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

ALMA 13B R by haoranxu

 »  All LLMs  »  haoranxu  »  ALMA 13B R   URL Share it on

  12562   
  Arxiv:2309.11674   Arxiv:2401.08417   Autotrain compatible   Endpoints compatible   Llama   Lora   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/haoranxu/ALMA-13B-R 

ALMA 13B R Benchmarks

MMLU Pro: 9.08
GPQA: 1.01
MUSR: 2.23
BBH: 8.82
IFEval: 0.39 vs 88 (so35)-99.6%
ARC: 55.55 vs 96.7 (so35)-42.6%
HellaSwag: 79.45 vs 95.3 (gpt4)-16.6%
MMLU: 49.52 vs 88.3 (so35)-43.9%
TruthfulQA: 36.09 vs 59 (gpt4)-38.8%
WinoGrande: 75.3 vs 87.5 (gpt4)-13.9%
MATH Lvl 5: 1.74
LLME Score: 0.22837
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ALMA 13B R (haoranxu/ALMA-13B-R)
🌟 Advertise your project 🚀

ALMA 13B R Parameters and Internals

Model Type 
machine translation
Additional Notes 
ALMA-7B-Pretrain and ALMA-13B-Pretrain are only monolingually fine-tuned and are not translation models independently.
Supported Languages 
Chinese (High), English (High)
Training Details 
Data Sources:
Human-Written Parallel Data, Triplet Preference Data
Methodology:
LoRA fine-tuning with Contrastive Preference Optimization
Input Output 
Input Format:
Source sentence in prompt template
Accepted Modalities:
text
Output Format:
Translated output text
LLM NameALMA 13B R
Repository 🤗https://huggingface.co/haoranxu/ALMA-13B-R 
Model Size13b
Required VRAM26 GB
Updated2025-07-29
Maintainerhaoranxu
Model Files  0.0 GB   5.0 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   4.9 GB: 4-of-6   4.9 GB: 5-of-6   1.2 GB: 6-of-6
Model ArchitectureAutoModelForCausalLM
Licensemit
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesdown_proj
LoRA Alpha32
LoRA Dropout0.05
R Param16

Best Alternatives to ALMA 13B R

Best Alternatives
Context / RAM
Downloads
Likes
Small Tiny V10K / 0.1 GB90
...ama2 13B No Robots Alpaca Lora0K / 4 GB142810
Llava V1.5 13B S2 Lora0K / 0.1 GB52
Llama 2 13B Chat Hf GPT 4 80K0K / 26 GB60
Llava Chart 13b Lora0K / 0.1 GB92
Ko En Llama2 13B Finetune Ex0K / 26 GB10010
Ko En Llama2 13B Finetune0K / 26 GB10250
Ko Llama2 13B Finetune Ex0K / 26 GB10250
ChartLlama 13B0K / 0.1 GB8620
Llama 2 13B Longlora 64K0K / 0.1 GB127310

Rank the ALMA 13B R 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? 50230 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 v20241124
  Support LLM Explorer