LLM EXPLORER 56,604 MODELS INDEXED

LLaMAntino 3 ANITA 8B Inst DPO ITA by swap-uniba

By swap-uniba · 2783 downloads
HF Repo ↗ Copy URL

LLaMAntino 3 ANITA 8B Inst DPO ITA is an open-source language model by swap-uniba. Features: 8b LLM, VRAM: 16.1GB, Context: 8K, License: llama3, Instruction-Based, LLM Explorer Score: 0.21, Arc: 74.6, HellaSwag: 92.8, MMLU: 66.9, GSM8K: 58.6.

  Arxiv:2312.09993   Arxiv:2405.07101 Base model:finetune:meta-llama... Base model:meta-llama/meta-lla...   Conversational Dataset:chat-error/wizard alpa...   Dataset:gsarti/clean mc4 it Dataset:mlabonne/orpo-dpo-mix-...   Deploy:azure   En   Endpoints compatible   Facebook   Instruct   It   Llama   Llama-3   Llamantino   Meta   Model-index   Pythorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA 

LLaMAntino 3 ANITA 8B Inst DPO ITA Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, Italian Language applications
Additional Notes 
Multilingual model focusing on English and Italian.
Supported Languages 
en (full proficiency), it (full proficiency)
Training Details 
Data Sources:
gsarti/clean_mc4_it, Chat-Error/wizard_alpaca_dolly_orca, mlabonne/orpo-dpo-mix-40k
Methodology:
Supervised fine-tuning using QLoRA 4bit, DPO approach over the mlabonne/orpo-dpo-mix-40k dataset.
Context Length:
8192
Model Architecture:
Llama 3 architecture
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
text and code
Release Notes 
Version:
10/05/2024
Notes:
Latest updates and improved performance.
LLM NameLLaMAntino 3 ANITA 8B Inst DPO ITA
Repository 🤗https://huggingface.co/swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA 
Model CreatorMarco Polignano - SWAP Research Group
Base Model(s)  Meta Llama 3 8B Instruct   meta-llama/Meta-Llama-3-8B-Instruct
Model Size8b
Required VRAM16.1 GB
Updated2026-06-29
Maintainerswap-uniba
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagesen it
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to LLaMAntino 3 ANITA 8B Inst DPO ITA

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB1135125
UltraLong Thinking4192K / 16.1 GB23
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB12418
Cthulhu 8B V1.41048K / 16.1 GB1010
...raLong 1M Instruct Abliterated1048K / 32.1 GB49
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB70259
Zero Llama 3.1 8B Beta61048K / 16.1 GB71
Note: green Score (e.g. "73.2") means that the model is better than swap-uniba/LLaMAntino-3-ANITA-8B-Inst-DPO-ITA.