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

Mala 500 10B V1 by MaLA-LM

 »  All LLMs  »  MaLA-LM  »  Mala 500 10B V1   URL Share it on

  0   
  Arxiv:2401.13303 Base model:finetune:meta-llama... Base model:meta-llama/llama-2-...   Dataset:cis-lmu/glot500   Endpoints compatible   Lora   Multilingual   Region:us
Model Card on HF 🤗: https://huggingface.co/MaLA-LM/mala-500-10b-v1 

Mala 500 10B V1 Benchmarks

LLME Score: 0.17802
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mala 500 10B V1 (MaLA-LM/mala-500-10b-v1)

Mala 500 10B V1 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model designed to cover multiple languages with extended vocabulary and low-rank adaptation.
Supported Languages 
languages (534), proficiency (Multilingual)
Training Details 
Data Sources:
cis-lmu/Glot500
Model Architecture:
Continued pretraining with vocabulary extension and LoRA low-rank adaptation
LLM NameMala 500 10B V1
Repository 🤗https://huggingface.co/MaLA-LM/mala-500-10b-v1 
Base Model(s)  Llama 2 7B Hf   meta-llama/Llama-2-7b-hf
Model Size7b
Required VRAM4.3 GB
Updated2024-12-26
MaintainerMaLA-LM
Model Files  4.3 GB
Model ArchitectureAutoModel
Licensellama2
Is Biasednone
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesq_proj|v_proj
LoRA Alpha32
LoRA Dropout0.1
R Param8

Best Alternatives to Mala 500 10B V1

Best Alternatives
Context / RAM
Downloads
Likes
TroL 7B32K / 17.3 GB3438
CoLLaVO 7B32K / 18.6 GB50621
MoAI 7B32K / 17.7 GB31745
... 7b 448 Qinstruct Preview V0.12K / 17.3 GB144
...Tulu2 7b Writing Prompts 327680K / 8.5 GB770
Silicon Natsuki 7B0K / 14.4 GB181
Medical Mixtral 7B V2k0K / 0.4 GB50
Diff Starcoder 7B Rl0K / 0.1 GB90
Mistral 7B Instruct V0.2 ONNX0K /  GB126
Rolema 7B It0K / 0.8 GB02
Note: green Score (e.g. "73.2") means that the model is better than MaLA-LM/mala-500-10b-v1.

Rank the Mala 500 10B V1 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? 40248 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