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

Salamandra 7B Instruct by BSC-LT

 »  All LLMs  »  BSC-LT  »  Salamandra 7B Instruct   URL Share it on

  13840   
  Arxiv:1803.09010   Arxiv:1810.06694   Arxiv:1906.03741   Arxiv:1911.05507   Arxiv:2101.00027   Arxiv:2207.00220   Arxiv:2402.06619   Arxiv:2403.14009   Arxiv:2403.20266   Arxiv:2406.17557   Arxiv:2502.08489   Autotrain compatible Base model:bsc-lt/salamandra-7... Base model:finetune:bsc-lt/sal...   Bg   Ca   Code   Conversational   Cs   Cy   Da Dataset:ai-team-uoa/greek lega...   Dataset:allenai/pes2o   Dataset:bigcode/starcoderdata Dataset:bjoernp/tagesschau-201... Dataset:community-datasets/hrw... Dataset:danish-foundation-mode... Dataset:eleutherai/the pile de...   Dataset:hitz/euscrawl   Dataset:hitz/latxa-corpus-v1.1 Dataset:hoskinson-center/proof... Dataset:huggingfacefw/fineweb-...   Dataset:joelito/legal-mc4 Dataset:joelniklaus/eurlex res... Dataset:oscar-corpus/colossal-... Dataset:pile-of-law/pile-of-la...   Dataset:pleias/french-pd-books Dataset:pleias/french-pd-newsp...   Dataset:portulan/parlamento-pt   Dataset:projecte-aina/catalog Dataset:togethercomputer/redpa...   Dataset:ufrgs/brwac   De   El   En   Endpoints compatible   Es   Et   Eu   Fi   Fr   Ga   Gl   Hr   Hu   Instruct   It   Llama   Lt   Lv   Mt   Nl   Nn   Oc   Pl   Pt   Region:us   Ro   Ru   Safetensors   Sh   Sharded   Sk   Sl   Sr   Sv   Tensorflow   Uk
Model Card on HF 🤗: https://huggingface.co/BSC-LT/salamandra-7b-instruct 

Salamandra 7B Instruct Benchmarks

MMLU Pro: 8.95
GPQA: 1.9
MUSR: 10.21
BBH: 14.69
IFEval: 24.51 vs 88 (so35)-72.1%
MATH Lvl 5: 0.83
LLME Score: 0.31593
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Salamandra 7B Instruct (BSC-LT/salamandra-7b-instruct)

Salamandra 7B Instruct Parameters and Internals

Model Type 
transformer-based, decoder-only, language model, instruction-tuned
Use Cases 
Areas:
Research, Commercial applications
Primary Use Cases:
Language generation, General-purpose assistance
Limitations:
Not intended for malicious uses, Current version not aligned to avoid sensitive topics
Considerations:
Users should be aware of and mitigate model limitations.
Additional Notes 
Users are responsible for mitigating risks and ensuring compliance with regulations.
Supported Languages 
bg (high proficiency), ca (high proficiency), code (included), cs (high proficiency), cy (high proficiency), da (high proficiency), de (high proficiency), el (high proficiency), en (high proficiency), es (high proficiency), et (high proficiency), eu (high proficiency), fi (high proficiency), fr (high proficiency), ga (high proficiency), gl (high proficiency), hr (high proficiency), hu (high proficiency), it (high proficiency), lt (high proficiency), lv (high proficiency), mt (high proficiency), nl (high proficiency), nn (high proficiency), no (high proficiency), oc (high proficiency), pl (high proficiency), pt (high proficiency), ro (high proficiency), ru (high proficiency), sh (high proficiency), sk (high proficiency), sl (high proficiency), sr (high proficiency), sv (high proficiency), uk (high proficiency)
Training Details 
Data Sources:
Colossal OSCAR, Starcoder, Spanish Crawling, Parlamint corpus, Wikimedia dumps, OpenSubtitlesv2016, MaCoCu web corpus, EurLEX-Resources, MC4-Legal, CURLICAT Corpus, CATalog, SYN v9, Welsh-GOV, DaNewsroom, The Danish Parliament Corpus 2009 - 2017, v1, Danish GigaWord, DK-CLARIN Reference Corpus of General Danish, Open Legal Data - German court decisions and laws, DeWaC, Greek Web Corpus, Greek Legal Code, BIGPATENT, peS2o, PG-19, proof-pile, Auxiliary Mathematics Problems and Solutions (AMPS), Pile of Law, RedPajama-Data T1, The Pile, Spanish Legal Domain Corpora, HPLTDatasets v1 - Spanish, Biomedical, Scientific, Estonian National Corpus 2021, Estonian Reference Corpus, EusCrawl, Yle Finnish News Archive, CaBeRnet, French Public Domain Newspapers, French Public Domain Books, The Gaois bilingual corpus of English-Irish legislation, Irish Universal Dependencies, CorpusNÓS, hrWaC 2.1, ITWaC, Korpus Malti, SoNaR Corpus NC 1.2, Norwegian Colossal Corpus, Occitan Corpus, Polish Parliamentary Corpus, NKJP-PodkorpusMilionowy-1.2, Brazilian Portuguese Web as Corpus, ParlamentoPT, MARCELL Romanian legislative subcorpus v2, Korpus slovenských právnych predpisov, od-justice 2.0, Corpus of academic Slovene KAS, slWaC web corpus, SrpKorSubset, The Swedish Culturomics Gigaword Corpus, Corpus of laws and legal acts of Ukraine
Data Volume:
7.8 trillion tokens
Methodology:
pre-training with highly curated data, instruction-tuning for general-purpose assistance
Context Length:
8192
Hardware Used:
MareNostrum 5, a pre-exascale EuroHPC supercomputer, Nvidia Hopper GPUs, Intel Sapphire Rapids
Model Architecture:
Transformer-based decoder-only
Safety Evaluation 
Methodologies:
LLM-judge for multilingual evaluation, BBQ dataset testing for societal biases, ARC Multiple Choice Question dataset for positional effects
Findings:
High performance in disambiguated settings, Presence of societal biases in ambiguous settings, Weak primacy effects for cognitive bias
Risk Categories:
Undesired societal and cognitive biases, Potential generation of harmful content
Ethical Considerations:
Bias and safety improvements planned for further alignment
Responsible Ai Considerations 
Fairness:
Detected societal biases need alignment and fairness improvements.
Transparency:
Full model details, training scripts, and data sources are disclosed.
Accountability:
Developers using the model are responsible for mitigating risks.
Mitigation Strategies:
Further RLHF tuning and ethical audits planned.
Release Notes 
Version:
7B
Date:
2024-09-30
Notes:
Multilingual transformer-based model with 7.8 trillion tokens of data and instruction-tuning.
LLM NameSalamandra 7B Instruct
Repository 🤗https://huggingface.co/BSC-LT/salamandra-7b-instruct 
Base Model(s)  Salamandra 7B   BSC-LT/salamandra-7b
Model Size7b
Required VRAM15.6 GB
Updated2025-03-22
MaintainerBSC-LT
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   3.5 GB: 3-of-4   2.1 GB: 4-of-4
Supported Languagesbg ca code cs cy da de el en es et eu fi fr ga gl hr hu it lt lv mt nl nn oc pl pt ro ru sh sk sl sr sv uk
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Salamandra 7B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
1241024K / 16.1 GB930
... Qwen2.5llamaify 7B V23.1 200K195K / 15.2 GB19863
SuperNeuralDreadDevil 8B128K / 16.1 GB821
Falcon3 7B Instruct32K / 14.8 GB5912764
Falcon3 Jessi V0.4 7B Slerp32K / 14.9 GB1509
Jessi V0.4 Falcon3 7B Instruct32K / 14.8 GB390
Jessi V0.6 Falcon3 7B Instruct32K / 14.8 GB300
Jessi V0.5 Falcon3 7B Instruct32K / 14.8 GB350
...noAi 7B French Instruct 20250232K / 14.8 GB320
Falcon3 Ultraset32K / 14.8 GB220
Note: green Score (e.g. "73.2") means that the model is better than BSC-LT/salamandra-7b-instruct.

Rank the Salamandra 7B Instruct 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? 45429 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 v20241227
  Support LLM Explorer