commit 5197abcc1ae88e864317bcf85544f1d37652012d Author: ModelHub XC Date: Fri May 22 22:02:30 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: lianghsun/Llama-3.2-Taiwan-3B-Instruct Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5c74fd7 --- /dev/null +++ b/README.md @@ -0,0 +1,1412 @@ +--- +license: llama3.2 +language: +- zh +- en +- it +- de +- fr +- ja +- ko +base_model: +- meta-llama/Llama-3.2-3B +- lianghsun/Llama-3.2-Taiwan-3B +datasets: +- lianghsun/tw-emergency-medicine-bench +- lianghsun/tw-legal-nlp +- lianghsun/tw-legal-synthetic-qa +- lianghsun/tw-law-article-qa +- lianghsun/tw-judgment-qa +- lianghsun/tw-judgment-gist-chat +- lianghsun/tw-bar-examination-2020-chat +- lianghsun/tw-structured-law-article +- lianghsun/tw-judgment-gist-chat +- lianghsun/tw-contract-review-chat +- lianghsun/reasoning-base-20k-chat +- lianghsun/vulnerability-mitigation-qa-zh_tw +- lianghsun/tw-instruct +- rombodawg/Everything_Instruct_Multilingual +- xzuyn/manythings-translations-alpaca +- neural-bridge/rag-dataset-12000 +- minyichen/glaive_toolcall_zh_tw +pipeline_tag: text-generation +library_name: transformers +tags: +- Taiwan +- ROC +- zh-tw +- instruct +- chat +- llama3.2 +- SLM +model-index: +- name: Llama-3.2-Taiwan-3B-Instruct + results: + - task: + type: text-generation + name: Single Choice Question + dataset: + type: lianghsun/tw-legal-benchmark-v1 + name: tw-legal-benchmark-v1 + metrics: + - name: single choice + type: accuracy + value: 31.1 + - task: + type: text-generation + name: Single Choice Question + dataset: + type: lianghsun/Formosa-bench + name: (Society) Formosa Taiwan Knowledge Bench + config: society + split: test + revision: v2024.11.27 + metrics: + - name: single choice + type: accuracy + value: 60.42 + - task: + type: text-generation + name: Single Choice Question + dataset: + type: lianghsun/Formosa-bench + name: (Governmnt) Formosa Taiwan Knowledge Bench + config: governmnt + split: test + revision: v2024.11.27 + metrics: + - name: single choice + type: accuracy + value: 44.25 + - task: + type: text-generation + name: Single Choice Question + dataset: + type: lianghsun/Formosa-bench + name: (Geography) Formosa Taiwan Knowledge Bench + config: geography + split: test + revision: v2024.11.27 + metrics: + - name: single choice + type: accuracy + value: 47.54 + - task: + type: text-generation + name: Single Choice Question + dataset: + type: lianghsun/Formosa-bench + name: (History) Formosa Taiwan Knowledge Bench + config: history + split: test + revision: v2024.11.27 + metrics: + - name: single choice + type: accuracy + value: 60 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (geography_of_taiwan) tmmlu++ + config: geography_of_taiwan + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 36.2 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (dentistry) tmmlu++ + config: dentistry + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 33.83 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (technical) tmmlu++ + config: technical + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 35.07 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (statistics_and_machine_learning) tmmlu++ + config: statistics_and_machine_learning + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 28.57 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (clinical_psychology) tmmlu++ + config: clinical_psychology + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 29.6 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (tve_design) tmmlu++ + config: tve_design + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 38.54 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (three_principles_of_people) tmmlu++ + config: three_principles_of_people + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 48.2 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (introduction_to_law) tmmlu++ + config: introduction_to_law + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 29.96 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (linear_algebra) tmmlu++ + config: linear_algebra + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 21.43 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (agriculture) tmmlu++ + config: agriculture + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 24.5 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (jce_humanities) tmmlu++ + config: jce_humanities + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 38.89 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (music) tmmlu++ + config: music + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 25.9 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (secondary_physics) tmmlu++ + config: secondary_physics + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 33.04 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (physics) tmmlu++ + config: physics + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 27.84 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (advance_chemistry) tmmlu++ + config: advance_chemistry + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 27.64 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (junior_science_exam) tmmlu++ + config: junior_science_exam + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 30.05 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (veterinary_pathology) tmmlu++ + config: veterinary_pathology + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 25.09 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (financial_analysis) tmmlu++ + config: financial_analysis + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 25.13 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (national_protection) tmmlu++ + config: national_protection + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 42.65 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (macroeconomics) tmmlu++ + config: macroeconomics + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 26.76 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (politic_science) tmmlu++ + config: politic_science + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 27.44 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (ttqav2) tmmlu++ + config: ttqav2 + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 61.06 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (junior_chinese_exam) tmmlu++ + config: junior_chinese_exam + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 30.86 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (traditional_chinese_medicine_clinical_medicine) tmmlu++ + config: traditional_chinese_medicine_clinical_medicine + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 25.9 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (junior_math_exam) tmmlu++ + config: junior_math_exam + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 21.71 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (auditing) tmmlu++ + config: auditing + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 21.82 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (anti_money_laundering) tmmlu++ + config: anti_money_laundering + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 37.31 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (pharmacology) tmmlu++ + config: pharmacology + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 30.68 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (trust_practice) tmmlu++ + config: trust_practice + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 28.18 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (tve_mathematics) tmmlu++ + config: tve_mathematics + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 18.67 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (human_behavior) tmmlu++ + config: human_behavior + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 32.04 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (pharmacy) tmmlu++ + config: pharmacy + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 22.76 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (tve_chinese_language) tmmlu++ + config: tve_chinese_language + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 36.65 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (optometry) tmmlu++ + config: optometry + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 25.11 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (physical_education) tmmlu++ + config: physical_education + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 30.73 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (organic_chemistry) tmmlu++ + config: organic_chemistry + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 35.78 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (tve_natural_sciences) tmmlu++ + config: tve_natural_sciences + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 33.73 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (education) tmmlu++ + config: education + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 37.9 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (mechanical) tmmlu++ + config: mechanical + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 42.37 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (taiwanese_hokkien) tmmlu++ + config: taiwanese_hokkien + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 14.73 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (nautical_science) tmmlu++ + config: nautical_science + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 30.49 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (business_management) tmmlu++ + config: business_management + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 39.57 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (logic_reasoning) tmmlu++ + config: logic_reasoning + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 27.34 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (marketing_management) tmmlu++ + config: marketing_management + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 39.78 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (economics) tmmlu++ + config: economics + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 25.95 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (basic_medical_science) tmmlu++ + config: basic_medical_science + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 28.41 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (occupational_therapy_for_psychological_disorders) tmmlu++ + config: occupational_therapy_for_psychological_disorders + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 35.73 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (general_principles_of_law) tmmlu++ + config: general_principles_of_law + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 31.13 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (junior_chemistry) tmmlu++ + config: junior_chemistry + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 24.88 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (veterinary_pharmacology) tmmlu++ + config: veterinary_pharmacology + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 36.3 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (educational_psychology) tmmlu++ + config: educational_psychology + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 33.52 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (finance_banking) tmmlu++ + config: finance_banking + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 32.59 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (official_document_management) tmmlu++ + config: official_document_management + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 32.43 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (fire_science) tmmlu++ + config: fire_science + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 30.65 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (junior_social_studies) tmmlu++ + config: junior_social_studies + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 47.62 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (accounting) tmmlu++ + config: accounting + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 20.94 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (engineering_math) tmmlu++ + config: engineering_math + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 27.18 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (education_(profession_level)) tmmlu++ + config: education_(profession_level) + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 24.07 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (chinese_language_and_literature) tmmlu++ + config: chinese_language_and_literature + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 27.64 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (management_accounting) tmmlu++ + config: management_accounting + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 24.19 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (culinary_skills) tmmlu++ + config: culinary_skills + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 39.38 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (administrative_law) tmmlu++ + config: administrative_law + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 25.71 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (insurance_studies) tmmlu++ + config: insurance_studies + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 33.42 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (real_estate) tmmlu++ + config: real_estate + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 22.83 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (computer_science) tmmlu++ + config: computer_science + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 31.61 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (taxation) tmmlu++ + config: taxation + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 27.47 + - task: + type: question-answering + name: Single Choice Question + dataset: + type: ikala/tmmluplus + name: (trade) tmmlu++ + config: trade + split: test + revision: c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + metrics: + - name: single choice + type: accuracy + value: 20.32 +widget: +- text: 中華民國憲法第一條 +metrics: +- accuracy +--- + +# Model Card for lianghsun/Llama-3.2-Taiwan-3B-Instruct + + +[👋 歡迎加入 Discord 討論 🎉] + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/618dc56cbc345ca7bf95f3cd/v_cfMxTtVE6_eh0rzcy5L.png) +*圖像生成來自 [OpenArt](https://openart.ai/home):An anime-style 🦙 standing proudly atop the summit of Taiwan’s [Yushan (Jade Mountain)](https://zh.wikipedia.org/wiki/%E7%8E%89%E5%B1%B1), gazing forward.* + +採用 [lianghsun/Llama-3.2-Taiwan-3B](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B) 為[基礎模型(foundation model)](https://en.wikipedia.org/wiki/Foundation_model),使用大量[中華民國台灣](https://zh.wikipedia.org/zh-tw/%E8%87%BA%E7%81%A3)的繁體中文對話集和多國語言對話集進行模型[指令微調(instruction fine-tuning)](https://www.ibm.com/topics/instruction-tuning)和多輪迭代[直接偏好優化(direct preference optimization, DPO)](https://arxiv.org/abs/2305.18290),旨在訓練出具有中華民國台灣知識及風格的[小語言模型(small langugae model, SLM)](https://www.ibm.com/think/topics/small-language-models)之對話模型。 + +
+ Model Change Log + + | Update Date | Model Version | Key Changes | + |--------------|-----------------------|-------------------------------------| + | 2025/01/01 | v2025.01.01 | Fine-tuning is based on the [foundation model](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B) version v2024.12.28, and it uses self-prepared instruction datasets for this round of fine-tuning. | + | 2024/12/13 | v2024.12.13 | Completed 1st round DPO training (10/10 epochs). Preparing for next round DPO training. | + | 2024/11/27 | v2024.11.27 | Completed SFT training (5/5 epochs). Preparing for multi-round DPO training. | + | 2024/11/25 | v2024.11.25 | Updated model version to v2024.11.25, training progressed to (3/5) epochs. Still in SFT stage, DPO training remains pending. | + | 2024/11/22 | v2024.11.22 | Initial upload: Model version v2024.11.22, training completed up to (1/5) epochs. Currently trained only on SFT, DPO training not yet performed. | + +
+ +## Model Details + +### Model Description + + +- **Developed by:** [Huang Liang Hsun](https://www.linkedin.com/in/lianghsunhuang) +- **Model type:** LlamaForCausalLM +- **Language(s) (NLP):** Tranditional Chinese (zh-tw), English +- **License:** [llama3.2](https://huggingface.co/meta-llama/Llama-3.2-1B/blob/main/LICENSE.txt) +- **Fine-tuned from model:** [lianghsun/Llama-3.2-Taiwan-3B](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B) + +### Model Sources + + +- **Repository:** [lianghsun/Llama-3.2-Taiwan-3B](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B) +- **Paper:** (WIP, show me the time) +- **Playground:** [🦉 Tawian SmolLM Chat](https://huggingface.co/spaces/lianghsun/tw-smol-chat) 👈🏼 來玩看看 😻 +- **Demo:** +```yaml +user: 請介紹台灣 +assistant: 台灣,位於亞洲東部,地處太平洋與菲律賓海之間,面積約36,000平方公里,人口約2,300萬,是民主自由的國家,經濟實力強勁,擁有世界第10大經濟體。台灣以美食、文化、自然美景著稱,還有豐富的歷史與傳統,吸引全球遊客。台灣語為官方語言,但中文也廣為使用,英語也常用於國際交流。台灣政治多元,執政黨為民進黨,台灣是全球科技產業的重鎮,擁有先進的製造業與服務業。台灣氣候溫暖潮濕,四季分明,夏季炎熱,冬季涼爽,雨季則在5月至10月。台灣的美食以小吃為主,如滷肉飯、珍珠 +``` + +## Uses + + + +### Direct Use + + +本模型已經具備有繁體中文對話能力,使用者可以直接部署推論端點使用。 + +### Downstream Use + + +若需強化模型在特定領域的知識,可透過微調進一步提升其性能與專業能力。 + +### Out-of-Scope Use + + +本模型旨在提供資訊,不參與任何政治或法律問題的評斷或立場表達。 + +## Bias, Risks, and Limitations + + +語言模型的生成內容可能因訓練集的多樣性而帶有偏見、特定立場,或包含與事實不符的言論,請使用者務必在使用過程中仔細確認內容的準確性與中立性。 + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +要使用 [vLLM Docker image](https://docs.vllm.ai/en/latest/serving/deploying_with_docker.html) 來啟動此模型,您可以按照以下操作: +```bash +docker run --runtime nvidia --gpus all \ + -v ~/.cache/huggingface:/root/.cache/huggingface \ + --env "HUGGING_FACE_HUB_TOKEN=" \ + -p 8000:8000 \ + --ipc=host \ + vllm/vllm-openai:latest \ + --model lianghsun/Llama-3.2-Taiwan-3B-Instruct +``` + +請注意,如果想要使用不同版本的 checkpoint,請加上 `--revision ` +```bash +docker run --runtime nvidia --gpus all \ + -v ~/.cache/huggingface:/root/.cache/huggingface \ + --env "HUGGING_FACE_HUB_TOKEN=" \ + -p 8000:8000 \ + --ipc=host \ + vllm/vllm-openai:latest \ + --model lianghsun/Llama-3.2-Taiwan-3B-Instruct --revision +``` + +## Training Details + +### Training Data + + + +
+ 繁體中文對話資料集 + + - [lianghsun/tw-legal-nlp](https://huggingface.co/datasets/lianghsun/tw-legal-nlp) + - [lianghsun/tw-legal-synthetic-qa](https://huggingface.co/datasets/lianghsun/tw-legal-synthetic-qa) + - [lianghsun/tw-law-article-qa](https://huggingface.co/datasets/lianghsun/tw-law-article-qa) + - [lianghsun/tw-judgment-qa](https://huggingface.co/datasets/lianghsun/tw-judgment-qa) + - [lianghsun/tw-bar-examination-2020-chat](https://huggingface.co/datasets/lianghsun/tw-bar-examination-2020-chat) + - [lianghsun/tw-structured-law-article](https://huggingface.co/datasets/lianghsun/tw-structured-law-article) + - [lianghsun/tw-judgment-gist-chat](https://huggingface.co/datasets/lianghsun/tw-judgment-gist-chat) + - [lianghsun/vulnerability-mitigation-qa-zh_tw](https://huggingface.co/datasets/lianghsun/vulnerability-mitigation-qa-zh_tw) + - [lianghsun/tw-legal-qa-chat](https://huggingface.co/datasets/lianghsun/tw-legal-qa-chat) + - [lianghsun/reasoning-base-20k-chat](https://huggingface.co/datasets/lianghsun/reasoning-base-20k-chat) + - [lianghsun/tw-contract-review-chat](https://huggingface.co/datasets/lianghsun/tw-contract-review-chat) + - [lianghsun/tw-legal-methodology-chat](https://huggingface.co/datasets/lianghsun/tw-legal-methodology-chat) + - [minyichen/glaive_toolcall_zh_tw](https://huggingface.co/datasets/minyichen/glaive_toolcall_zh_tw) + +
+ +
+ 多國語系對話資料集 + + - [rombodawg/Everything_Instruct_Multilingual](https://huggingface.co/datasets/rombodawg/Everything_Instruct_Multilingual) + - [xzuyn/manythings-translations-alpaca](https://huggingface.co/datasets/xzuyn/manythings-translations-alpaca) + - [neural-bridge/rag-dataset-12000](https://huggingface.co/datasets/neural-bridge/rag-dataset-12000) + +
+ +### Training Procedure + + + +#### Preprocessing + +(WIP) + +#### Training Hyperparameters + +
+ SFT stage for v2024.11.27 + + **Note:** 以下包含 `v2024.11.22` 和 `v2025.11.25` 的超參數設定 + - **learning_rate:** 5e-05 + - **min_learning_rate:** 5e-07 + - **train_batch_size:** 105 + - **seed:** 42 + - **distributed_type:** multi-GPU + - **num_devices:** 4 + - **gradient_accumulation_steps:** 50 + - **total_train_batch_size:** 21,000 + - **optimizer:** Adam with betas=(0.9,0.999) and epsilon=1e-08 + - **lr_scheduler_type:** cosine + - **lr_scheduler_warmup_ratio:** 0.01 + - **num_epochs:** 5.0 + - **global_step:** 590 +
+ +#### Speeds, Sizes, Times + + +
+ SFT stage for v2024.11.27 + + **Note:** 以下包含 `v2024.11.22` 和 `v2025.11.25` 的超參數設定 + - **Duration**: 5 days, 16:15:11.17 + - **Train runtime**: 490,511.1789 + - **Train samples per second**: 25.37 + - **Train steps per second**: 0.001 + - **Total training FLOPs**: 26,658,386,120,540,160 + - **Train loss**: 0.8533 +
+ +## Evaluation + + + +### Testing Data, Factors & Metrics + +
+ Formosa Taiwan Knowledge Bench + + #### Testing Data + + + + [lianghsun/Formosa-bench](https://huggingface.co/datasets/lianghsun/Formosa-bench) + + #### Factors + + + + [More Information Needed] + + #### Metrics + + + + [More Information Needed] + + ### Results + + [More Information Needed] + + #### Summary + +
+ +
+ lianghsun/tw-legal-benchmark-v1 + + #### Testing Data + + + + - **Dataset:** [lianghsun/tw-legal-benchmark-v1](https://huggingface.co/datasets/lianghsun/tw-legal-benchmark-v1) + - **Revision:** 66c3a5f3ff2298f6a1cf23201070b5317bdd1893 + + #### Factors + + + + [More Information Needed] + + #### Metrics + + + Accuracy + + ### Results + + - **Model Revision:** v2024.11.27 + + | **Subset** | **Split** | **Score** | + |--------------|-------|-------| + | [lianghsun/tw-legal-benchmark-v1](https://huggingface.co/datasets/lianghsun/tw-legal-benchmark-v1/blob/main/benchmark.csv) | train | 31.1 | + + #### Summary + +
+ +
+ tmmlu++ + + #### Testing Data + + + - **Dataset:** [ikala/tmmluplus](https://huggingface.co/datasets/ikala/tmmluplus) + - **Revision:** c0e8ae955997300d5dbf0e382bf0ba5115f85e8c + + #### Factors + + + [More Information Needed] + + #### Metrics + + + Accuracy + + ### Results + + - **Model Revision:** v2024.11.27 + + | **Subset** | **Split** | **Score** | + |--------------|-------|-------| + | [geography_of_taiwan](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/geography_of_taiwan_test.csv) | test | 36.2 | + | [dentistry](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/dentistry_test.csv) | test | 33.83 | + | [technical](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/technical_test.csv) | test | 35.07 | + | [statistics_and_machine_learning](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/statistics_and_machine_learning_test.csv) | test | 28.57 | + | [clinical_psychology](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/clinical_psychology_test.csv) | test | 29.6 | + | [tve_design](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/tve_design_test.csv) | test | 38.54 | + | [three_principles_of_people](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/three_principles_of_people_test.csv) | test | 48.2 | + | [introduction_to_law](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/introduction_to_law_test.csv) | test | 29.96 | + | [linear_algebra](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/linear_algebra_test.csv) | test | 21.43 | + | [agriculture](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/agriculture_test.csv) | test | 24.5 | + | [jce_humanities](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/jce_humanities_test.csv) | test | 38.89 | + | [music](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/music_test.csv) | test | 25.9 | + | [secondary_physics](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/secondary_physics_test.csv) | test | 33.04 | + | [physics](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/physics_test.csv) | test | 27.84 | + | [advance_chemistry](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/advance_chemistry_test.csv) | test | 27.64 | + | [junior_science_exam](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/junior_science_exam_test.csv) | test | 30.05 | + | [veterinary_pathology](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/veterinary_pathology_test.csv) | test | 25.09 | + | [financial_analysis](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/financial_analysis_test.csv) | test | 25.13 | + | [national_protection](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/national_protection_test.csv) | test | 42.65 | + | [macroeconomics](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/macroeconomics_test.csv) | test | 26.76 | + | [politic_science](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/politic_science_test.csv) | test | 27.44 | + | [ttqav2](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/ttqav2_test.csv) | test | 61.06 | + | [junior_chinese_exam](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/junior_chinese_exam_test.csv) | test | 30.86 | + | [traditional_chinese_medicine_clinical_medicine](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/traditional_chinese_medicine_clinical_medicine_test.csv) | test | 25.9 | + | [junior_math_exam](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/junior_math_exam_test.csv) | test | 21.71 | + | [auditing](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/auditing_test.csv) | test | 21.82 | + | [anti_money_laundering](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/anti_money_laundering_test.csv) | test | 37.31 | + | [pharmacology](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/pharmacology_test.csv) | test | 30.68 | + | [trust_practice](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/trust_practice_test.csv) | test | 28.18 | + | [tve_mathematics](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/tve_mathematics_test.csv) | test | 18.67 | + | [human_behavior](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/human_behavior_test.csv) | test | 32.04 | + | [pharmacy](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/pharmacy_test.csv) | test | 22.76 | + | [tve_chinese_language](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/tve_chinese_language_test.csv) | test | 36.65 | + | [optometry](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/optometry_test.csv) | test | 25.11 | + | [physical_education](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/physical_education_test.csv) | test | 30.73 | + | [organic_chemistry](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/organic_chemistry_test.csv) | test | 35.78 | + | [tve_natural_sciences](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/tve_natural_sciences_test.csv) | test | 33.73 | + | [education](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/education_test.csv) | test | 37.9 | + | [mechanical](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/mechanical_test.csv) | test | 42.37 | + | [taiwanese_hokkien](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/taiwanese_hokkien_test.csv) | test | 14.73 | + | [nautical_science](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/nautical_science_test.csv) | test | 30.49 | + | [business_management](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/business_management_test.csv) | test | 39.57 | + | [logic_reasoning](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/logic_reasoning_test.csv) | test | 27.34 | + | [marketing_management](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/marketing_management_test.csv) | test | 39.78 | + | [economics](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/economics_test.csv) | test | 25.95 | + | [basic_medical_science](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/basic_medical_science_test.csv) | test | 28.41 | + | [occupational_therapy_for_psychological_disorders](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/occupational_therapy_for_psychological_disorders_test.csv) | test | 35.73 | + | [general_principles_of_law](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/general_principles_of_law_test.csv) | test | 31.13 | + | [junior_chemistry](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/junior_chemistry_test.csv) | test | 24.88 | + | [veterinary_pharmacology](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/veterinary_pharmacology_test.csv) | test | 36.3 | + | [educational_psychology](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/educational_psychology_test.csv) | test | 33.52 | + | [finance_banking](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/finance_banking_test.csv) | test | 32.59 | + | [official_document_management](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/official_document_management_test.csv) | test | 32.43 | + | [fire_science](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/fire_science_test.csv) | test | 30.65 | + | [junior_social_studies](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/junior_social_studies_test.csv) | test | 47.62 | + | [accounting](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/accounting_test.csv) | test | 20.94 | + | [engineering_math](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/engineering_math_test.csv) | test | 27.18 | + | [education_(profession_level)](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/education_(profession_level)_test.csv) | test | 24.07 | + | [chinese_language_and_literature](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/chinese_language_and_literature_test.csv) | test | 27.64 | + | [management_accounting](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/management_accounting_test.csv) | test | 24.19 | + | [culinary_skills](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/culinary_skills_test.csv) | test | 39.38 | + | [administrative_law](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/administrative_law_test.csv) | test | 25.71 | + | [insurance_studies](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/insurance_studies_test.csv) | test | 33.42 | + | [real_estate](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/real_estate_test.csv) | test | 22.83 | + | [computer_science](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/computer_science_test.csv) | test | 31.61 | + | [taxation](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/taxation_test.csv) | test | 27.47 | + | [trade](https://huggingface.co/datasets/ikala/tmmluplus/blob/main/data/trade_test.csv) | test | 20.32 | + + + #### Summary + 模型版號 `v2024.11.27`,無論是基礎模型([lianghsun/Llama-3.2-Taiwan-3B](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B))還是指令微調模型([lianghsun/Llama-3.2-Taiwan-3B-Instruct](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B-Instruct)),均未接受過 tmmlu++ 資料集的訓練,以確保測試的公平性。經測試,目前該模型在 tmmlu++ 上表現普遍不佳,未達及格分數,可能需要加入專業領域的資料集來強化基礎模型能力。 + +
+ +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + +- **Hardware Type:** 🚀 +- **Hours used:** ⏳⏳⌛ +- **Cloud Provider:** [鴻鵠國際股份有限公司](https://www.honghutech.com/) +- **Compute Region:** 🇹🇼 +- **Carbon Emitted:** ♻️ + +## Technical Specifications + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +- **CPU count:** 32 +- **Logical CPU count:** 64 +- **GPU count:** 4 +- **GPU type:** NVIDIA H100 NVL + +#### Software + +- **OS version:** Linux-5.15.0-124-generic-x86_64-with-glibc2.35 +- **Python version:** 3.12.7 + +## Citation + + +```bibtex +@misc{lianghsun2024llama32taiwan3binstruct, + author = {Huang, Liang Hsun}, + title = {Llama-3.2-Taiwan-3B-Instruct}, + year = {2024}, + publisher = {Hugging Face}, + howpublished = {\url{https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B-Instruct}}, + note = {Accessed: 2024-11-25} +} +``` + +## Glossary [optional] + + +N/A + +## More Information + +### Acknowledge +![image/png](https://cdn-uploads.huggingface.co/production/uploads/618dc56cbc345ca7bf95f3cd/28u7rOLoeUgn67clYEKuZ.png) +在此致謝[鴻鵠國際股份有限公司](https://www.honghutech.com/)蔡長明先生無償地贊助算力,以及曾經幫忙過:廖振翔、chweng、Ben、kevin、Maxxchu、Lam 和陳林彥…等朋友們,才能讓這個模型得以訓練完成,提供算力者乃人生父母。 + +### Usage +如果你基於此指令模型進行微調,希望能不吝嗇在 **模型卡片(model card)** 裡標註 **基礎模型** 為: +```yaml +base_model: lianghsun/Llama-3.2-Taiwan-3B-Instruct +``` + +標註和 ❤️ 是給予我們最大的鼓勵,謝謝。😀 + +## Model Card Authors + +[Huang Liang Hsun](https://www.linkedin.com/in/lianghsunhuang) + +## Model Card Contact + +[Huang Liang Hsun](https://www.linkedin.com/in/lianghsunhuang) + +### Framework versions + +- Transformers 4.45.2 +- Pytorch 2.4.1+cu121 +- Datasets 2.21.0 +- Tokenizers 0.20.0 diff --git a/config.json b/config.json new file mode 100644 index 0000000..069125f --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "_name_or_path": "lianghsun/Llama-3.2-Taiwan-3B-Instruct", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 24, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.1", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..eab5082 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.46.1" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..aa15aa7 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c114557d56bfbec77c9c763cc71c1a04c1668566636cfe4d1d489f3ddb9f4ff7 +size 4965799096 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..a7cdf29 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e20fae2caad0bd2dadabd50a7e5524a4421ecfe29b4b3b0aad1c1d0fab9de16 +size 2247734992 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..ed64de8 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,262 @@ +{ + "metadata": { + "total_size": 7213504512 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..344c826 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3ae1585 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +}