commit 14f52bfbb8814f82eb55a90715d1fea08b78e3c0 Author: ModelHub XC Date: Wed May 20 01:39:35 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: gplsi/Aitana-7B-S-Instruct-v0.1 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..91f55ed --- /dev/null +++ b/README.md @@ -0,0 +1,319 @@ +--- +license: apache-2.0 +language: + - ca + - es + - en +base_model: gplsi/Aitana-7B-S-base-1.0 +tags: + - valencian + - spanish + - english + - text-generation + - instruct + - alia + - gplsi +datasets: + - OpenAssistant/oasst2 + - OpenAssistant/oasst1 + - BSC-LT/m-personas + - projecte-aina/RAG_Multilingual + - facebook/flores + - CohereLabs/aya_dataset + - Unbabel/TowerBlocks-v0.2 + - projecte-aina/MentorES + - databricks/databricks-dolly-15k + - tatsu-lab/alpaca + - openai/gsm8k + - Open-Orca/OpenOrca + - HuggingFaceH4/no_robots + - projecte-aina/CoQCat + - gplsi/boua_parallel + - allenai/scifact + - somosnlp/LingComp_QA + - somosnlp/instruct-legal-refugiados-es +library_name: transformers +pipeline_tag: text-generation +--- +# Aitana-7B-S-Instruct-v0.1 + +**Aitana-7B-S-Instruct-v0.1** 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 [gplsi/Aitana-7B-S-base-1.0](https://huggingface.co/gplsi/Aitana-7B-S-base-1.0), this model has been fine-tuned to follow instructions effectively across Valencian, Spanish, and English, with particular emphasis on enhancing Valencian language capabilities. + +## Table of Contents + +- [Model Description](#model-description) +- [Evaluation](#evaluation) +- [Training Data](#training-data) +- [Intended Uses](#intended-uses) +- [How to Use](#how-to-use) +- [Additional Information](#additional-information) + +## Model Description + +| Property | Value | +|----------|-------| +| **Base Model** | [gplsi/Aitana-7B-S-base-1.0](https://huggingface.co/gplsi/Aitana-7B-S-base-1.0) | +| **Architecture** | Transformer decoder-only | +| **Parameters** | ~7.77B | +| **Languages** | Valencian, Spanish, English | +| **License** | Apache 2.0 | + +Aitana-7B-S-Instruct-v0.1 is an instruction-tuned variant of Aitana-7B-S-base-1.0, fine-tuned on multilingual instruction data to follow user prompts and generate helpful responses across Valencian, Spanish, and English. + + +## Training Data + +This model was instruction fine-tuned on the ALIA Instruction/v12 dataset, composed of the following sources: + +| Dataset ID | Name | Languages | Source | +|------------|------|-----------|--------| +| ins1 | OpenAssistant2 (OASST2) | CA, EN, ES, VA | [OpenAssistant/oasst2](https://huggingface.co/datasets/OpenAssistant/oasst2) | +| ins2 | OpenAssistant1 (OASST1) | CA, VA | [OpenAssistant/oasst1](https://huggingface.co/datasets/OpenAssistant/oasst1) | +| ins3 | M-Personas | CA, EN, ES, VA | [BSC-LT/m-personas](https://huggingface.co/datasets/BSC-LT/m-personas) | +| ins4 | RAG Multilingual | CA, EN, ES, VA | [projecte-aina/RAG_Multilingual](https://huggingface.co/datasets/projecte-aina/RAG_Multilingual) | +| ins5 | FLORES | CA, EN, ES | [facebook/flores](https://huggingface.co/datasets/facebook/flores) | +| ins6 | Aya Dataset | EN, ES, VA | [CohereLabs/aya_dataset](https://huggingface.co/datasets/CohereLabs/aya_dataset) | +| ins7 | TowerBlocks | EN, ES | [Unbabel/TowerBlocks-v0.2](https://huggingface.co/datasets/Unbabel/TowerBlocks-v0.2) | +| ins8 | 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) | +| ins9 | Dolly / Dolly 3K | CA, EN, VA | [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) | +| ins10 | Alpaca | EN, VA | [tatsu-lab/alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca) | +| ins11 | GSM8K | EN, VA | [openai/gsm8k](https://huggingface.co/datasets/openai/gsm8k) | +| ins12 | OpenOrca | EN | [Open-Orca/OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca) | +| ins13 | No Robots | EN | [HuggingFaceH4/no_robots](https://huggingface.co/datasets/HuggingFaceH4/no_robots) | +| ins14 | CoQCA / CoQCat | CA, VA | [projecte-aina/CoQCat](https://huggingface.co/datasets/projecte-aina/CoQCat) | +| ins15 | BOUA | ES | [gplsi/boua_parallel](https://huggingface.co/datasets/gplsi/boua_parallel) | +| ins16 | SciFact | VA | [allenai/scifact](https://huggingface.co/datasets/allenai/scifact) | +| ins17 | LingComp QA | VA | [somosnlp/LingComp_QA](https://huggingface.co/datasets/somosnlp/LingComp_QA) | +| ins18 | Instruct Legal Refugiados | VA | [somosnlp/instruct-legal-refugiados-es](https://huggingface.co/datasets/somosnlp/instruct-legal-refugiados-es) | +| ins19 | Amic-Paralelo | ES | — | + +The model was NOT instruction-tuned on Catalan data, though some Catalan appears in multilingual datasets. + +## Intended Uses + +This model can be used for: + +- **Instruction following** in Valencian, Spanish, and English +- **Chat and conversational applications** requiring multilingual support +- **Text generation** with task-specific prompting +- **Domain-specific applications** in administrative, legal, or tourism contexts + +> **Note**: As an instruction-tuned model, it is designed to follow user prompts and generate helpful responses. It is not intended for use as a factual knowledge base. + + + +## How to Use + +### Transformers + +```python +import torch +from transformers import pipeline, AutoTokenizer + +model_id = "gplsi/Aitana-7B-S-Instruct-v0.1" +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 són les Corts Valencianes i quina funció tenen." +result = generator(text, do_sample=True, top_k=10, max_new_tokens=100) +print(result[0]['generated_text']) +# Spanish example +text = "Describe las principales funciones del gobierno autonómico valenciano." +result = generator(text, do_sample=True, top_k=10, max_new_tokens=100) +print(result[0]['generated_text']) +# English example +text = "Explain the role of tourism in the Valencian Community economy." +result = generator(text, do_sample=True, top_k=10, max_new_tokens=100) +print(result[0]['generated_text']) +``` + + +## Evaluation + +In the following table, we present the results obtained with different benchmarks from [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) in comparison with [Salamandra-7B-Instruct](https://huggingface.co/BSC-LT/Salamandra-7B-Instruct). The results reflect the instruction-tuned performance of both models. + +### Normalized score per language + +| Language |Salamandra-7B-Instruct| Aitana-7B-S-Instruct-v0.1 | +|----------|----------|----------| +| Spanish | **0.236** | 0.219 | +| Catalan | **0.343**| 0.304 | +| English | 0.300 | **0.303** | +| Valencian | 0.546 | **0.600** | + + +### Valencian + +#### Classification Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-7B-Instruct | Aitana-7B-S-Instruct-v0.1 | +|------------------------------|--------|----------------------------|-------------|---------------|-----------------------| +| XNLI | va |Natural Language Inference | acc | **0.552** | 0.534 | + + +#### Generation Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-7B-Instruct | Aitana-7B-S-Instruct-v0.1 | +|------------------------------|--------|----------------------------|-------------|---------------|-----------------------| +| Cocoteros | va |Reading Comprehension | bleu | 6.391 | **8.929** | +| Phrases ca-va | va-ca |Translation - Adaptation | bleu | 67.980 | **81.743** | +| Phrases va-ca | va-ca |Translation - Adaptation | bleu | 79.375 | **83.501** | +| Phrases va-es | va-es |Translation | bleu | 63.104 | **80.329** | +| Phrases es-va | es-va |Translation | bleu | 51.64 | **63.95** | +| Truthfulqa_va | va | Truthfulness | bleu_acc | **0.454** | 0.412 | + +### Catalan + +#### Classification Benchmarks + + +| Dataset | Lang. | Task | Metric | Salamandra-7B-Instruct | Aitana-7B-S-Instruct-v0.1 | +|------------------------------|--------|---------------------------|-------------|---------------|-----------------------| +| Belebele Cat_latn | ca | Reading Comprehension | acc | **0.718** | 0.581 | +| COPA | ca | Commonsense Reasoning | acc | **0.824** | 0.822 | +| XStoryCloze | ca | Commonsense Reasoning | acc | **0.708** | 0.678 | +| OpenBookQA | ca | Question Answering | acc | **0.374** | 0.36 | +| PAWS | ca | Paraphrasing | acc | **0.671** | 0.662 | +| PiQA | ca | Question Answering | acc | **0.718** | 0.722 | +| ARC Easy | ca | Question Answering | acc | 0.686 | **0.713** | +| ARC Challenge | ca | Question Answering | acc | 0.425 | **0.435** | +| XNLI | ca | Natural Language Inference| acc | **0.559** | 0.540 | +| Teca | ca | Natural Language Inference| acc | **0.557** | 0.522 | +| WNLI | ca | Natural Language Inference| acc | **0.592** | 0.479 | +| Catcola | ca | Linguistic Acceptability | acc | 0.660 | **0.687** | +| Catcola | ca | Linguistic Acceptability | mcc | **0.170** | 0.156 | +| Catalanqa | ca | Question Answering | F1 | **0.576** | 0.526 | +| Mgsm direct | ca | Math | exact match | **0.02** | 0.004 | +| Catalanqa | ca | Question Answering | exact match | **0.259** | 0.176 | +| Xquad | ca | Question Answering | exact match | **0.228** | 0.157 | +| Xquad | ca | Question Answering | F1 | **0.507** | 0.451 | + +#### Generation Benchmarks +| Dataset | Lang. | Task | Metric | Salamandra-7B-Instruct | Aitana-7B-S-Instruct-v0.1 | +|------------------------------|--------|--------------------------|--------|----------------|-----------------------| +| Cabreu abstractive | ca | Summarization | bleu | 8.60 | **10.10** | +| Cabreu extractive | ca | Summarization | bleu | **39.10** | 28.37 | +| Cabreu extreme | ca | Summarization | bleu | 3.21 | **3.86** | + +### Spanish +#### Classification Benchmarks +| Dataset | Lang. | Task | Metric | Salamandra-7B-Instruct | Aitana-7B-S-Instruct-v0.1 | +|------------------------------|--------|---------------------------|-------------|---------------|-----------------------| +| Belebele | es | Reading Comprehension | acc | **0.698** | 0.590 | +| PAWS | es | Paraphrasing | acc | **0.629** | 0.626 | +| XNLI | es | Natural Language Inference| acc | **0.487** | 0.485 | +| WNLI | es | Natural Language Inference| acc | **0.549** | 0.493 | +| XStoryCloze | es | Commonsense Reasoning | acc | 0.674 | **0.676** | +| Escola | es | Linguistic Acceptability | acc | 0.577 | **0.681** | +| Escola | es | Linguistic Acceptability | mcc | **0.179** | 0.178 | +| OpenbookQA | es | Question Answering | acc | 0.374 | **0.392** | +| MGSM Direct | es | Math | exact match | **0.100** | **0.100** | +| XQUAD | es | Question Answering | exact match | **0.189** | 0.087 | +| XQUAD | es | Question Answering | F1 | **0.467** | 0.413 | + +#### Generation Benchmarks +| Dataset | Lang. | Task | Metric | Salamandra-7B-Instruct | Aitana-7B-S-Instruct-v0.1 | +|------------------------------|--------|---------------------|---------|----------------|-----------------------| +| Cocoteros | es |Reading Comprehension| bleu | 6.306 | **8.680** | +| XLSum | es | Summarization | bleu | **2.048** | 1.502 | + +### English +#### Classification Benchmarks +| Dataset | Lang. | Task | Metric | Salamandra-7B-Instruct | Aitana-7B-S-Instruct-v0.1 | +|------------------------------|--------|----------------------------|-------------|---------------|-----------------------| +| Arc Challenge | en | Question Answering | acc | 0.478 | **0.523** | +| Arc Easy | en | Question Answering | acc | 0.780 | **0.811** | +| Belebele | en | Reading Comprehension | acc | **0.769** | 0.622 | +| PAWS | en | Paraphrasing | acc | 0.655 | **0.677** | +| XNLI | en | Natural Language Inference | acc | 0.534 | **0.555** | +| XStoryCloze | en | Commonsense Reasoning | acc | **0.729** | 0.716 | +| OpenBookQA | en | Question Answering | acc | **0.348** | 0.340 | +| PiQA | en | Question Answering | acc | 0.781 | **0.784** | +| Social iqa | en | Question Answering | acc | 0.520 | **0.524** | +| WNLI | en | Natural Language Inference | acc | **0.493** | **0.493** | +| MGSM Direct | en | Math | exact match | 0.080 | **0.200** | +| TriviaQA | en | Question Answering | exact match | 0.204 | **0.433** | + +### 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 Aitana-7B-S-Instruct-v0.1 against Salamandra-7B-Instruct. + +| Task Category | Salamandra-7B-Instruct | Aitana-7B-S-Instruct-v0.1 | +|---------------|------------------------|---------------------------| +| CommonSense reasoning | 2.637 / 1.295 | **2.989 / 1.200** | +| Maths | 2.386 / 1.536 | **2.584 / 1.474** | +| Paraphrasing | 3.725 / 0.967 | **3.927 / 0.981** | +| Reading comprehension | **3.472 / 1.015** | 3.420 / 1.268 | +| Summarization | **2.369 / 0.932** | 1.862 / 0.713 | +| Translation | 3.770 / 0.580 | **3.895 / 0.814** | +| **Overall Avg** | 3.060 / 1.054 | **3.113 / 1.075** | + +## 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 developed by the GPLSI research group, which includes: + - [gplsi/Aitana-7B-S-base-1.0](https://huggingface.co/gplsi/Aitana-7B-S-base-1.0) - Base version (1.0) of the 7B model + - [gplsi/Aitana-7B-S-Instruct-v0.1](https://huggingface.co/gplsi/Aitana-7B-S-Instruct-v0.1) - Instruction-tuned 7B model + - [gplsi/Aitana-2B-S](https://huggingface.co/gplsi/Aitana-2B-S) - Valencian-focused 2B model + - [gplsi/Aitana-2B-S-base-1.0](https://huggingface.co/gplsi/Aitana-2B-S-base-1.0) - Base version (1.0) of the 2B model + - [gplsi/Aitana-2B-S-Instruct-v0.1](https://huggingface.co/gplsi/Aitana-2B-S-Instruct-v0.1) - Instruction-tuned 2B model + - [gplsi/Aitana-2B-S-Instruct-Aligned-v0.1](https://huggingface.co/gplsi/Aitana-2B-S-Instruct-Aligned-v0.1) - DPO-aligned instruction-tuned 2B model + - [gplsi/Aitana-6.3B](https://huggingface.co/gplsi/Aitana-6.3B) - Larger 6.3B parameter model + - [gplsi/Aitana-TA-2B-S](https://huggingface.co/gplsi/Aitana-TA-2B-S) - Translation model (Spanish ↔ Valencian) + - [gplsi/Aitana-2B-S-LF](https://huggingface.co/gplsi/Aitana-2B-S-LF) - 2B Text Generation variant + - [gplsi/Aitana-2B-S-tourism-base-1.0](https://huggingface.co/gplsi/Aitana-2B-S-tourism-base-1.0) - Domain-specific base model focused on Tourism + - [gplsi/Aitana-tourism-mb-encoder-1.0](https://huggingface.co/gplsi/Aitana-tourism-mb-encoder-1.0) - Tourism domain Fill-Mask/Encoder model + - [gplsi/Aitana-FraudDetection-R-1.0](https://huggingface.co/gplsi/Aitana-FraudDetection-R-1.0) - Text Classification model for Fraud Detection + +### 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-7B-S-Instruct-v0.1, + author = {Sepúlveda-Torres, Robiert and Martínez-Murillo, Iván and Grande, Eduardo and Galiano, Santiago 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 7B Instruct: Instruction-tuned model for 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-7B-S-Instruct-v0.1}}, + note = {Accessed: 2026-05-11} +} +``` +--- +**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.** \ No newline at end of file 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..f1c9620 --- /dev/null +++ b/config.json @@ -0,0 +1,32 @@ +{ + "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": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": null, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "rope_theta": 10000.0, + "rope_type": "default" + }, + "tie_word_embeddings": false, + "transformers_version": "5.3.0", + "use_cache": false, + "vocab_size": 256000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..4270d83 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": [2,5], + "transformers_version": "5.3.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..dfa501c --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45430e36ca00d784dfc89c85a832a22558117a9cb60a0c83416a31367424c11c +size 15536268648 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..4b560cf --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,28 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>" + ], + "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..f703b48 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c251673bdb03b73127fbba6bb6096617d767360e77844b982923ffc5b8268f4 +size 36981859 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..3307f8d --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa490e57cebce5cb1a0a5b1a5d3fa4de05aee53dc3a44791f1c3401db44d802d +size 4813274 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..079b661 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,63 @@ +{ + "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 + }, + "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 + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>" + ], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 8192, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} \ No newline at end of file