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

Manticore 13B AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Manticore 13B AWQ   URL Share it on

  5   
  4-bit   Autotrain compatible   Awq Base model:openaccess-ai-colle... Base model:quantized:openacces... Dataset:anon8231489123/sharegp... Dataset:ehartford/wizard vicun... Dataset:ehartford/wizardlm alp...   Dataset:hellaswag Dataset:metaeval/scienceqa tex... Dataset:openai/summarize from ...   Dataset:qingyisi/alpaca-cot   Dataset:tasksource/mmlu Dataset:teknium/gpt4-llm-clean... Dataset:teknium/gpteacher-gene...   En   Instruct   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Manticore-13B-AWQ 

Manticore 13B AWQ Benchmarks

LLME Score: 0.10978
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Manticore 13B AWQ (TheBloke/Manticore-13B-AWQ)
🌟 Advertise your project 🚀

Manticore 13B AWQ Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
Research, Commercial applications
Applications:
General conversational AI, Text generation
Primary Use Cases:
Chatbot for detailed and polite answers, Information retrieval
Limitations:
The model can produce problematic outputs when prompted to do so.
Considerations:
It has not been aligned to human preferences or safety mechanisms like RLHF.
Additional Notes 
Models are released as sharded safetensors files for AWQ, allowing easier deployment and overall cost savings.
Training Details 
Data Sources:
anon8231489123/ShareGPT_Vicuna_unfiltered, ehartford/wizard_vicuna_70k_unfiltered, ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered, QingyiSi/Alpaca-CoT, teknium/GPT4-LLM-Cleaned, teknium/GPTeacher-General-Instruct, metaeval/ScienceQA_text_only, openai/summarize_from_feedback
Training Time:
Approximately 24 hours for 3 epochs
Hardware Used:
8xA100 80GB
Model Architecture:
Llama 13B fine-tuned on multiple datasets
Responsible Ai Considerations 
Mitigation Strategies:
Manticore has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses.
Input Output 
Input Format:
Prompt-based dialogue format
Accepted Modalities:
Text
Output Format:
Text responses
Release Notes 
Version:
Preview release
Notes:
3 epochs taking approximately 24 hours.
LLM NameManticore 13B AWQ
Repository 🤗https://huggingface.co/TheBloke/Manticore-13B-AWQ 
Model NameManticore 13B
Model CreatorOpen Access AI Collective
Base Model(s)  Manticore 13B   openaccess-ai-collective/manticore-13b
Model Size13b
Required VRAM7.2 GB
Updated2025-09-17
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  7.2 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.30.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Manticore 13B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 13B Instruct AWQ16K / 7.2 GB13489
NexusRaven 13B AWQ16K / 7.2 GB64
...ma 13B Instruct Hf W4 G128 AWQ16K / 7.2 GB80
Meta Llama 3 13B Instruct AWQ8K / 8.8 GB31200
Leo Hessianai 13B Chat AWQ8K / 7.2 GB170
...ssianai 13B Chat Bilingual AWQ8K / 7.2 GB81
Swallow 13B Instruct AWQ4K / 7.5 GB91
Mythalion 13B AWQ4K / 7.2 GB111610
Pygmalion 2 13B AWQ4K / 7.2 GB10946
Speechless Llama2 13B AWQ4K / 7.2 GB101
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Manticore-13B-AWQ.

Rank the Manticore 13B AWQ 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? 51415 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