Context Aware Splitter 1B by mhenrichsen

 ยป  All LLMs  ยป  mhenrichsen  ยป  Context Aware Splitter 1B   URL Share it on

  Autotrain compatible   Da Dataset:mhenrichsen/context-aw...   Endpoints compatible   Llama   Pytorch   Region:us   Safetensors

Context Aware Splitter 1B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Context Aware Splitter 1B (mhenrichsen/context-aware-splitter-1b)

Context Aware Splitter 1B Parameters and Internals

Model Type 
text splitter, Retrieval Augmented Generation
Use Cases 
Areas:
text processing
Primary Use Cases:
text segmentation
Additional Notes 
The model is instructed to divide text into meaningful separate parts that can be read independently.
Supported Languages 
language (da), proficiency (unknown)
Training Details 
Data Sources:
mhenrichsen/context-aware-splits
Data Volume:
13.4 million tokens
Input Output 
Input Format:
text input format with word count specification
Accepted Modalities:
text
Output Format:
dictionary with 'splits' and 'topic'
LLM NameContext Aware Splitter 1B
Repository ๐Ÿค—https://huggingface.co/mhenrichsen/context-aware-splitter-1b 
Model Size1b
Required VRAM2.2 GB
Updated2024-12-22
Maintainermhenrichsen
Model Typellama
Model Files  2.2 GB   2.2 GB
Supported Languagesda
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8194
Model Max Length8194
Transformers Version4.34.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Context Aware Splitter 1B

Best Alternatives
Context / RAM
Downloads
Likes
LWM Text Chat 1M1024K / 13.5 GB1033176
LWM Text 1M1024K / 13.5 GB149928
JOSIE 1M Base1024K / 13.5 GB121
JOSIE 1M Base1024K / 13.5 GB61
Llama 3.2 1B128K / 2.5 GB22118491302
Llama 3.2 1B Instruct128K / 2.5 GB1821782655
Llama 3.2 1B Instruct128K / 2.5 GB7367845
Llama 3.2 1B128K / 2.5 GB12513822
FastLlama 3.2 1B Instruct128K / 4.9 GB11529
Llama 3.2 SUN HDIC 1B Instruct128K / 3 GB910
Note: green Score (e.g. "73.2") means that the model is better than mhenrichsen/context-aware-splitter-1b.

Rank the Context Aware Splitter 1B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217