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

LLaMA2 13B Psyfighter2 by KoboldAI

 »  All LLMs  »  KoboldAI  »  LLaMA2 13B Psyfighter2   URL Share it on

  765   

LLaMA2 13B Psyfighter2 is an open-source language model by KoboldAI. Features: 13b LLM, VRAM: 26GB, Context: 4K, License: llama2, Quantized, HF Score: 54.7, LLM Explorer Score: 0.14, Arc: 60.1, HellaSwag: 84, MMLU: 55.1, TruthfulQA: 53, WinoGrande: 74.4, GSM8K: 1.4.

  Endpoints compatible   Fp16   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/KoboldAI/LLaMA2-13B-Psyfighter2 

LLaMA2 13B Psyfighter2 Benchmarks

ARC: 60.07 vs 96.7 (so35)-37.9%
HellaSwag: 84.02 vs 95.3 (gpt4)-11.8%
MMLU: 55.07 vs 88.3 (so35)-37.6%
TruthfulQA: 53 vs 59 (gpt4)-10.2%
WinoGrande: 74.35 vs 87.5 (gpt4)-15%
GSM8K: 1.44 vs 96.4 (so35)-98.5%
LLME Score: 0.14019
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LLaMA2 13B Psyfighter2 (KoboldAI/LLaMA2-13B-Psyfighter2)
🌟 Advertise your project 🚀

LLaMA2 13B Psyfighter2 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
creative writing
Applications:
story writing, chatbots, instruct-style prompting, adventuring and adventure games
Primary Use Cases:
creative writing
Limitations:
model should not be used for medical advice or therapy
Considerations:
Model tends to improvise and may generate fictional content.
Additional Notes 
The model is a merge of various models, with a focus on creativity rather than factual accuracy.
Training Details 
Methodology:
task_arithmetic
Release Notes 
Version:
V1
Notes:
Published under the account of the creator of the merge.
LLM NameLLaMA2 13B Psyfighter2
Repository 🤗https://huggingface.co/KoboldAI/LLaMA2-13B-Psyfighter2 
Model Size13b
Required VRAM26 GB
Updated2026-03-30
MaintainerKoboldAI
Model Typellama
Model Files  9.9 GB: 1-of-3   9.8 GB: 2-of-3   6.3 GB: 3-of-3
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the LLaMA2 13B Psyfighter2

Model
Likes
Downloads
VRAM
LLaMA2 13B Psyfighter2 GGUF166895 GB
LLaMA2 13B Psyfighter2 GPTQ1677 GB
LLaMA2 13B Psyfighter2 AWQ4107 GB

Best Alternatives to LLaMA2 13B Psyfighter2

Best Alternatives
Context / RAM
Downloads
Likes
Llama13b 32K Illumeet Finetune32K / 26 GB80
...Maid V3 13B 32K 8.0bpw H8 EXL232K / 13.2 GB71
...Maid V3 13B 32K 6.0bpw H6 EXL232K / 10 GB41
WhiteRabbitNeo 13B V116K / 26 GB2146448
CodeLlama 13B Python Fp1616K / 26 GB144725
CodeLlama 13B Instruct Fp1616K / 26 GB284728
CodeLlama 13B Fp1616K / 26 GB6567
...Llama 13B Instruct Hf 4bit MLX16K / 7.8 GB3463
Airophin 13B Pntk 16K Fp1616K / 26 GB7884
Codellama 13B Bnb 4bit16K / 7.2 GB885
Note: green Score (e.g. "73.2") means that the model is better than KoboldAI/LLaMA2-13B-Psyfighter2.

Rank the LLaMA2 13B Psyfighter2 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer