Instructions to use occiglot/occiglot-7b-eu5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use occiglot/occiglot-7b-eu5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="occiglot/occiglot-7b-eu5")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("occiglot/occiglot-7b-eu5") model = AutoModelForCausalLM.from_pretrained("occiglot/occiglot-7b-eu5") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use occiglot/occiglot-7b-eu5 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "occiglot/occiglot-7b-eu5" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "occiglot/occiglot-7b-eu5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/occiglot/occiglot-7b-eu5
- SGLang
How to use occiglot/occiglot-7b-eu5 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "occiglot/occiglot-7b-eu5" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "occiglot/occiglot-7b-eu5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "occiglot/occiglot-7b-eu5" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "occiglot/occiglot-7b-eu5", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use occiglot/occiglot-7b-eu5 with Docker Model Runner:
docker model run hf.co/occiglot/occiglot-7b-eu5
| # Config file for https://github.com/malteos/lm-datasets | |
| # | |
| # EU top-5 (en,fr,es,de,it) + code | |
| # target size: 300B tokens (train first for 200B tokens) | |
| # a fixed random seed for shuffling etc. | |
| seed: 0 | |
| # data split settings | |
| validation_ratio: 0.005 # number of documents in the split: len(dataset) * ratio | |
| validation_min_total_docs: 1_000 # to be used as validation set, the dataset must have at least n docs | |
| validation_max_split_docs: 1_000 # number of documents in validation split are capped at this numbers | |
| validation_min_split_docs: 10 # split must have at least this number of documents, otherwise it will be discarded | |
| tokenizer_train_ratio: 0.1 | |
| selected_source_ids: | |
| - starcoder | |
| selected_dataset_ids: | |
| # english | |
| - pes2o | |
| - math_amps | |
| - eurlex_en | |
| - wikipedia_20231101_en | |
| - wikibooks_en | |
| - wikiquote_en | |
| - wikinews_en | |
| - wikisource_en | |
| - wikivoyage_en | |
| - colossal_oscar_2015-14_en | |
| - colossal_oscar_2016-40_en | |
| - colossal_oscar_2017-43_en | |
| - colossal_oscar_2018-47_en | |
| - colossal_oscar_2019-22_en | |
| - colossal_oscar_2020-24_en | |
| - colossal_oscar_2020-45_en | |
| - colossal_oscar_2021-49_en | |
| - colossal_oscar_2022-27_en | |
| - colossal_oscar_2022-49_en | |
| - colossal_oscar_2023-14_en | |
| - colossal_oscar_2023-23_en | |
| - pile_of_law_r_legaladvice | |
| - pile_of_law_atticus_contracts | |
| - pile_of_law_un_debates | |
| - proof_pile2_open_web_math | |
| - parlamint_gb | |
| - redpajama_stackexchange | |
| # french | |
| - cabernet | |
| - eurlex_fr | |
| - legal_mc4_fr | |
| - wikipedia_20231101_fr | |
| - wikibooks_fr | |
| - wikiquote_fr | |
| - wikinews_fr | |
| - wikisource_fr | |
| - wikivoyage_fr | |
| - colossal_oscar_2015-14_fr | |
| - colossal_oscar_2016-40_fr | |
| - colossal_oscar_2017-43_fr | |
| - colossal_oscar_2018-47_fr | |
| - colossal_oscar_2019-22_fr | |
| - colossal_oscar_2020-24_fr | |
| - colossal_oscar_2020-45_fr | |
| - colossal_oscar_2021-49_fr | |
| - colossal_oscar_2022-27_fr | |
| - colossal_oscar_2022-49_fr | |
| - colossal_oscar_2023-14_fr | |
| - colossal_oscar_2023-23_fr | |
| - opensubtitles_fr | |
| - parlamint_fr | |
| # spanish | |
| - spanish_legal | |
| - eurlex_es | |
| - legal_mc4_es | |
| - wikipedia_20231101_es | |
| - wikibooks_es | |
| - wikiquote_es | |
| - wikinews_es | |
| - wikisource_es | |
| - wikivoyage_es | |
| - colossal_oscar_2015-14_es | |
| - colossal_oscar_2016-40_es | |
| - colossal_oscar_2017-43_es | |
| - colossal_oscar_2018-47_es | |
| - colossal_oscar_2019-22_es | |
| - colossal_oscar_2020-24_es | |
| - colossal_oscar_2020-45_es | |
| - colossal_oscar_2021-49_es | |
| - colossal_oscar_2022-27_es | |
| - colossal_oscar_2022-49_es | |
| - colossal_oscar_2023-14_es | |
| - colossal_oscar_2023-23_es | |
| - opensubtitles_es | |
| - parlamint_es | |
| # german | |
| - openlegaldata | |
| - dewac | |
| - eurlex_de | |
| - legal_mc4_de | |
| - wikipedia_20231101_de | |
| - wikibooks_de | |
| - wikiquote_de | |
| - wikinews_de | |
| - wikisource_de | |
| - wikivoyage_de | |
| - colossal_oscar_2015-14_de | |
| - colossal_oscar_2016-40_de | |
| - colossal_oscar_2017-43_de | |
| - colossal_oscar_2018-47_de | |
| - colossal_oscar_2019-22_de | |
| - colossal_oscar_2020-24_de | |
| - colossal_oscar_2020-45_de | |
| - colossal_oscar_2021-49_de | |
| - colossal_oscar_2022-27_de | |
| - colossal_oscar_2022-49_de | |
| - colossal_oscar_2023-14_de | |
| - colossal_oscar_2023-23_de | |
| - open_discourse_bundestag | |
| - tagesschau_2018_2023 | |
| - opensubtitles_de | |
| - parlamint_at | |
| # italian | |
| - itwac | |
| - eurlex_it | |
| - legal_mc4_it | |
| - wikipedia_20231101_it | |
| - wikibooks_it | |
| - wikiquote_it | |
| - wikinews_it | |
| - wikisource_it | |
| - wikivoyage_it | |
| - colossal_oscar_2015-14_it | |
| - colossal_oscar_2016-40_it | |
| - colossal_oscar_2017-43_it | |
| - colossal_oscar_2018-47_it | |
| - colossal_oscar_2019-22_it | |
| - colossal_oscar_2020-24_it | |
| - colossal_oscar_2020-45_it | |
| - colossal_oscar_2021-49_it | |
| - colossal_oscar_2022-27_it | |
| - colossal_oscar_2022-49_it | |
| - colossal_oscar_2023-14_it | |
| - colossal_oscar_2023-23_it | |
| - opensubtitles_it | |
| - parlamint_it | |
| - tatoeba_translation_en_fr | |
| - tatoeba_translation_en_es | |
| - tatoeba_translation_en_it | |
| - tatoeba_translation_fr_it | |
| - tatoeba_translation_es_fr | |
| - tatoeba_translation_es_it | |
| - tatoeba_translation_de_en | |
| - tatoeba_translation_de_fr | |
| - tatoeba_translation_de_es | |
| - tatoeba_translation_de_it | |
| - opus100_translation_de_en | |
| - opus100_translation_en_es | |
| - opus100_translation_en_fr | |
| - opus100_translation_en_it | |
| - wmt19_translation_de_en | |
| - wmt19_translation_fr_de | |
| sampling_factor_by_dataset_id: | |
| redpajama_stackexchange: 0.1 | |
| pes2o: 0.1 | |
| math_amps: 0.1 | |
| openlegaldata: 0.75 | |
| dewac: 0.05 | |
| itwac: 1 | |
| cabernet: 1 | |
| spanish_legal: 0.1 | |
| eurlex_de: 0.5 | |
| eurlex_en: 0.5 | |
| eurlex_es: 1 | |
| eurlex_fr: 1 | |
| eurlex_it: 1 | |
| legal_mc4_de: 0.1 | |
| legal_mc4_es: 0.25 | |
| legal_mc4_fr: 0.25 | |
| legal_mc4_it: 1 | |
| wikipedia_20231101_de: 2 | |
| wikibooks_de: 1 | |
| wikiquote_de: 1 | |
| wikinews_de: 2 | |
| wikisource_de: 1 | |
| wikivoyage_de: 1 | |
| wikipedia_20231101_en: 1 | |
| wikibooks_en: 1 | |
| wikiquote_en: 0.25 | |
| wikinews_en: 1 | |
| wikisource_en: 1 | |
| wikivoyage_en: 1 | |
| wikipedia_20231101_es: 2 | |
| wikibooks_es: 1 | |
| wikiquote_es: 1 | |
| wikinews_es: 2 | |
| wikisource_es: 1 | |
| wikivoyage_es: 1 | |
| wikipedia_20231101_fr: 2 | |
| wikibooks_fr: 1 | |
| wikiquote_fr: 1 | |
| wikinews_fr: 2 | |
| wikisource_fr: 1 | |
| wikivoyage_fr: 1 | |
| wikipedia_20231101_it: 2 | |
| wikibooks_it: 1 | |
| wikiquote_it: 1 | |
| wikinews_it: 2 | |
| wikisource_it: 1 | |
| wikivoyage_it: 1 | |
| colossal_oscar_2015-14_de: 1 | |
| colossal_oscar_2016-40_de: 0.95 | |
| colossal_oscar_2017-43_de: 0.1 | |
| colossal_oscar_2018-47_de: 0.1 | |
| colossal_oscar_2019-22_de: 0.1 | |
| colossal_oscar_2020-24_de: 0.1 | |
| colossal_oscar_2020-45_de: 0.1 | |
| colossal_oscar_2021-49_de: 0.1 | |
| colossal_oscar_2022-27_de: 0.1 | |
| colossal_oscar_2022-49_de: 0.1 | |
| colossal_oscar_2023-14_de: 0.95 | |
| colossal_oscar_2023-23_de: 1 | |
| colossal_oscar_2015-14_en: 0.05 | |
| colossal_oscar_2016-40_en: 0.05 | |
| colossal_oscar_2017-43_en: 0.001 | |
| colossal_oscar_2018-47_en: 0.001 | |
| colossal_oscar_2019-22_en: 0.001 | |
| colossal_oscar_2020-24_en: 0.001 | |
| colossal_oscar_2020-45_en: 0.001 | |
| colossal_oscar_2021-49_en: 0.001 | |
| colossal_oscar_2022-27_en: 0.001 | |
| colossal_oscar_2022-49_en: 0.001 | |
| colossal_oscar_2023-14_en: 0.05 | |
| colossal_oscar_2023-23_en: 0.05 | |
| colossal_oscar_2015-14_es: 1 | |
| colossal_oscar_2016-40_es: 1 | |
| colossal_oscar_2017-43_es: 0.25 | |
| colossal_oscar_2018-47_es: 0.1 | |
| colossal_oscar_2019-22_es: 0.1 | |
| colossal_oscar_2020-24_es: 0.1 | |
| colossal_oscar_2020-45_es: 0.1 | |
| colossal_oscar_2021-49_es: 0.1 | |
| colossal_oscar_2022-27_es: 0.1 | |
| colossal_oscar_2022-49_es: 0.3 | |
| colossal_oscar_2023-14_es: 1 | |
| colossal_oscar_2023-23_es: 1 | |
| colossal_oscar_2015-14_fr: 1 | |
| colossal_oscar_2016-40_fr: 1 | |
| colossal_oscar_2017-43_fr: 0.25 | |
| colossal_oscar_2018-47_fr: 0.25 | |
| colossal_oscar_2019-22_fr: 0.1 | |
| colossal_oscar_2020-24_fr: 0.1 | |
| colossal_oscar_2020-45_fr: 0.1 | |
| colossal_oscar_2021-49_fr: 0.1 | |
| colossal_oscar_2022-27_fr: 0.1 | |
| colossal_oscar_2022-49_fr: 0.75 | |
| colossal_oscar_2023-14_fr: 1 | |
| colossal_oscar_2023-23_fr: 1 | |
| starcoder_emacs-lisp: 0.1 | |
| starcoder_literate-haskell: 0.1 | |
| starcoder_shell: 0.1 | |
| starcoder_ada: 0.1 | |
| starcoder_erlang: 0.1 | |
| starcoder_lua: 0.1 | |
| starcoder_smalltalk: 0.1 | |
| starcoder_agda: 0.1 | |
| starcoder_f-sharp: 0.1 | |
| starcoder_makefile: 0.1 | |
| starcoder_solidity: 0.1 | |
| starcoder_alloy: 0.1 | |
| starcoder_fortran: 0.1 | |
| starcoder_maple: 0.1 | |
| starcoder_sparql: 0.1 | |
| starcoder_antlr: 0.1 | |
| starcoder_git-commits-cleaned: 0.05 | |
| starcoder_markdown: 0.05 | |
| starcoder_sql: 0.1 | |
| starcoder_applescript: 0.1 | |
| starcoder_github-issues-filtered-structured: 0.075 | |
| starcoder_mathematica: 0.1 | |
| starcoder_stan: 0.1 | |
| starcoder_assembly: 0.1 | |
| starcoder_glsl: 0.1 | |
| starcoder_matlab: 0.1 | |
| starcoder_standard-ml: 0.1 | |
| starcoder_augeas: 0.1 | |
| starcoder_go: 0.05 | |
| starcoder_ocaml: 0.1 | |
| starcoder_stata: 0.1 | |
| starcoder_awk: 0.1 | |
| starcoder_groovy: 0.1 | |
| starcoder_pascal: 0.1 | |
| starcoder_systemverilog: 0.1 | |
| starcoder_batchfile: 0.1 | |
| starcoder_haskell: 0.1 | |
| starcoder_perl: 0.1 | |
| starcoder_tcl: 0.1 | |
| starcoder_bluespec: 0.1 | |
| starcoder_html: 0.05 | |
| starcoder_php: 0.05 | |
| starcoder_tcsh: 0.1 | |
| starcoder_c: 0.05 | |
| starcoder_idris: 0.1 | |
| starcoder_powershell: 0.1 | |
| starcoder_tex: 0.1 | |
| starcoder_c-sharp: 0.05 | |
| starcoder_isabelle: 0.1 | |
| starcoder_prolog: 0.1 | |
| starcoder_thrift: 0.1 | |
| starcoder_clojure: 0.1 | |
| starcoder_java: 0.05 | |
| starcoder_protocol-buffer: 0.1 | |
| starcoder_typescript: 0.05 | |
| starcoder_cmake: 0.1 | |
| starcoder_java-server-pages: 0.1 | |
| starcoder_python: 0.05 | |
| starcoder_verilog: 0.1 | |
| starcoder_coffeescript: 0.1 | |
| starcoder_javascript: 0.05 | |
| starcoder_r: 0.1 | |
| starcoder_vhdl: 0.1 | |
| starcoder_common-lisp: 0.1 | |
| starcoder_json: 0.1 | |
| starcoder_racket: 0.1 | |
| starcoder_visual-basic: 0.1 | |
| starcoder_cpp: 0.05 | |
| starcoder_julia: 0.1 | |
| starcoder_restructuredtext: 0.1 | |
| starcoder_xslt: 0.1 | |
| starcoder_css: 0.1 | |
| starcoder_jupyter-scripts-dedup-filtered: 0.1 | |
| starcoder_rmarkdown: 0.1 | |
| starcoder_yacc: 0.1 | |
| starcoder_cuda: 0.1 | |
| starcoder_jupyter-structured-clean-dedup: 0.1 | |
| starcoder_ruby: 0.1 | |
| starcoder_yaml: 0.1 | |
| starcoder_dart: 0.1 | |
| starcoder_kotlin: 0.1 | |
| starcoder_rust: 0.1 | |
| starcoder_zig: 0.1 | |
| starcoder_dockerfile: 0.1 | |
| starcoder_lean: 0.1 | |
| starcoder_sas: 0.1 | |
| starcoder_elixir: 0.1 | |
| starcoder_literate-agda: 0.1 | |
| starcoder_scala: 0.1 | |
| starcoder_elm: 0.1 | |
| starcoder_literate-coffeescript: 0.1 | |
| starcoder_scheme: 0.1 | |
| pile_of_law_r_legaladvice: 1 | |
| pile_of_law_atticus_contracts: 0.25 | |
| pile_of_law_un_debates: 1 | |
| open_discourse_bundestag: 0.5 | |
| tagesschau_2018_2023: 1 | |
| proof_pile2_open_web_math: 0.25 | |
| tatoeba_translation_en_fr: 1 | |
| tatoeba_translation_en_es: 1 | |
| tatoeba_translation_en_it: 1 | |
| tatoeba_translation_fr_it: 1 | |
| tatoeba_translation_es_fr: 1 | |
| tatoeba_translation_es_it: 1 | |
| tatoeba_translation_de_en: 1 | |
| tatoeba_translation_de_fr: 1 | |
| tatoeba_translation_de_es: 1 | |
| tatoeba_translation_de_it: 1 | |
| opus100_translation_de_en: 1 | |
| opus100_translation_en_es: 1 | |
| opus100_translation_en_fr: 1 | |
| opus100_translation_en_it: 1 | |
| wmt19_translation_de_en: 1 | |
| wmt19_translation_fr_de: 1 | |
| opensubtitles_es: 1 | |
| opensubtitles_fr: 1 | |
| opensubtitles_de: 1 | |
| opensubtitles_it: 1 | |
| parlamint_es: 1 | |
| parlamint_it: 1 | |
| parlamint_at: 1 | |
| parlamint_fr: 1 | |
| parlamint_gb: 1 | |
| colossal_oscar_2015-14_it: 1 | |
| colossal_oscar_2016-40_it: 1 | |
| colossal_oscar_2017-43_it: 0.75 | |
| colossal_oscar_2018-47_it: 0.75 | |
| colossal_oscar_2019-22_it: 0.75 | |
| colossal_oscar_2020-24_it: 0.75 | |
| colossal_oscar_2020-45_it: 0.75 | |
| colossal_oscar_2021-49_it: 0.75 | |
| colossal_oscar_2022-27_it: 0.75 | |
| colossal_oscar_2022-49_it: 0.75 | |
| colossal_oscar_2023-14_it: 0.9 | |
| colossal_oscar_2023-23_it: 1 | |