commit edb84d8f479c1c0617ef2e61380b97b5d4367d89 Author: ModelHub XC Date: Sun Aug 30 17:02:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: gplsi/Aitana-7B-S-base 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..ef8eee0 --- /dev/null +++ b/README.md @@ -0,0 +1,290 @@ +--- +license: apache-2.0 +language: + - ca + - es + - en +base_model: BSC-LT/salamandra-7b +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-7B-S-base + +**Aitana-7B-S-base** 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 and [Language Modeling Group at Barcelona Supercomputing Center](https://www.bsc.es/research-development/research-areas/cognitive-computing/language-modeling). This model is based on [BSC-LT/salamandra-7b](https://huggingface.co/BSC-LT/salamandra-7b) 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) +- [Additional Information](#additional-information) + +## Model Description + +| Property | Value | +|----------|-------| +| **Base Model** | [BSC-LT/salamandra-7b](https://huggingface.co/BSC-LT/salamandra-7b) | +| **Architecture** | Transformer decoder-only | +| **Parameters** | ~7.77B | +| **Languages** | Valencian, Spanish, English | +| **License** | Apache 2.0 | + +Aitana-7B-S-base 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) | +|-|alia_multilingual_parallel_sentences|Spanish/Valencian/English|[gplsi/alia_multilingual_parallel_sentences](https://huggingface.co/datasets/gplsi/alia_multilingual_parallel_sentences)| + +### 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-7B-S-base" +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']) +``` + + +## 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-7B | Aitana-7B-S-base | +|----------|----------|----------| +| **Spanish** | 0.248 | **0.26** | +| **Catalan** | 0.364 | **0.373** | +| **English** | 0.319 | **0.349** | +| **Valencian** | 0.663 | **0.664** | + +### Valencian + + +#### Classification Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-7B | Aitana-7B-S-base | +|------------------------------|--------|----------------------------|-------------|---------------|-----------------------| +| XNLI | va |Natural Language Inference | acc | **0.496** | 0.495 | + + +#### Generation Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-7B | Aitana-7B-S-base | +|------------------------------|--------|----------------------------|-------------|---------------|-----------------------| +| Cocoteros | va |Reading Comprehension | bleu | 12.30 | **16.09** | +| Phrases ca-va | va-ca |Translation - Adaptation | bleu | **86.83** | 86.53 | +| Phrases va-ca | va-ca |Translation - Adaptation | bleu | **94.68** | 82.99 | +| Phrases va-es | va-es |Translation | bleu | 79.83 | **80.76** | +| Phrases es-va | es-va |Translation | bleu | 66.31 | **71.01** | +| Truthfulqa_va | va | Truthfulness | bleu_acc| 0.353 | **0.388** | + + +### Catalan + + +#### Classification Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-7B | Aitana-7B-S-base | +|------------------------------|--------|----------------------------|-------------|---------------|-----------------------| +| Belebele Cat_latn | ca | Reading Comprehension | acc | 0.51 | **0.546** | +| COPA | ca | Commonsense Reasoning | acc | 0.798 | **0.812** | +| XStoryCloze | ca | Commonsense Reasoning | acc | 0.75 | **0.767** | +| OpenBookQA | ca | Question Answering | acc | 0.366 | **0.376** | +| PAWS | ca | Paraphrasing | acc | **0.626** | 0.613 | +| PiQA | ca | Question Answering | acc | 0.702 | **0.725** | +| SiQA | ca | Question Answering | acc | 0.489 | **0.506** | +| ARC Easy | ca | Question Answering | acc | 0.726 | **0.73** | +| ARC Challenge | ca | Question Answering | acc | **0.47** | 0.459 | +| XNLI | ca | Natural Language Inference | acc | **0.504** | 0.494 | +| Teca | ca | Natural Language Inference | acc | **0.527** | 0.514. | +| WNLI | ca | Natural Language Inference | acc | 0.577 | **0.633** | +| Catcola | ca | Linguistic Acceptability | acc | **0.732** | 0.71 +| Catalanqa | ca | Question Answering | F1 | **0.832** | 0.829 | +| Catalanqa | ca | Question Answering | exact match | 0.62 | **0.65** | +| Mgsm direct | ca | Math | exact match | 0.068 | **0.096** | +| Xquad | ca | Question Answering | exact match | **0.498** | 0.497 | +| Xquad | ca | Question Answering | F1 | 0.717 | **0.724** | + + + +#### Generation Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-7B | Aitana-7B-S-base | +|------------------------------|--------|----------------------------|--------|----------------|-----------------------| +| Cabreu abstractive | ca | Summarization | bleu | 8.46 | **11.34** | +| Cabreu extractive | ca | Summarization | bleu | **44.62** | 41.73 | +| Cabreu extreme | ca | Summarization | bleu | 11.02 | **12.44** | + + + +### Spanish + +#### Classification Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-7B | Aitana-7B-S-base | +|------------------------------|--------|---------------------------|-------------|---------------|-----------------------| +| Belebele | es | Reading Comprehension | acc | 0.49 | **0.55** | +| PAWS | es | Paraphrasing | acc | **0.616** | 0.591 | +| XNLI | es | Natural Language Inference| acc | **0.462** | 0.447 | +| WNLI | es | Natural Language Inference| acc | **0.45** | **0.45** | +| XStoryCloze | es | Commonsense Reasoning | acc | 0.746 | **0.754** | +| Escola | es | Linguistic Acceptability | acc | - | - | +| Escola | es | Linguistic Acceptability | mcc | - | - | +| OpenbookQA | es | Question Answering | acc | - | - | +| MGSM Direct | es | Math | exact match | 0.064 | **0.084** | +| XQUAD | es | Question Answering | exact match | **0.51** | 0.509 | +| XQUAD | es | Question Answering | F1 | 0.746 | **0.754** | + + + +#### Generation Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-7B | Aitana-7B-S-base | +|------------------------------|--------|---------------------|---------|----------------|-----------------------| +| Cocoteros | es |Reading Comprehension| bleu | 14.57 | **17.35** | +| XLSum | es | Summarization | bleu | 3.52 | **5.79** | + +### English + +#### Classification Benchmarks + +| Dataset | Lang. | Task | Metric | Salamandra-7B | Aitana-7B-S-base | +|------------------------------|--------|----------------------------|-------------|---------------|-----------------------| +| Arc Challenge | en | Question Answering | acc | **0.53** | 0.529 | +| Arc Easy | en | Question Answering | acc | **0.822** | 0.816 | +| Belebele | en | Reading Comprehension | acc | **0.562** | 0.537 | +| PAWS | en | Paraphrasing | acc | **0.632** | 0.604 | +| XNLI | en | Natural Language Inference | acc | **0.474** | 0.472 | +| XStoryCloze | en | Commonsense Reasoning | acc | **0.796** | 0.79 | +| OpenBookQA | en | Question Answering | acc | 0.352 | **0.356** | +| PiQA | en | Question Answering | acc | 0.793 | **0.796** | +| Social iqa | en | Question Answering | acc | **0.509** | 0.508 | +| WNLI | en | Natural Language Inference | acc | 0.464 | **0.549** | +| MGSM Direct | en | Math | exact match | 0.264 | **0.564** | +| TriviaQA | en | Question Answering | exact match | 0.597 | **0.601** | +| CoLA | en | Linguistic Acceptability | mcc | **0.381** | 0.339 | + +## Additional Information + +### Author + +The model has been developed by the **Language and [Information Systems Group (GPLSI)](https://gplsi.dlsi.ua.es/)**, the **[Centro de Inteligencia Digital (CENID)](https://cenid.es)**, and the [Language Modeling Group at Barcelona Supercomputing Center] (https://www.bsc.es/research-development/research-areas/cognitive-computing/language-modeling), all contributing to cutting-edge research in Natural Language Processing (NLP). GPLSI and CENID are part of the **[University of Alicante (UA)](https://www.ua.es/es/)**, while the Language Modeling Group operates within the [Barcelona Supercomputing Center](https://www.bsc.es/es). + + +### 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 Modeling at Barcelona Supercomputing Center](https://www.bsc.es/research-development/research-areas/cognitive-computing/language-modeling) +- [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-base, + author = {Sepúlveda-Torres, Robiert and Baucells, Irene and Estevanell-Valladares, Ernesto L. and Galiano, Santiago and Consuegra-Ayala, Juan Pablo and Miró Maestre, María and Martínez-Murillo, Iván and Grande, Eduardo 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 7B base: Continually pre-trained on Valencian}, + 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/gplsi/Aitana-2B-S-base}}, + note = {Accessed: 2026-4-8} +} +``` + +--- + +**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/config.json b/config.json new file mode 100644 index 0000000..340846f --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "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, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.40.2", + "use_cache": true, + "vocab_size": 256000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..f784d96 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.45.2" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..368912c --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d35dd7970143b8f7c73bea75fc2e639ed5176c5e8bcddfb252067282bcc5b43c +size 4982973048 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..1e1bc65 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d7b0ca473d9240738ae86ceccf3573388e72bb18d12981bddb0f9641623d05a +size 4995660232 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..d7ca990 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fa487237135bb8b1d8d23dcd7178e2a0f6963ba081d51ee8e031bfea63c6129 +size 3460482936 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..28e6f0c --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a2d377a1e8649882ea726b9a2c5666edfda341330e6ee39a3a799dbb4d6d645 +size 2097152128 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..5cbd692 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 15536234496 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00003-of-00004.safetensors" + } +} 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..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..91b37e7 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,43 @@ +{ + "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 + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "local_files_only": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}