# Text Generation Optimization

This is a quantized version of the Sarvam-m model, supporting text generation tasks in multiple Indian languages and English.

This model has undergone self-quantization processing, with output and embedding tensors quantized to f16 format, and the remaining tensors quantized to q5_k or q6_k format, resulting in a smaller size while maintaining performance comparable to pure f16.

Compressible version of Llama-2-13b provided by the ACIP project, supporting dynamic adjustment of compression ratio

A 9-billion-parameter large language model based on the DeepSeek-V3 architecture, trained from scratch using a fully open-source and exclusively English dataset of over 350 billion tokens, specifically designed for open-source community development and debugging.

This is a merged model based on the Gemma-2-9B series, utilizing the DARE TIES method to combine multiple Gemma variants, aiming to enhance text generation capabilities.

A large language model based on the Phi 4 architecture, with 14 billion parameters, optimized for natural language processing and text dialogue tasks.

An optimized layer merging (OLM) model based on Qwen2.5-7B, enhancing performance through automated layer reorganization techniques

Diffusion language model fine-tuned based on Llama-2-7b

L3-8B-Lunar-Stheno is a model merged from L3-8B-Lunaris-v1 and L3-8B-Stheno-v3.2, addressing issues of overly long responses and insufficient initiative while enhancing context awareness and text generation capabilities.

GGUF-Imatrix quantized version of Prodigy_7B, utilizing importance matrix technology to enhance quantization quality

A medium-scale Mixture of Experts (MoE) implementation based on Dolphin-2.6-Mistral-7B-DPO-Laser, with an average performance improvement of approximately 1 point in evaluations

A GPT2-based prompt expansion model designed to enhance the quality and diversity of text generation prompts

This model is a fine-tuned version of distilroberta-base on the wikitext2 dataset, primarily used for text generation tasks.

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.

This model is a fine-tuned version of distilroberta-base on the wikitext2 dataset, primarily used for text generation tasks.

This model is a fine-tuned version of t5-small on an unknown dataset, primarily used for text rewriting tasks, specifically targeting PubMed-related texts.

GPT-2 language model trained with the SimCTG framework, using contrastive search to generate more coherent text

This model is a fine-tuned version of distilroberta-base on the wikitext2 dataset, primarily used for text generation tasks.

This model is a fine-tuned version of distilroberta-base on the wikitext2 dataset, primarily designed for text generation tasks.

A fine-tuned version of the distilroberta-base model on the wikitext2 dataset, suitable for text-related tasks