commit ea767d6d70bbf6b6137a1929f665ee22d141a8bf Author: ModelHub XC Date: Wed Jun 10 18:39:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: gplsi/Aitana-2B-S-IP-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..4457c82 --- /dev/null +++ b/README.md @@ -0,0 +1,318 @@ +--- +license: apache-2.0 +language: + - ca + - es + - en +base_model: gplsi/Aitana-2B-S-IP-base +tags: + - valencian + - spanish + - english + - text-generation + - instruct + - intellectual-property + - alia + - gplsi +datasets: + - projecte-aina/InstruCAT + - projecte-aina/NLUCat + - projecte-aina/escagleu-64k + - OpenAssistant/oasst2 + - projecte-aina/oasst1_ca + - BSC-LT/m-personas + - projecte-aina/RAG_Multilingual + - facebook/flores + - CohereLabs/aya_dataset + - Unbabel/TowerBlocks-v0.1 + - projecte-aina/MentorES + - databricks/databricks-dolly-15k + - yahma/alpaca-cleaned + - openai/gsm8k + - Open-Orca/OpenOrca + - HuggingFaceH4/no_robots + - LipengCS/Table-GPT + - projecte-aina/CoQCat + - allenai/scifact + - somosnlp/LingComp_QA + - somosnlp/instruct-legal-refugiados-es + - somosnlp-hackathon-2025/gastronomia-hispana-dpo + - gplsi/boua_parallel +library_name: transformers +pipeline_tag: text-generation +--- +# Aitana-2B-S-IP-Instruct + +**Aitana-2B-S-IP-Instruct** is an instruction-tuned generative language model from the **Aitana family**, developed by the [GPLSI (Language and Information Systems Group)](https://gplsi.dlsi.ua.es/) at the University of Alicante. Built on Aitana-2B-S-IP-Instruct, this model has been fine-tuned to follow instructions across Valencian, Spanish, and English, with a specialized focus on intellectual property domain tasks. + +## Table of Contents + +- [Model Description](#model-description) +- [Training Data](#training-data) +- [Intended Uses](#intended-uses) +- [How to Use](#how-to-use) +- [Evaluation](#evaluation) +- [Additional Information](#additional-information) + +## Model Description + +| Property | Value | +|----------|-------| +| **Base Model** | [gplsi/Aitana-2B-S-IP-Instruct](https://huggingface.co/gplsi/Aitana-2B-S-IP-Instruct) | +| **Architecture** | Transformer decoder-only | +| **Parameters** | ~2.25B | +| **Languages** | Valencian, Spanish, English | +| **License** | Apache 2.0 | + +Aitana-2B-S-IP-Instruct is an instruction-tuned variant of Aitana-2B-S-IP-Instruct, fine-tuned on multilingual instruction data with emphasis on intellectual property applications. + +## Training Data + +This model was instruction fine-tuned using the following data: + +| Dataset ID | Name | Languages | Source | +|------------|------|-----------|--------| +| ins1 | InstruCAT | CA | [projecte-aina/InstruCAT](https://huggingface.co/datasets/projecte-aina/InstruCAT) | +| ins2 | NLUCat | CA | [projecte-aina/NLUCat](https://huggingface.co/datasets/projecte-aina/NLUCat) | +| ins3 | Escagleu 64K | CA | [projecte-aina/escagleu-64k](https://huggingface.co/datasets/projecte-aina/escagleu-64k) | +| ins4 | OpenAssistant2 (OASST2) | CA, EN, ES, VA | [OpenAssistant/oasst2](https://huggingface.co/datasets/OpenAssistant/oasst2) | +| ins5 | OpenAssistant1 (OASST1) | CA, VA | [projecte-aina/oasst1_ca](https://huggingface.co/datasets/projecte-aina/oasst1_ca) | +| ins6 | M-Personas | CA, EN, ES, VA | [BSC-LT/m-personas](https://huggingface.co/datasets/BSC-LT/m-personas) | +| ins7 | RAG Multilingual | CA, EN, ES | [projecte-aina/RAG_Multilingual](https://huggingface.co/datasets/projecte-aina/RAG_Multilingual) | +| ins8 | FLORES | CA, EN, ES | [facebook/flores](https://huggingface.co/datasets/facebook/flores) | +| ins9 | Aya Dataset | EN, ES, VA | [CohereLabs/aya_dataset](https://huggingface.co/datasets/CohereLabs/aya_dataset) | +| ins10 | TowerBlocks | EN, ES | [Unbabel/TowerBlocks-v0.1](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.1) | +| ins11 | Mentor / Mentores | CA, ES, VA | [projecte-aina/MentorES](https://huggingface.co/datasets/projecte-aina/MentorES) / [projecte-aina/MentorCA](https://huggingface.co/datasets/projecte-aina/MentorCA) | +| ins12 | Dolly / Dolly 3K | CA, EN, VA | [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) / [projecte-aina/dolly3k_ca](https://huggingface.co/datasets/projecte-aina/dolly3k_ca) | +| ins13 | Alpaca | EN, VA | [yahma/alpaca-cleaned](https://huggingface.co/datasets/yahma/alpaca-cleaned) | +| ins14 | GSM8K | EN, VA | [openai/gsm8k](https://huggingface.co/datasets/openai/gsm8k) | +| ins15 | OpenOrca | EN | [Open-Orca/OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca) | +| ins16 | No Robots | EN | [HuggingFaceH4/no_robots](https://huggingface.co/datasets/HuggingFaceH4/no_robots) | +| ins17 | TableGPT | EN | [LipengCS/Table-GPT](https://huggingface.co/datasets/LipengCS/Table-GPT) | +| ins18 | CoQCA / CoQCat | CA, VA | [projecte-aina/CoQCat](https://huggingface.co/datasets/projecte-aina/CoQCat) | +| ins19 | SciFact | EN, VA | [allenai/scifact](https://huggingface.co/datasets/allenai/scifact) | +| ins20 | LingComp QA | ES, VA | [somosnlp/LingComp_QA](https://huggingface.co/datasets/somosnlp/LingComp_QA) | +| ins21 | Instruct Legal Refugiados | ES, VA | [somosnlp/instruct-legal-refugiados-es](https://huggingface.co/datasets/somosnlp/instruct-legal-refugiados-es) | +| ins22 | Gastronomia Hispana | ES, VA | [somosnlp-hackathon-2025/gastronomia-hispana-dpo](https://huggingface.co/datasets/somosnlp-hackathon-2025/gastronomia-hispana-dpo) | +| ins23 | TurismInstructionsGPLSI | VA | — | +| ins24 | Amic-Paralelo | VA | — | +| ins25 | BOUA | VA | [gplsi/boua_parallel](https://huggingface.co/datasets/gplsi/boua_parallel) | +| ins26 | DOGV Parallel | VA | — | +| ins27 | UJI VA-EN Parallel | VA | — | +| ins28 | UJI VA-ES Parallel | VA | — | + +## Intended Uses + +This model can be used for: + +- **Instruction following** in Valencian, Spanish, and English +- **Intellectual property domain** applications +- **Chat and conversational applications** requiring multilingual support +- **Text generation** with task-specific prompting + +## How to Use + +### Transformers + +```python +import torch +from transformers import pipeline, AutoTokenizer + +model_id = "gplsi/Aitana-2B-S-IP-Instruct-IP" +tokenizer = AutoTokenizer.from_pretrained(model_id) +generator = pipeline( + "text-generation", + model=model_id, + tokenizer=tokenizer, + torch_dtype=torch.bfloat16, + device_map="auto", +) +# Valencian example +text = "Explica què és la propietat intel·lectual i quins drets atorga." +result = generator(text, do_sample=True, top_k=10, max_new_tokens=100) +print(result[0]['generated_text']) +# Spanish example +text = "Describe los principales tipos de propiedad intelectual y su marco legal." +result = generator(text, do_sample=True, top_k=10, max_new_tokens=100) +print(result[0]['generated_text']) +# English example +text = "Explain the concept of intellectual property and its importance in innovation." +result = generator(text, do_sample=True, top_k=10, max_new_tokens=100) +print(result[0]['generated_text']) +``` + +## Evaluation + +In the following tables, we present the results obtained with different benchmarks from [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) in comparison with [Salamandra-2B-Instruct](https://huggingface.co/BSC-LT/Salamandra-2B-Instruct). + +### Normalized score per language + +| Language | Salamandra-2B-Instruct | Aitana-2B-S-IP-Instruct | +|----------|------------------------|-----------------------------| +| Spanish | 0.079 | **0.112** | +| Catalan | **0.202** | 0.182 | +| English | **0.178** | 0.167 | +| Valencian | **0.507** | 0.489 | +| **Average** | **0.242** | 0.237 | + +### Valencian + +#### Classification Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-2B-Instruct | Aitana-2B-S-IP-Instruct | +|---------|--------|------|--------|------------------------|-----------------------------| +| XNLI | va | Natural Language Inference | acc | **0.520** | 0.501 | + +#### Generation Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-2B-Instruct | Aitana-2B-S-IP-Instruct | +|---------|--------|------|--------|------------------------|-----------------------------| +| Cocoteros | va | Reading Comprehension | bleu | 2.796 | **3.204** | +| Phrases ca-va | va-ca | Translation - Adaptation | bleu | 58.425 | **58.694** | +| Phrases va-ca | va-ca | Translation - Adaptation | bleu | **70.660** | 56.706 | +| Phrases va-es | va-es | Translation | bleu | **65.427** | 53.129 | +| Phrases es-va | es-va | Translation | bleu | **45.688** | 43.098 | +| Truthfulqa_va | va | Truthfulness | bleu_acc | **0.409** | 0.381 | + +### Catalan + +#### Classification Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-2B-Instruct | Aitana-2B-S-IP-Instruct | +|---------|--------|------|--------|------------------------|-----------------------------| +| Belebele Cat_latn | ca | Reading Comprehension | acc | **0.287** | 0.253 | +| COPA | ca | Commonsense Reasoning | acc | **0.708** | 0.706 | +| XStoryCloze | ca | Commonsense Reasoning | acc | **0.616** | **0.616** | +| OpenBookQA | ca | Question Answering | acc | **0.296** | 0.270 | +| PAWS | ca | Paraphrasing | acc | 0.602 | **0.603** | +| PiQA | ca | Question Answering | acc | 0.638 | **0.643** | +| SiQA | ca | Question Answering | acc | **0.422** | 0.421 | +| ARC Easy | ca | Question Answering | acc | **0.516** | 0.501 | +| ARC Challenge | ca | Question Answering | acc | 0.298 | **0.299** | +| XNLI | ca | Natural Language Inference | acc | 0.513 | **0.517** | +| Teca | ca | Natural Language Inference | acc | 0.486 | **0.494** | +| WNLI | ca | Natural Language Inference | acc | **0.563** | 0.437 | +| Catcola | ca | Linguistic Acceptability | acc | 0.492 | **0.718** | +| Catcola | ca | Linguistic Acceptability | mcc | **0.097** | -0.034 | +| Catalanqa | ca | Question Answering | F1 | **0.516** | 0.397 | +| Mgsm direct | ca | Math | exact match | 0.000 | 0.000 | +| Catalanqa | ca | Question Answering | exact match | **0.182** | 0.049 | +| Xquad | ca | Question Answering | exact match | **0.103** | 0.055 | +| Xquad | ca | Question Answering | F1 | **0.394** | 0.312 | + +#### Generation Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-2B-Instruct | Aitana-2B-S-IP-Instruct | +|---------|--------|------|--------|------------------------|-----------------------------| +| Cabreu abstractive | ca | Summarization | bleu | 7.610 | **8.516** | +| Cabreu extractive | ca | Summarization | bleu | **38.002** | 31.230 | +| Cabreu extreme | ca | Summarization | bleu | 2.733 | **3.070** | + +### Spanish + +#### Classification Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-2B-Instruct | Aitana-2B-S-IP-Instruct | +|---------|--------|------|--------|------------------------|-----------------------------| +| Belebele | es | Reading Comprehension | acc | **0.268** | **0.268** | +| PAWS | es | Paraphrasing | acc | 0.566 | **0.623** | +| XNLI | es | Natural Language Inference | acc | **0.463** | 0.442 | +| WNLI | es | Natural Language Inference | acc | **0.479** | 0.451 | +| XStoryCloze | es | Commonsense Reasoning | acc | **0.617** | 0.614 | +| Escola | es | Linguistic Acceptability | acc | 0.293 | **0.662** | +| Escola | es | Linguistic Acceptability | mcc | **0.020** | 0.000 | +| OpenbookQA | es | Question Answering | acc | 0.286 | **0.296** | +| MGSM Direct | es | Math | exact match | 0.020 | **0.060** | +| XQUAD | es | Question Answering | exact match | **0.066** | 0.035 | +| XQUAD | es | Question Answering | F1 | **0.355** | 0.292 | + +#### Generation Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-2B-Instruct | Aitana-2B-S-IP-Instruct | +|---------|--------|------|--------|------------------------|-----------------------------| +| Cocoteros | es | Reading Comprehension | bleu | **3.308** | 2.755 | +| XLSum | es | Summarization | bleu | **1.695** | 1.474 | + +### English + +#### Classification Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-2B-Instruct | Aitana-2B-S-IP-Instruct | +|---------|--------|------|--------|------------------------|-----------------------------| +| Arc Challenge | en | Question Answering | acc | **0.354** | 0.348 | +| Arc Easy | en | Question Answering | acc | 0.681 | **0.693** | +| Belebele | en | Reading Comprehension | acc | 0.260 | **0.267** | +| PAWS | en | Paraphrasing | acc | 0.597 | **0.602** | +| XNLI | en | Natural Language Inference | acc | 0.512 | **0.547** | +| XStoryCloze | en | Commonsense Reasoning | acc | **0.662** | 0.655 | +| OpenBookQA | en | Question Answering | acc | 0.298 | **0.308** | +| PiQA | en | Question Answering | acc | 0.715 | **0.721** | +| Social iqa | en | Question Answering | acc | **0.453** | 0.419 | +| WNLI | en | Natural Language Inference | acc | **0.535** | 0.437 | +| MGSM Direct | en | Math | exact match | 0.008 | **0.080** | +| TriviaQA | en | Question Answering | exact match | 0.076 | **0.095** | +| CoLA | en | Linguistic Acceptability | mcc | **0.055** | -0.008 | + +### Judge Evaluation + +The model was also evaluated using an LLM-as-judge approach across different task categories. The scores below represent the average rating (1-5 scale, 5 being best) and standard deviation for each task category, comparing against Salamandra-2B-Instruct. + +| Task Category | Salamandra-2B-Instruct | Aitana-2B-S-IP-Instruct | +|---------------|------------------------|-----------------------------| +| CommonSense reasoning | **2.277 / 1.151** | 1.891 / 0.934 | +| Maths | 1.060 / 0.124 | **1.075 / 0.151** | +| Paraphrasing | 3.518 / 1.308 | **3.536 / 1.348** | +| Reading comprehension | **2.966 / 1.111** | 2.599 / 1.331 | +| Summarization | **2.217 / 1.068** | 1.827 / 0.822 | +| Translation | **3.557 / 0.760** | 3.502 / 1.031 | +| **Overall Avg** | **2.599 / 0.920** | 2.405 / 0.936 | + +## Additional Information + +### Author + +The model has been developed by the **Language and [Information Systems Group (GPLSI)](https://gplsi.dlsi.ua.es/)** and the **[Centro de Inteligencia Digital (CENID)](https://cenid.es)**, both part of the **[University of Alicante (UA)](https://www.ua.es/es/)**, as part of their ongoing research in **Natural Language Processing (NLP)**. + + +### Funding + +This work is funded by the **Ministerio para la Transformación Digital y de la Función Pública**, co-financed by the **EU – NextGenerationEU**, within the framework of the project *Desarrollo de Modelos ALIA*. This work has also been partially supported by Project HEART-NLP (PID2024-156263OB-C22). + +### Acknowledgments + +We would like to express our gratitude to all individuals and institutions that have contributed to the development of this work. +Special thanks to: +- [Language Technologies Laboratory at Barcelona Supercomputing Center](https://www.bsc.es/es/discover-bsc/organisation/research-structure/language-technologies-laboratory) +- [Centro Vasco de Tecnología de la Lengua (HiTZ)](https://www.hitz.eus/es) +- [Centro Singular de Investigación en Tecnologías Inteligentes (CiTIUS)](https://citius.gal/) +- [Sistemas Inteligentes de Acceso a la Información (SINAI)](https://www.ujaen.es/investigacion-y-transferencia/grupos-de-investigacion/sistemas-inteligentes-de-acceso-la-informacion-sinai) +- [Instituto Universitario de Investigación Informática (IUII)](https://web.ua.es/es/iuii/) +- [Leonardo HPC System](https://leonardo-supercomputer.cineca.eu/) +- [European supercomputing ecosystem (EUROHPC)](https://www.eurohpc-ju.europa.eu/) + +We also acknowledge the financial, technical, and scientific support of the **Ministerio para la Transformación Digital y de la Función Pública - Funded by EU – NextGenerationEU within the framework of the project Desarrollo de Modelos ALIA**, whose contribution has been essential to the completion of this research. + +### License + +[Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0) + +### Disclaimer + +This model is intended for general purposes and is available under a permissive Apache License 2.0. Be aware that the model may have biases and/or undesirable outputs. Users deploying systems based on this model are responsible for mitigating risks and complying with applicable AI regulations. + +### Reference + +```bibtex +@misc{gplsi-Aitana-2B-S-IP-Instruct, + author = {Martínez-Murillo, Iván and Sepúlveda-Torres, Robiert and Grande, Eduardo and Galiano, Santiago and Estevanell-Valladares, Ernesto L. and Consuegra-Ayala, Juan Pablo and Miró Maestre, María and Canal-Esteve, Miquel and Bonora, Mar and Gutierrez, Yoan and Abreu Salas, José Ignacio and Lloret, Elena and Montoyo, Andrés and Muñoz-Guillena, Rafael and Palomar, Manuel}, + title = {Aitana 2B Instruct IP: Instruction-tuned model for intellectual property applications in Valencian, Spanish and English}, + year = {2026}, + institution = {Language and Information Systems Group (GPLSI) and Centro de Inteligencia Digital (CENID), University of Alicante (UA)}, + howpublished = {\url{https://huggingface.co/gplsi/Aitana-2B-S-IP-Instruct}}, + note = {Accessed: 2026-05-21} +} +``` + +--- + +**Copyright © 2026 Language and Information Systems Group (GPLSI) and Centro de Inteligencia Digital (CENID), University of Alicante (UA). Distributed under the Apache License 2.0.** diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..f69fbc7 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,9 @@ +{%- if not date_string is defined %}{%- set date_string = "2025-12-09" %}{%- endif %}{%- set base_system_message = "I am Aitana, experimental model developed at the University of Alicante by the Language and Information Systems Group (GPLSI). My knowledge base was last updated on November 2025. Always respond in a friendly manner and following the user's instructions. Today Date: "+ date_string +" +Soy Aitana, un modelo experimental desarrollado en la Universidad de Alicante por el Grupo de Procesamiento del Lenguaje y Sistemas de Información (GPLSI). Mi base de conocimiento se actualizó por última vez en noviembre de 2025. Responde siempre de manera amigable y siguiendo las indicaciones del usuario. +Soc Aitana, un model experimental desenvolupat a la Universitat d'Alacant pel Grup de Processament del Llenguatge i Sistemes d'Informació (GPLSI). La meua base de coneixement es va actualitzar per última vegada en novembre del 2025. Respon sempre de manera amigable i seguint les indicacions de l'usuari." -%}{%- if messages and messages[0].role == "system" -%}{%- set task_system = messages[0].content -%}{%- set messages = messages[1:] -%}{%- else -%}{%- set task_system = "" -%}{%- endif -%}{%- if task_system -%}{%- set system_message = base_system_message + " +" + task_system -%}{%- else -%}{%- set system_message = base_system_message -%}{%- endif -%}{{ "<|im_start|>system +" + system_message + "<|im_end|> +" }}{% for message in messages %}{{'<|im_start|>' + message['role'] + ' +' + message['content'] + '<|im_end|>' + ' +'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant +' }}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..42c2f0a --- /dev/null +++ b/config.json @@ -0,0 +1,34 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "dtype": "bfloat16", + "eos_token_id": 2, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 5440, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 16, + "num_hidden_layers": 24, + "num_key_value_heads": 16, + "pad_token_id": 3, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "rope_theta": 10000.0, + "rope_type": "default" + }, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "transformers_version": "4.57.1", + "use_cache": false, + "vocab_size": 256000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..cad7045 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.57.1" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..53551b5 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34ac627ad4c90791edf10bd35994fc5896fae1e702021af0100c5ef5a206b15e +size 4507005744 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..72ecfee --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..0f0bd57 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:990527d1e7b98c027d386c742250b2f8517bd3adf98c46cc6c1c2f35b234c224 +size 37007559 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..bf57480 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab94ddf46d14f0279254858d53770c5319c5129d47291ee2bada530271cb1292 +size 4813276 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..4615a99 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,1102 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "5": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "6": { + "content": "<|reserved_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "7": { + "content": "<|reserved_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "8": { + "content": "<|reserved_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "9": { + "content": "<|reserved_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "10": { + "content": "<|reserved_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "11": { + "content": "<|reserved_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "12": { + "content": "<|reserved_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "13": { + "content": "<|reserved_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "14": { + "content": "<|reserved_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "15": { + "content": "<|reserved_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "16": { + "content": "<|reserved_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "17": { + "content": "<|reserved_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "18": { + "content": "<|reserved_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "19": { + "content": "<|reserved_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "20": { + "content": "<|reserved_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "21": { + "content": "<|reserved_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "22": { + "content": "<|reserved_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "23": { + "content": "<|reserved_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "24": { + "content": "<|reserved_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "25": { + "content": "<|reserved_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "26": { + "content": "<|reserved_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "27": { + "content": "<|reserved_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "28": { + "content": "<|reserved_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "29": { + "content": "<|reserved_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "30": { + "content": "<|reserved_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "31": { + "content": "<|reserved_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32": { + "content": "<|reserved_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "33": { + "content": "<|reserved_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "34": { + "content": "<|reserved_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "35": { + "content": "<|reserved_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "36": { + "content": "<|reserved_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "37": { + "content": "<|reserved_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "38": { + "content": "<|reserved_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "39": { + "content": "<|reserved_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "40": { + "content": "<|reserved_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "41": { + "content": "<|reserved_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "42": { + "content": "<|reserved_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "43": { + "content": "<|reserved_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "44": { + "content": "<|reserved_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "45": { + "content": "<|reserved_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "46": { + "content": "<|reserved_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "47": { + "content": "<|reserved_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "48": { + "content": "<|reserved_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "49": { + "content": "<|reserved_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "50": { + "content": "<|reserved_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "51": { + "content": "<|reserved_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "52": { + "content": "<|reserved_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "53": { + "content": "<|reserved_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "54": { + "content": "<|reserved_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "55": { + "content": "<|reserved_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "56": { + "content": "<|reserved_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "57": { + "content": "<|reserved_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "58": { + "content": "<|reserved_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "59": { + "content": "<|reserved_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "60": { + "content": "<|reserved_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "61": { + "content": "<|reserved_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "62": { + "content": "<|reserved_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "63": { + "content": "<|reserved_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "64": { + "content": "<|reserved_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "65": { + "content": "<|reserved_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "66": { + "content": "<|reserved_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "67": { + "content": "<|reserved_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "68": { + "content": "<|reserved_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "69": { + "content": "<|reserved_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "70": { + "content": "<|reserved_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "71": { + "content": "<|reserved_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "72": { + "content": "<|reserved_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "73": { + "content": "<|reserved_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "74": { + "content": "<|reserved_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "75": { + "content": "<|reserved_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "76": { + "content": "<|reserved_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "77": { + "content": "<|reserved_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "78": { + "content": "<|reserved_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "79": { + "content": "<|reserved_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "80": { + "content": "<|reserved_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "81": { + "content": "<|reserved_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "82": { + "content": "<|reserved_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "83": { + "content": "<|reserved_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "84": { + "content": "<|reserved_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "85": { + "content": "<|reserved_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "86": { + "content": "<|reserved_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "87": { + "content": "<|reserved_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "88": { + "content": "<|reserved_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "89": { + "content": "<|reserved_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "90": { + "content": "<|reserved_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "91": { + "content": "<|reserved_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "92": { + "content": "<|reserved_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "93": { + "content": "<|reserved_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "94": { + "content": "<|reserved_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "95": { + "content": "<|reserved_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "96": { + "content": "<|reserved_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "97": { + "content": "<|reserved_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "98": { + "content": "<|reserved_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "99": { + "content": "<|reserved_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "100": { + "content": "<|reserved_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "101": { + "content": "<|reserved_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "102": { + "content": "<|reserved_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "103": { + "content": "<|reserved_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "104": { + "content": "\\r", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "107": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "108": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "backend": "tokenizers", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_special_tokens": {}, + "is_local": false, + "legacy": true, + "local_files_only": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}