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 by openaccess-ai-collective

 »  All LLMs  »  openaccess-ai-collective  »  Manticore 13B Chat Pyg   URL Share it on

  2771   
  Autotrain compatible 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   Endpoints compatible   Instruct   Llama   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/openaccess-ai-collective/manticore-13b-chat-pyg 

Manticore 13B Chat Pyg Benchmarks

ARC: 58.53 vs 96.7 (so35)-39.5%
HellaSwag: 81.96 vs 95.3 (gpt4)-14%
MMLU: 48.76 vs 88.3 (so35)-44.8%
TruthfulQA: 48.76 vs 59 (gpt4)-17.4%
WinoGrande: 77.19 vs 87.5 (gpt4)-11.8%
GSM8K: 9.55 vs 96.4 (so35)-90.1%
LLME Score: 0.13264
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 (openaccess-ai-collective/manticore-13b-chat-pyg)
🌟 Advertise your project 🚀

Manticore 13B Chat Pyg Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
text generation, roleplaying, chatbots
Limitations:
Produced outputs can be problematic, Not aligned with human preferences using RLHF
Additional Notes 
Manticore 13B Chat was built with Axolotl and is based on the LlaMa 13B model. Certain datasets like MMLU were excluded from the training.
Supported Languages 
en (English)
Training Details 
Data Sources:
ShareGPT_Vicuna_unfiltered, WizardLM_alpaca_evol_instruct_70k_unfiltered, wizard_vicuna_70k_unfiltered, QingyiSi/Alpaca-CoT, GPT4-LLM-Cleaned, GPTeacher-General-Instruct, metaeval/ScienceQA_text_only, hellaswag, openai/summarize_from_feedback, riddle_sense, gsm8k, ewof/code-alpaca-instruct-unfiltered, ARC-Easy, ARC-Challenge
Methodology:
Fine-tuning on a selected 25% of merged and shuffled datasets
Training Time:
8 hours on 8xA100 80GB for 3 epochs
Hardware Used:
8xA100 80GB
Input Output 
Input Format:
Chat style prompts using 'USER:', 'ASSISTANT:', '<|system|>, <|user|> and <|model|>' tokens
Accepted Modalities:
text
Output Format:
Text responses fit for chat applications.
Release Notes 
Version:
2
Notes:
https://wandb.ai/wing-lian/manticore-13b-v2/runs/hxr3aiiw
LLM NameManticore 13B Chat Pyg
Repository 🤗https://huggingface.co/openaccess-ai-collective/manticore-13b-chat-pyg 
Model Size13b
Required VRAM26 GB
Updated2025-09-23
Maintaineropenaccess-ai-collective
Model Typellama
Instruction-BasedYes
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3   9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3
Supported Languagesen
Model ArchitectureLlamaForCausalLM
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 Manticore 13B Chat Pyg

Model
Likes
Downloads
VRAM
Manticore 13B Chat Pyg GGUF85225 GB
Manticore 13B Chat Pyg GPTQ33147 GB
Manticore 13B Chat Pyg AWQ0147 GB

Best Alternatives to Manticore 13B Chat Pyg

Best Alternatives
Context / RAM
Downloads
Likes
NexusRaven V2 13B16K / 26 GB1096469
CodeLlama 13B Instruct Hf16K / 26 GB21962154
CodeLlama 13B MORepair16K / 26 GB32
CodeLlama 13B Instruct Hf16K / 26 GB75726
TableLLM 13B16K / 26 GB130729
NexusRaven 13B16K / 26 GB14104
Panda Coder 13B16K / 26 GB613
... Llama 2 13B Instruct Text2sql16K / 26 GB2727
Gen Sim16K / 0.3 GB72
Llama 3 13B Instruct Ft8K / 26.1 GB92
Note: green Score (e.g. "73.2") means that the model is better than openaccess-ai-collective/manticore-13b-chat-pyg.

Rank the Manticore 13B Chat Pyg 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