# English text generation

BrtGPT-124M-Base is a basic model pre - trained on a large amount of English corpora and can be used for free. It solves the problems of cumbersome use of open - source models and high requirements for processing power.

GPT-2 is an open-source language model developed by OpenAI, based on the Transformer architecture, capable of generating coherent text.

A Mist model optimized with Unsloth lazy-free framework and Huggingface TRL training library, achieving 2x training efficiency

The 4-bit quantized version of Qwen/QwQ-32B, implemented using the BitsAndBytes library, suitable for text generation tasks in resource-constrained environments.

Optimized Qwen2 model based on Unsloth and Huggingface TRL library, achieving 2x inference speed improvement

This is the 4-bit quantized version of the mistralai/Mistral-Small-24B-Instruct-2501 model, quantized by ConfidentialMind.com, achieving a smaller and faster model with minimal performance loss.

This is a fine-tuned Phi-4 model that achieves 2x training acceleration through the Unsloth and TRL libraries and focuses on text generation tasks.

This is a GGUF format model converted from NanoLM-1B-Instruct-v2, suitable for text generation tasks.

Mini-Magnum-12B-V1.1 is a text generation model built on the basis of the intervitens/mini-magnum-12b-v1.1 base model, supporting English and adopting a specific quantization method.

This is a 4-bit quantized 135M parameter small language model, suitable for text generation tasks in resource-constrained environments.

This is a 774M-parameter language model based on the GPT-2 architecture, trained on 150 billion tokens from the FineWeb dataset.

An optimized model based on Meta LLAMA-3-8B, trained using lazy-free optimization techniques and the Huggingface TRL library, achieving 2x speed improvement

K2 is a large language model with 65 billion parameters, surpassing Llama 2 70B with a 35% computational advantage through a fully transparent training approach.

A text generation model trained on the SlimPajama-627B dataset, utilizing the retina network architecture.

MicroLlama is a 300-million-parameter Llama model pretrained by individual developer keeeeenw within a $500 budget, focusing on English text generation tasks.

Gemma is a lightweight open model series launched by Google, built with the same technology as Gemini, suitable for text generation tasks.

Matter 7B is a fine-tuned model based on Mistral 7B, designed for text generation tasks, supporting conversational interaction and function calling.

This is a hybrid model created by merging multiple Mistral-7B variant models using the mergekit tool, focusing on text generation tasks.

Ministral is a GPT-like model based on 4 billion parameters, adopting the same architecture as the Mistral model but on a smaller scale, primarily designed for English text generation tasks.

This is a static quantization version of the Doctor-Shotgun/lzlv-limarpv3-l2-70b model, offering multiple quantization options to suit different needs.

Daring Maid-13B is a smarter and more instruction-following capable version of Noromaid, created by integrating features from multiple excellent models.

Rose 20B is a 20B-parameter large language model based on the LLaMA architecture, adopting Alpaca-style instruction templates, suitable for text generation tasks.

TinyLlama-1.1B is a compact large language model with 1.1 billion parameters, based on the Llama 2 architecture, optimized for computation and memory-constrained scenarios.

TinyMistral-248M is a small language model based on pre-training from the Mistral 7B model, with parameters scaled down to approximately 248 million, primarily used for fine-tuning downstream tasks.

Opus V0 7B is a 7B-parameter language model based on the Mistral architecture, developed by DreamGen, focusing on text generation tasks.

A lightweight conversational model fine-tuned based on TinyLlama-1.1B, trained using the Alpaca dataset, suitable for English text generation tasks

Yarn Mistral 7B 128K is an advanced language model optimized for long-context processing, further pre-trained on long-context data using the YaRN extension method, supporting a 128k token context window.

A pre-trained language model based on the Llama2 architecture, suitable for English text generation tasks

GPT-2 is a self-supervised pre-trained language model based on the Transformer architecture, which excels at text generation tasks.

This is a small GPT-2 model pre-trained on the TinyStories V2 dataset, featuring 3M trainable parameters and demonstrating good text generation coherence.

This is a 42M-parameter Llama 2 architecture float32 precision model trained on the TinyStories dataset, suitable for simple text generation tasks.

An instruction-following model fine-tuned based on Llama-2-70B, trained using the Dolly15k dataset, suitable for English text generation tasks.

Phi-1.5 model fine-tuned on the Hermes dataset, primarily used for text generation tasks

qCammel 70 is a large language model based on the Llama 2 architecture, developed by augtoma and quantized by TheBloke. This model focuses on text generation tasks, offering multiple quantization versions to suit different hardware requirements.

Pile-T5 Large is an encoder-decoder model trained on The Pile dataset based on the T5x library, primarily used for English text-to-text generation tasks.

Llama 2 is an open-source large language model series developed by Meta, ranging from 7B to 70B parameters, supporting English text generation tasks.

Cerebras-GPT 2.7B is a language model based on the Transformer architecture, aiming to support the research of large language models and can serve as a basic model in fields such as natural language processing.

Cerebras-GPT 590M is a language model based on the Transformer architecture and belongs to the Cerebras-GPT model family. It aims to study the scaling laws of large language models and demonstrate the simplicity and scalability of training large language models on the Cerebras software and hardware stack.

Pythia - 2.8 billion is a member of the scalable language model suite developed by EleutherAI, designed specifically to promote the interpretability research of large language models. This model is based on the Transformer architecture and is trained on the The Pile dataset, with 2.8 billion parameters.

Pythia-160M is a language model dedicated to interpretability research developed by EleutherAI. It belongs to the 160M parameter scale version in the Pythia suite and is based on the Transformer architecture, trained on the Pile dataset.