commit 5be6301034ebe618b8b721ffa13c99390407023a Author: ModelHub XC Date: Mon May 18 02:53:24 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: gplsi/Aitana-2B-S-base-1.0 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..73666d9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.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 +Aitana-s2b-c0dc17-bf16.gguf filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/Aitana-s2b-c0dc17-bf16.gguf b/Aitana-s2b-c0dc17-bf16.gguf new file mode 100644 index 0000000..b27d814 --- /dev/null +++ b/Aitana-s2b-c0dc17-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7c2de76071359e7e3bf3ca7caeeda27a8913c48256d83f2b0aa643557a1a7ee +size 4513628992 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8cad135 --- /dev/null +++ b/README.md @@ -0,0 +1,319 @@ +--- +license: apache-2.0 +language: + - ca + - es + - en +base_model: BSC-LT/salamandra-2b +tags: + - valencian + - catalan + - spanish + - english + - text-generation + - alia + - gplsi +datasets: + - gplsi/alia_dogv + - gplsi/alia_les_corts + - gplsi/alia_amic + - gplsi/alia_boua + - gplsi/alia_tourism +library_name: transformers +pipeline_tag: text-generation +--- + +# Aitana-2B-S-base-1.0 + +**Aitana-2B-S-base-1.0** is a generative language model from the **Aitana family**, developed by the [GPLSI (Language and Information System Group)](https://gplsi.dlsi.ua.es/) at the University of Alicante. This model is based on [BSC-LT/salamandra-2b](https://huggingface.co/BSC-LT/salamandra-2b) and has been continuously pre-trained on multilingual data (Valencian, Spanish, and English) to improve representation of Valencian and Catalan languages. + +## Table of Contents + +- [Model Description](#model-description) +- [Evaluation](#evaluation) +- [Training Data](#training-data) +- [Intended Uses](#intended-uses) +- [How to Use](#how-to-use) +- [GGUF for LM Studio](#gguf-for-lm-studio) +- [Additional Information](#additional-information) + +## Model Description + +| Property | Value | +|----------|-------| +| **Base Model** | [BSC-LT/salamandra-2b](https://huggingface.co/BSC-LT/salamandra-2b) | +| **Architecture** | Transformer decoder-only | +| **Parameters** | ~2.25B | +| **Languages** | Valencian, Spanish, English | +| **License** | Apache 2.0 | + +Aitana-2B-S-base-1.0 extends the multilingual Salamandra foundation with additional training on domain-specific Valencian, Spanish, and English data. The training emphasizes administrative, legal, and tourism domains. + +## Training Data + +This model was trained on the following ALIA datasets: + +| Dataset ID | Name | Language | Source | +|------------|------|----------|--------| +| dc8 | dogv_va_2025 | Valencian | [gplsi/alia_dogv](https://huggingface.co/datasets/gplsi/alia_dogv) | +| dc9 | dogv_es_2025 | Spanish | [gplsi/alia_dogv](https://huggingface.co/datasets/gplsi/alia_dogv) | +| dc10 | corts_es_va_2025 | Spanish/Valencian | [gplsi/alia_les_corts](https://huggingface.co/datasets/gplsi/alia_les_corts) | +| dc11 | amic_va_2025 | Valencian | [gplsi/alia_amic](https://huggingface.co/datasets/gplsi/alia_amic) | +| dc12 | boua_va_2025 | Valencian | [gplsi/alia_boua](https://huggingface.co/datasets/gplsi/alia_boua) | +| dc13 | boua_es_2025 | Spanish | [gplsi/alia_boua](https://huggingface.co/datasets/gplsi/alia_boua) | +| dc14 | tourism_va_2025 | Valencian | [gplsi/alia_tourism](https://huggingface.co/datasets/gplsi/alia_tourism) | +| dc15 | tourism_es_2025 | Spanish | [gplsi/alia_tourism](https://huggingface.co/datasets/gplsi/alia_tourism) | +| dc16 | tourism_en_2025 | English | [gplsi/alia_tourism](https://huggingface.co/datasets/gplsi/alia_tourism) | + +### Data Sources + +- **DOGV (Diari Oficial de la Generalitat Valenciana)**: Official communications of the Valencian Community including laws and public sector communications +- **Les Corts Valencianes**: Transcripts from the Valencian Parliament plenary sessions and committee meetings +- **AMIC**: Valencian language corpus +- **BOUA (Butlletí Oficial de la Universitat d'Alacant)**: Official University of Alicante documents including grants, regulations, and resolutions +- **Tourism**: Multilingual tourism domain content + +## Intended Uses + +This model can be used for: + +- **Text generation** in Valencian, Spanish, and English +- **Fine-tuning** for specific downstream tasks +- **Domain adaptation** for administrative, legal, or tourism applications + +> **Note**: Due to the formal register of training data (administrative and legal domains), generated text tends toward formal language. + +## How to Use + +### Transformers + +```python +import torch +from transformers import pipeline, AutoTokenizer + +model_id = "gplsi/Aitana-2B-S-base-1.0" +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 = "Les corts valencianes han pres la decisió de" +result = generator(text, do_sample=True, top_k=10, max_new_tokens=100) +print(result[0]['generated_text']) + +# Spanish example +text = "El turismo en la Comunidad Valenciana" +result = generator(text, do_sample=True, top_k=10, max_new_tokens=100) +print(result[0]['generated_text']) +``` + +## GGUF for LM Studio + +This repository includes GGUF quantized versions for use with [LM Studio](https://lmstudio.ai/), [Ollama](https://ollama.ai/), and other llama.cpp-based tools. + +| File | Quantization | Size | Quality | +|------|--------------|------|---------| +| `Aitana-s2b-c0dc17-Q4_K_M.gguf` | Q4_K_M | ~1.3 GB | Good balance | +| `Aitana-s2b-c0dc17-f16.gguf` | F16 | ~4.5 GB | Full precision | + +### Using with llama-cpp-python + +```python +from llama_cpp import Llama + +llm = Llama.from_pretrained( + repo_id="gplsi/Aitana-2B-S-base-1.0", + filename="Aitana-s2b-c0dc17-Q4_K_M.gguf", +) + +output = llm("Les corts valencianes han decidit", max_tokens=100) +print(output["choices"][0]["text"]) +``` + +## Evaluation + +In the following table, we can see the results obtained with different benchmarks from [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) in comparison with the model used for continuous pre-training. +The results have been obtained from the model pre-trained; no instruction tuning or fine-tuning of any kind has been performed. + +### Normalized score per language + +| Language |Salamandra 2B| Aitana-2B-S-base-1.0 | +|----------|----------|----------| +| Spanish | 0.150 |**0.163**| +| Catalan | **0.224** | 0.220 | +| English | **0.168** | 0.161 | +| Valencian | 0.603 | **0.608**| + +### Valencian + +#### Classification Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-2B | Aitana-2B-S-base-1.0 | +|------------------------------|--------|----------------------------|-------------|---------------|-----------------------| +| XNLI | va |Natural Language Inference | acc | **0.475** | 0.474 | + + +#### Generation Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-2B | Aitana-2B-S-base-1.0 | +|------------------------------|--------|----------------------------|-------------|---------------|-----------------------| +| Cocoteros | va |Reading Comprehension | bleu | 6.32 | **6.61** | +| Phrases ca-va | va-ca |Translation - Adaptation | bleu | 79.82 | **81.57** | +| Phrases va-ca | va-ca |Translation - Adaptation | bleu | **78.05** | 75.68 | +| Phrases va-es | va-es |Translation | bleu | 76.04 | **76.31** | +| Phrases es-va | es-va |Translation | bleu | 58.86 | **62.86** | + + +### Catalan + +#### Classification Benchmarks + + +| Dataset | Lang. | Task | Metric | Salamandra-2B | Aitana-2B-S-base-1.0 | +|------------------------------|--------|---------------------------|-------------|---------------|-----------------------| +| Belebele Cat_latn | ca | Reading Comprehension | acc | 0.231 | **0.257** | +| COPA | ca | Commonsense Reasoning | acc | **0.700** | 0.690 | +| XStoryCloze | ca | Commonsense Reasoning | acc | 0.655 | 0.655 | +| OpenBookQA | ca | Question Answering | acc | 0.294 | **0.300** | +| PAWS | ca | Paraphrasing | acc | 0.556 | **0.566** | +| PiQA | ca | Question Answering | acc | **0.643** | 0.641 | +| SiQA | ca | Question Answering | acc | **0.434** | 0.425 | +| ARC Easy | ca | Question Answering | acc | 0.551 | **0.553** | +| ARC Challenge | ca | Question Answering | acc | **0.290** | 0.282 | +| XNLI | ca | Natural Language Inference| acc | **0.473** | 0.469 | +| Teca | ca | Natural Language Inference| acc | **0.465** | 0.430 | +| WNLI | ca | Natural Language Inference| acc | 0.577 | 0.577 | +| Catcola | ca | Linguistic Acceptability | acc | 0.543 | **0.596** | +| Catcola | ca | Linguistic Acceptability | mcc | 0.046 | -0.002 | +| Catalanqa | ca | Question Answering | F1 | **0.668** | 0.643 | +| Mgsm direct | ca | Math | exact match | 0.024 | 0.024 | +| Catalanqa | ca | Question Answering | exact match | **0.437** | 0.405 | +| Xquad | ca | Question Answering | exact match | **0.371** | 0.344 | +| Xquad | ca | Question Answering | F1 | **0.579** | 0.568 | + + +#### Generation Benchmarks + + +| Dataset | Lang. | Task | Metric | Salamandra-2B | Aitana-2B-S-base-1.0 | +|------------------------------|--------|--------------------------|--------|----------------|-----------------------| +| Cabreu abstractive | ca | Summarization | bleu | 5.78 | **6.52** | +| Cabreu extractive | ca | Summarization | bleu | **42.89** | 41.61 | +| Cabreu extreme | ca | Summarization | bleu | **3.29** | 3.01 | + + +### Spanish + + +#### Classification Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-2B | Aitana-2B-S-base-1.0 | +|------------------------------|--------|---------------------------|-------------|---------------|-----------------------| +| Belebele | es | Reading Comprehension | acc | 0.228 | **0.263** | +| PAWS | es | Paraphrasing | acc | **0.561** | 0.553 | +| XNLI | es | Natural Language Inference| acc | **0.439** | 0.422 | +| WNLI | es | Natural Language Inference| acc | 0.563 | 0.563 | +| XStoryCloze | es | Commonsense Reasoning | acc | 0.653 | **0.655** | +| Escola | es | Linguistic Acceptability | acc | 0.593 | **0.618** | +| Escola | es | Linguistic Acceptability | mcc | **0.031** | -0.020 | +| OpenbookQA | es | Question Answering | acc | 0.308 | **0.316** | +| MGSM Direct | es | Math | exact match | 0.020 | **0.032** | +| XQUAD | es | Question Answering | exact match | **0.377** | 0.341 | +| XQUAD | es | Question Answering | F1 | **0.584** | 0.559 | + + +#### Generation Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-2B | Aitana-2B-S-base-1.0 | +|------------------------------|--------|---------------------|---------|----------------|-----------------------| +| Cocoteros | es |Reading Comprehension| bleu | **8.46** | 7.043 | +| XLSum | es | Summarization | bleu | 0.801 | **1.622** | + + + +### English + + +#### Classification Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-2B | Aitana-2B-S-base-1.0 | +|------------------------------|--------|----------------------------|-------------|---------------|-----------------------| +| Arc Challenge | en | Question Answering | acc | **0.370** | 0.360 | +| Arc Easy | en | Question Answering | acc | **0.722** | 0.712 | +| Belebele | en | Reading Comprehension | acc | 0.216 | **0.252** | +| PAWS | en | Paraphrasing | acc | 0.561 | **0.574** | +| XNLI | en | Natural Language Inference | acc | **0.462** | 0.452 | +| XStoryCloze | en | Commonsense Reasoning | acc | 0.711 | **0.713** | +| OpenBookQA | en | Question Answering | acc | **0.300** | 0.270 | +| PiQA | en | Question Answering | acc | 0.737 | **0.742** | +| Social iqa | en | Question Answering | acc | **0.454** | 0.450 | +| WNLI | en | Natural Language Inference | acc | 0.465 | **0.380** | +| MGSM Direct | en | Math | exact match | **0.064** | 0.06 | +| TriviaQA | en | Question Answering | exact match | **0.376** | 0.352 | + + + +## 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)**. + +### Part of the Aitana Family + +This model is part of the Aitana model family, which includes: +- [gplsi/Aitana-2B-S](https://huggingface.co/gplsi/Aitana-2B-S) - Valencian-focused base model +- [gplsi/Aitana-TA-2B-S](https://huggingface.co/gplsi/Aitana-TA-2B-S) - Translation model (Spanish ↔ Valencian) + +### 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*. + + +### 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-base-1.0, + author = {Estevanell-Valladares, Ernesto L. and Yáñez-Romero, Fabio and Sepúlveda-Torres, Robiert and Consuegra-Ayala, Juan Pablo and Galeano, Santiago and Miró Maestre, María and Martínez-Murillo, Iván and Grande, Eduardo and Canal-Esteve, Miquel and Bonora, Mar and Gutierrez, Yoan and Abreu Salas, José Ignacio and Lloret, Elena and Montoyo, Andrés and Muñoz-Guillena and Palomar, Manuel}, + title = {Aitana 2B base: Continually pre-trained on Valencian}, + year = {2025}, + institution = {Language and Information Systems Group (GPLSI) and Centro de Inteligencia Digital (CENID), University of Alicante (UA)}, + howpublished = {\url{https://huggingface.co/gplsi/gplsi/Aitana-2B-S-base-1.0}}, + note = {Accessed: 2025-12-12} +} +``` + +--- + +**Copyright © 2025 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/config.json b/config.json new file mode 100644 index 0000000..f60075c --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "dtype": "bfloat16", + "eos_token_id": 2, + "pad_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, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "transformers_version": "4.56.2", + "use_cache": true, + "vocab_size": 256000 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..8275dfe --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.56.2" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..c950402 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2d325c4737523aaab79339f72a9301aa562c18a9a91da410bf1fdd936aa094a +size 4507005744 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..451134b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "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..ffed458 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e90b85b3e3b3ebfc6b9bafeb954b37f2435eed595738337e53f2a746d23d5a2 +size 37007416 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..bb4a836 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,1100 @@ +{ + "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 + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_special_tokens": {}, + "legacy": false, + "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 +} \ No newline at end of file