# Low-resource Fine-tuning

A model fine-tuned for role-playing scenarios based on Qwen3-8B, suitable for Japanese role-playing dialogue generation.

A fine-tuned version based on the lmms-lab/llava-onevision-qwen2-7b-ov model, supporting video-text-to-text conversion tasks.

This is a sentence transformer model fine-tuned from sentence-transformers/all-mpnet-base-v2, which maps text to a 768-dimensional vector space for tasks such as semantic similarity calculation.

A text-to-speech model fine-tuned on the VoxPopuli dataset based on microsoft/speecht5_tts

An English speech synthesis (TTS) model fine-tuned based on Microsoft's SpeechT5, specializing in voice generation for technical domain texts

MiniCPM-V 2.6 is a multimodal large model launched by OpenBMB, surpassing GPT-4V in single-image, multi-image, and video understanding tasks, and supports real-time video understanding on iPad.

A banking-specific large language model fine-tuned based on Mistral-7B, focusing on banking transactions and customer support scenarios

A code generation model fine-tuned based on distilgpt2, suitable for code-related tasks

A multimodal database interaction tool supporting Spanish, generating SQL queries from voice/text commands and returning results in the most suitable modality (voice/text/image)

MiniCPM is an edge-side large language model series jointly developed by FaceWall Intelligence and Tsinghua University's Natural Language Processing Laboratory. The core model contains only 1.2 billion non-embedding parameters and outperforms larger open-source models in multiple evaluations.

A text summarization generation model fine-tuned based on Falconsai/text_summarization, supporting the extraction of key information from long texts to generate concise summaries.

A dialogue AI based on Causal Language Modeling (CLM) architecture, designed for natural language interaction, capable of generating coherent and contextually appropriate responses.

A summarization model fine-tuned on the cnn_dailymail dataset based on google/mt5-small

The LoftQ (LoRA Fine-tuning Aware Quantization) model provides a quantized backbone network and LoRA adapters, specifically designed for LoRA fine-tuning to improve the fine-tuning performance and efficiency of large language models during the quantization process.

This is an English-to-Hindi neural machine translation model based on the Marian framework, fine-tuned by the Indian Institute of Technology Bombay

This model is a fine-tuned English-to-Hinglish (Hindi-English hybrid language) translation model based on Helsinki-NLP/opus-mt-en-hi, trained on the findnitai/english-to-hinglish dataset.

This model is a speech synthesis (TTS) model fine-tuned on the fleurs dataset based on microsoft/speecht5_tts, supporting Chinese speech generation.

A Chinese text-to-speech model fine-tuned on the fleurs dataset based on microsoft/speecht5_tts

A reward model trained based on the LMFlow framework. It is trained on the HH - RLHF dataset (only the useful part) with open_llama_3b as the base model and has good generalization ability.

mBLIP is a multilingual vision-language model based on BLIP-2 architecture, supporting image caption generation and visual question answering tasks in 96 languages.

This model is a speech classification model fine-tuned on the Minds14 dataset based on the WavLM pre-trained model, primarily used for speech intent recognition tasks.

English text-to-speech model based on SpeechT5 architecture, fine-tuned on CommonVoice dataset

A summary generation model fine-tuned based on facebook/mbart-large-50, specializing in stock event summarization tasks

An air traffic control speech recognition model fine-tuned on wav2vec2-xls-r-300m, supporting English

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the ATCOSIM corpus, specifically designed for automatic speech recognition tasks in air traffic control communications.

A fine-tuned text summarization model based on barthez-orangesum-title, supporting keyword summarization for French texts

A fine-tuned abstract generation model based on barthez-orangesum-title, trained on an unknown dataset, supporting French text summarization tasks.

This model is a dense retrieval model further fine-tuned on all Mr. TyDi training data based on the castorini/mdpr-tied-pft-msmarco checkpoint.

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base, achieving a word error rate of 0.5635 on the TIMIT dataset.

Text embedding model fine-tuned from all-distilroberta-v1, trained for 10 epochs with a validation loss of 0.0044

A speech recognition model fine-tuned on an empty dataset based on facebook/wav2vec2-base, using random high-pass filter technology to process training data

A speech recognition model fine-tuned on an unknown dataset based on facebook/wav2vec2-base, with a Word Error Rate (WER) of 0.7175

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base on an unknown dataset, trained using a 10% data subset.

This model is a fine-tuned version of TinyBERT_L-4_H-312_v2 on the wikitext dataset, primarily used for text-related tasks.

This model is a fine-tuned version of TinyBERT_General_6L_768D on the wikitext dataset, primarily used for text-related tasks.

A named entity recognition model fine-tuned based on distilbert-base-uncased, specializing in the DevOps domain

A text summarization model fine-tuned based on the BART-large architecture, performing well on ROUGE metrics

A wav2vec2-large-lv60 speech recognition model fine-tuned on the LibriSpeech dataset, supporting English speech-to-text tasks

A multilingual text classification model fine-tuned on the amazon_reviews_multi dataset based on XLM-RoBERTa-base

A fine-tuned Facebook wav2vec2 model for the speech-to-text module of The Sound of AI Open Source Research Group