SLIMER by expertai

 ยป  All LLMs  ยป  expertai  ยป  SLIMER   URL Share it on

  Arxiv:2407.01272   Autotrain compatible   Conversational Dataset:universal-ner/pile-ner...   En   Endpoints compatible   Llama   Ner   Region:us   Safetensors   Sharded   Tensorflow   Zero-shot ner
Model Card on HF ๐Ÿค—: https://huggingface.co/expertai/SLIMER 

SLIMER Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SLIMER (expertai/SLIMER)

SLIMER Parameters and Internals

Model Type 
text-generation, zero-shot NER
Additional Notes 
Specifically instructed for zero-shot NER using a prompt enriched with DEFINITION and GUIDELINES.
Supported Languages 
en (Full support for English.)
Input Output 
Input Format:
Text chunk delimited by triple quotes and an instruction.
Accepted Modalities:
text
Output Format:
JSON list of Named Entity instances
Performance Tips:
Use DEFINITION and GUIDELINES to enrich prompts for better zero-shot NER.
LLM NameSLIMER
Repository ๐Ÿค—https://huggingface.co/expertai/SLIMER 
Model Size7b
Required VRAM13.5 GB
Updated2024-12-22
Maintainerexpertai
Model Typellama
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   3.6 GB: 3-of-3
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.37.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to SLIMER

Best Alternatives
Context / RAM
Downloads
Likes
...1M 1000000ctx AEZAKMI 3 1 17021024K / 13.5 GB851
... Qwen2.5llamaify 7B V23.1 200K195K / 15.2 GB29350
SuperNeuralDreadDevil 8B128K / 16.1 GB1551
Yarn Llama 2 7B 128K128K / 13.5 GB226240
LLaMA 7B PoSE YaRN 128K128K / 13.5 GB113
LLaMA 7B PoSE Linear 96K96K / 27 GB102
LLaMA 7B PoSE YaRN 96K96K / 13.5 GB111
Chat Llama2 7B 80K80K / 13.8 GB260
Llama2 7B 80K80K / 13.8 GB250
Lloma Step40064K / 13.5 GB800
Note: green Score (e.g. "73.2") means that the model is better than expertai/SLIMER.

Rank the SLIMER 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