This is a lightweight text generation model based on the Meta LLaMA 3 8B model. It is efficiently fine-tuned using the Unsloth framework and converted to the GGUF format. The model is optimized for the Alpaca dataset, suitable for local deployment and inference, especially in resource-constrained environments.

Natural Language ProcessingGguf

EXAONE-4.0-1.2B is a text generation model developed by LG AI Research. It is based on the EXAONE-4.0-1.2B base model and fine-tuned using the tatsu-lab/alpaca dataset, supporting text generation tasks in both English and Korean. The model has been converted to the GGUF format for easy local deployment and operation.

Natural Language ProcessingGgufMultiple Languages

Samastam is an early instruction-tuned variant of the Sarvam-1 model, fine-tuned on the Alpaca-cleaned dataset to support multilingual instruction responses.

Natural Language ProcessingTransformersMultiple Languages

A cutting-edge speech large language model based on the Alpaca model, designed for high-quality, empathetic text-to-speech generation

Audio ProcessingTransformersMultiple Languages

A 7B-parameter LLaMa model fine-tuned on the Code Alpaca dataset, specializing in code generation tasks

Natural Language ProcessingTransformersEnglish

SmolLumi-8B-Instruct is an 8B-parameter Alpaca model trained using Unsloth and Huggingface TRL library, specializing in text generation inference tasks.

Natural Language ProcessingGgufEnglish

The Alpaca 3.2 series is a multilingual large language model developed by Meta, available in 1B and 3B parameter sizes, optimized for multilingual dialogue use cases.

Natural Language ProcessingPytorchMultiple Languages

Tinyllama-2B is a small but very practical language model created through merging and fine-tuning. It is optimized based on KobbleTinyV2-1.1B and has excellent performance. This model uses the Alpaca prompt template and is suitable for various text generation tasks.

Natural Language ProcessingTransformers

PersianLLaMA is the first large language model specifically designed for Persian, with 13 billion parameters. It is fine-tuned using the Persian Alpaca dataset and performs excellently in executing Persian instruction tasks.

Natural Language ProcessingTransformersOther

ECE-TW3-JRGL-V5 is a new model obtained by merging the MoMo-72B-lora-1.8.7-DPO and alpaca-dragon-72b-v1 models through mergekit, integrating the advantages of multiple models.

Natural Language ProcessingTransformers

A Finnish large language model based on the GPT-3 architecture, fine-tuned with the Alpaca dataset, supporting Finnish text generation tasks.

Natural Language ProcessingTransformersEnglish

11B parameter large language model based on Solar architecture, supports Alpaca and Vicuna prompt formats

Natural Language ProcessingTransformersEnglish

Bode is a large Portuguese language model with 7 billion parameters, based on the Llama 2 architecture. It is fine-tuned on the Portuguese Alpaca dataset and designed specifically for Portuguese natural language processing tasks.

Natural Language ProcessingTransformersMultiple Languages

Crunchy-onion is an instruction-tuned model obtained by fine-tuning the Mixtral base model on datasets such as LimaRP, theory of mind, and Gnosis. It performs excellently under specific instruction formats. This model is trained using 4-bit QLoRA technology and finally merged into Mixtral Instruct, achieving the best results in the Alpaca Instruct format.

Natural Language ProcessingTransformers

A language model optimized for chat scenarios, aligned through the DPO method, and performs excellently in the Alpaca-Eval 2.0 benchmark test.

Natural Language ProcessingTransformers

Kunoichi-DPO-7B is a model fine-tuned using Intel's Orca data for direct preference optimization (DPO) on the Alpaca template based on the Kunoichi-7B model. It is mainly targeted at general scenarios and has stronger reasoning and instruction-following abilities.

Natural Language ProcessingTransformers

Velara 11B v2 is a large language model based on the Mistral architecture, focusing on text generation tasks and utilizing the Alpaca-InstructOnly2 prompt template.

Natural Language ProcessingGgufEnglish

Maral is a large language model focused on Persian, built on the Mistral architecture and trained on the Persian Alpaca dataset, while also supporting English generation.

Natural Language ProcessingTransformersMultiple Languages

A fine-tuned version based on epfl-llm/meditron-7b using the Alpaca dataset for SFT training, specializing in medical Q&A tasks

Natural Language ProcessingTransformersEnglish

An open-source chat model specifically designed for financial and economic dialogues, based on Llama2-13B architecture, fine-tuned jointly with FinTalk-19k and Alpaca datasets

Natural Language ProcessingTransformersEnglish