Emma 500 Llama2 7B by MaLA-LM

 ยป  All LLMs  ยป  MaLA-LM  ยป  Emma 500 Llama2 7B   URL Share it on

  Arxiv:2409.17892   Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/llama-2-... Dataset:mala-lm/mala-monolingu...   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow

Emma 500 Llama2 7B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Emma 500 Llama2 7B (MaLA-LM/emma-500-llama2-7b)

Emma 500 Llama2 7B Parameters and Internals

Model Type 
multilingual language model
Use Cases 
Areas:
multilingual text generation, commonsense reasoning, machine translation, text classification, natural language inference, code generation, open-ended generation
Supported Languages 
number_of_languages (546), description (The model is trained on 546 languages, each with substantial training data of over 100k tokens.)
Training Details 
Data Sources:
MaLA Corpus
Data Volume:
74 billion tokens
Methodology:
Continual pre-training
Model Architecture:
Built on Llama 2 7B with enhanced language adaptation through continual pre-training.
LLM NameEmma 500 Llama2 7B
Repository ๐Ÿค—https://huggingface.co/MaLA-LM/emma-500-llama2-7b 
Base Model(s)  Llama 2 7B Hf   meta-llama/Llama-2-7b-hf
Model Size7b
Required VRAM27.1 GB
Updated2024-12-21
MaintainerMaLA-LM
Model Typellama
Model Files  4.8 GB: 1-of-6   4.9 GB: 2-of-6   4.9 GB: 3-of-6   4.9 GB: 4-of-6   4.9 GB: 5-of-6   2.7 GB: 6-of-6
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.43.3
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to Emma 500 Llama2 7B

Best Alternatives
Context / RAM
Downloads
Likes
...1M 1000000ctx AEZAKMI 3 1 17021024K / 13.5 GB861
... Qwen2.5llamaify 7B V23.1 200K195K / 15.2 GB29820
SuperNeuralDreadDevil 8B128K / 16.1 GB1871
Yarn Llama 2 7B 128K128K / 13.5 GB229640
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 MaLA-LM/emma-500-llama2-7b.

Rank the Emma 500 Llama2 7B 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? 40013 in total.

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