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

EverythingLM 13B 16K by totally-not-an-llm

 »  All LLMs  »  totally-not-an-llm  »  EverythingLM 13B 16K   URL Share it on

  1965   
  Autotrain compatible Dataset:totally-not-an-llm/eve...   Endpoints compatible   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/totally-not-an-llm/EverythingLM-13b-16k 

EverythingLM 13B 16K Benchmarks

ARC: 56.57 vs 96.7 (so35)-41.5%
HellaSwag: 80.58 vs 95.3 (gpt4)-15.4%
MMLU: 50.18 vs 88.3 (so35)-43.2%
TruthfulQA: 47.46 vs 59 (gpt4)-19.6%
WinoGrande: 72.77 vs 87.5 (gpt4)-16.8%
GSM8K: 6.44 vs 96.4 (so35)-93.3%
LLME Score: 0.18363
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
EverythingLM 13B 16K (totally-not-an-llm/EverythingLM-13b-16k)

EverythingLM 13B 16K Parameters and Internals

Model Type 
general-purpose
Use Cases 
Primary Use Cases:
Creative stories, Prompt understanding, CoT reasoning
Limitations:
Better with more detail, Uses numbered lists, Prefers fairy tales, May fall into repetition, Limited testing with full 16k context
Additional Notes 
An early test of a new dataset and experimental principles.
Training Details 
Data Sources:
EverythingLM dataset
Methodology:
QLoRa
Context Length:
16000
Training Time:
1 hour
Hardware Used:
1xA100
Input Output 
Input Format:
Modified Vicuna format
Output Format:
Verbose and detailed replies
Performance Tips:
Model performs better with more detailed prompts
LLM NameEverythingLM 13B 16K
Repository 🤗https://huggingface.co/totally-not-an-llm/EverythingLM-13b-16k 
Model Size13b
Required VRAM26 GB
Updated2024-12-22
Maintainertotally-not-an-llm
Model Typellama
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the EverythingLM 13B 16K

Model
Likes
Downloads
VRAM
EverythingLM 13B 16K GPTQ13487 GB
EverythingLM 13B 16K GGUF32515 GB
EverythingLM 13B 16K AWQ1197 GB
EverythingLM 13B 16K GGML13135 GB

Best Alternatives to EverythingLM 13B 16K

Best Alternatives
Context / RAM
Downloads
Likes
Luminaura RP 13B128K / 26 GB300
Yarn Llama 2 13B 128K128K / 26 GB945114
Agent Llama2 13B 80K80K / 26.4 GB260
Chat Llama2 13B 80K80K / 52.8 GB230
LongAlign 13B 64K64K / 26 GB6713
LongAlign 13B 64K Base64K / 26 GB253
Openbuddy Llama2 13B V15p1 64K64K / 26.1 GB274
Openbuddy Llama2 13b64k V1564K / 26.1 GB301
Yarn Llama 2 13B 64K64K / 26 GB76218
Airoboros L2 13B 2.1 YaRN 64K64K / 26 GB197
Note: green Score (e.g. "73.2") means that the model is better than totally-not-an-llm/EverythingLM-13b-16k.

Rank the EverythingLM 13B 16K 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? 40066 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 v20241217
  Support LLM Explorer