai collective   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/openaccess-ai-collective/minotaur-13b-fixed 

Minotaur 13B Fixed Benchmarks

ARC: 59.04 vs 96.7 (so35)-38.9%
HellaSwag: 81.66 vs 95.3 (gpt4)-14.3%
MMLU: 50.1 vs 88.3 (so35)-43.3%
TruthfulQA: 50.36 vs 59 (gpt4)-14.6%
WinoGrande: 76.87 vs 87.5 (gpt4)-12.1%
GSM8K: 13.12 vs 96.4 (so35)-86.4%
LLME Score: 0.13365
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Minotaur 13B Fixed (openaccess-ai-collective/minotaur-13b-fixed)
🌟 Advertise your project 🚀

Minotaur 13B Fixed Parameters and Internals

Model Type 
instruct fine-tuned
Additional Notes 
Minotaur has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT.
Training Details 
Data Sources:
https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered, https://huggingface.co/QingyiSi/Alpaca-CoT, https://huggingface.co/datasets/teknium/GPTeacher-General-Instruct, https://huggingface.co/datasets/metaeval/ScienceQA_text_only, https://huggingface.co/datasets/openai/summarize_from_feedback, https://huggingface.co/datasets/camel-ai/math, https://huggingface.co/datasets/camel-ai/physics, https://huggingface.co/datasets/camel-ai/chemistry, https://huggingface.co/datasets/camel-ai/biology, https://huggingface.co/datasets/winglian/evals
Methodology:
Fine-tuned
Training Time:
Approximately 7.5 hours for 1 epoch
Hardware Used:
6XA100 80GB
Input Output 
Input Format:
Chat only style prompts using `USER:`,`ASSISTANT:`
Accepted Modalities:
text
Output Format:
text
Release Notes 
Notes:
Fixed initial release issues, retrained model dropping fewer datasets.
LLM NameMinotaur 13B Fixed
Repository 🤗https://huggingface.co/openaccess-ai-collective/minotaur-13b-fixed 
Model Size13b
Required VRAM26 GB
Updated2025-08-21
Maintaineropenaccess-ai-collective
Model Typellama
Instruction-BasedYes
Model Files  26.0 GB
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.28.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the Minotaur 13B Fixed

Model
Likes
Downloads
VRAM
Minotaur 13B Fixed GGUF0825 GB
Minotaur 13B Fixed GPTQ5167 GB

Best Alternatives to Minotaur 13B Fixed

Best Alternatives
Context / RAM
Downloads
Likes
NexusRaven V2 13B16K / 26 GB3655469
CodeLlama 13B Instruct Hf16K / 26 GB19740154
CodeLlama 13B MORepair16K / 26 GB62
CodeLlama 13B Instruct Hf16K / 26 GB175025
TableLLM 13B16K / 26 GB106929
NexusRaven 13B16K / 26 GB36104
Panda Coder 13B16K / 26 GB1913
... Llama 2 13B Instruct Text2sql16K / 26 GB3227
Gen Sim16K / 0.3 GB52
Llama 3 13B Instruct Ft8K / 26.1 GB42
Note: green Score (e.g. "73.2") means that the model is better than openaccess-ai-collective/minotaur-13b-fixed.

Rank the Minotaur 13B Fixed 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? 50804 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