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 Chat Pyg AWQ by TheBloke

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

  14   
  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:ewof/code-alpaca-instr...   Dataset:gsm8k   Dataset:hellaswag Dataset:metaeval/scienceqa tex... Dataset:openai/summarize from ...   Dataset:qingyisi/alpaca-cot   Dataset:riddle sense 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-chat-pyg-AWQ 

Manticore 13B Chat Pyg AWQ Benchmarks

LLME Score: 0.10929
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Manticore 13B Chat Pyg AWQ (TheBloke/manticore-13b-chat-pyg-AWQ)
🌟 Advertise your project 🚀

Manticore 13B Chat Pyg AWQ Parameters and Internals

Model Type 
llama
Use Cases 
Applications:
Chatbot applications
Limitations:
Manticore has not been aligned to human preferences with techniques like RLHF, Can produce problematic outputs
Considerations:
Refer to base model LlaMa 13B limitations.
Additional Notes 
AWQ is a quantization method supporting 4-bit quantization allowing efficient Transformers-based inference. The model has been quantized for smaller GPUs usage.
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, hellaswag, openai/summarize_from_feedback, riddle_sense, gsm8k, ewof/code-alpaca-instruct-unfiltered
Methodology:
Manticore 13B Chat is a Llama 13B model fine-tuned with new datasets, using a de-duped subset of the Pygmalion dataset.
Training Time:
8 hours
Hardware Used:
8xA100 80GB
Model Architecture:
Llama
Input Output 
Input Format:
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
Accepted Modalities:
text
Output Format:
text
Release Notes 
Version:
first release
Notes:
Files provided as sharded safetensors.
LLM NameManticore 13B Chat Pyg AWQ
Repository 🤗https://huggingface.co/TheBloke/manticore-13b-chat-pyg-AWQ 
Model NameManticore 13B Chat Pyg
Model CreatorOpen Access AI Collective
Base Model(s)  Manticore 13B Chat Pyg   openaccess-ai-collective/manticore-13b-chat-pyg
Model Size13b
Required VRAM7.2 GB
Updated2025-09-23
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 Version4.28.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Manticore 13B Chat Pyg AWQ

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 13B Instruct AWQ16K / 7.2 GB13929
NexusRaven 13B AWQ16K / 7.2 GB64
...ma 13B Instruct Hf W4 G128 AWQ16K / 7.2 GB50
Meta Llama 3 13B Instruct AWQ8K / 8.8 GB33550
...ssianai 13B Chat Bilingual AWQ8K / 7.2 GB81
Leo Hessianai 13B Chat AWQ8K / 7.2 GB90
Swallow 13B Instruct AWQ4K / 7.5 GB71
Mythalion 13B AWQ4K / 7.2 GB110610
Pygmalion 2 13B AWQ4K / 7.2 GB11046
Speechless Llama2 13B AWQ4K / 7.2 GB101
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/manticore-13b-chat-pyg-AWQ.

Rank the Manticore 13B Chat Pyg 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? 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