together.

The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pre-trained and instruction tuned generative models in 8B, 70B and 405B sizes. The Llama 3.1 Instruct models (8B, 70B, 405B) outperform many of the available open source and closed chat models on common industry benchmarks.

The Mixtral-8x22B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.

The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.

A transformer-based decoder-only language model pre-trained on a large amount of data. In comparison with the previously released Qwen

Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.

A hybrid architecture composed of multi-head, grouped-query attention and gated convolutions arranged in Hyena blocks, different from traditional decoder-only Transformers

An universal English sentence embedding model by WhereIsAI. Its embedding dimension is 1024, it takes up to 512 context length.

Arctic is a dense-MoE Hybrid transformer architecture pre-trained from scratch by the Snowflake AI Research Team.

DBRX Instruct is a mixture-of-experts (MoE) large language model trained from scratch by Databricks. DBRX Instruct specializes in few-turn interactions.

Trained from scratch on a vast dataset of 2 trillion tokens in both English and Chinese.

A text-to-image generative AI model that excels at creating 1024x1024 images.

The Yi series models are large language models trained from scratch by developers at 01.AI

An 80M checkpoint of M2-BERT, pretrained with sequence length 32768, and it has been fine-tuned for long-context retrieval.

Code Llama is a family of large language models for code based on Llama 2 providing infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks.

instruct fine-tuned version of Mistral-7B-v0.1

Designed for few-shot prompts, fine-tuned over the RedPajama-INCITE-Base-7B-v1 base model.

Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.

First Nous collection of dataset and models made by fine-tuning mostly on data created by Nous in-house

NexusRaven is an open-source and commercially viable function calling LLM that surpasses the state-of-the-art in function calling capabilities.

Nous-Hermes-Llama2-13b is a state-of-the-art language model fine-tuned on over 300,000 instructions.

This model achieves a substantial and comprehensive improvement on coding, mathematical reasoning and open-domain conversation capacities

This model empowers Code LLMs with complex instruction fine-tuning, by adapting the Evol-Instruct method to the domain of code.

An 80M checkpoint of M2-BERT, pretrained with sequence length 8192, and it has been fine-tuned for long-context retrieval.

An 80M checkpoint of M2-BERT, pretrained with sequence length 2048, and it has been fine-tuned for long-context retrieval.

BAAI general embedding - large, english - model v1.5. FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector databases for LLMs.

Extending LLaMA-2 to 32K context, built with Meta's Position Interpolation and Together AI's data recipe and system optimizations, instruction tuned by Together

BAAI general embedding - base, english - model v1.5. FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector databases for LLMs.

7.3B parameter model that outperforms Llama 2 13B on all benchmarks, approaches CodeLlama 7B performance on code, Uses Grouped-query attention (GQA) for faster inference and Sliding Window Attention (SWA) to handle longer sequences at smaller cost

Code Llama is a family of large language models for code based on Llama 2 providing infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks.

Latent text-to-image diffusion model capable of generating photo-realistic images given any text input.

Vicuna is a chat assistant trained by fine-tuning Llama 2 on user-shared conversations collected from ShareGPT.

Phind-CodeLlama-34B-v1 trained on additional 1.5B tokens high-quality programming-related data proficient in Python, C/C++, TypeScript, Java, and more.

Fine-tune version of Stable Diffusion focused on photorealism.

Language model trained on 2 trillion tokens with double the context length of Llama 1. Available in three sizes: 7B, 13B and 70B parameters

Code Llama is a family of large language models for code based on Llama 2 providing infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks.

Extending LLaMA-2 to 32K context, built with Meta's Position Interpolation and Together AI's data recipe and system optimizations.

This model is a 75/25 merge of Chronos (13B) and Nous Hermes (13B) models resulting in having a great ability to produce evocative storywriting and follow a narrative.

An instruction fine-tuned LLaMA-2 (70B) model by merging Platypus2 (70B) by garage-bAInd and LLaMA-2 Instruct v2 (70B) by upstage.

This model achieves a substantial and comprehensive improvement on coding, mathematical reasoning and open-domain conversation capacities.

MythoLogic-L2 and Huginn merge using a highly experimental tensor type merge technique. The main difference with MythoMix is that I allowed more of Huginn to intermingle with the single tensors located at the front and end of a model

7B-parameter version of the large language model series, Qwen (abbr. Tongyi Qianwen), proposed by Aibaba Cloud. Qwen-7B-Chat is a large-model-based AI assistant, which is trained with alignment techniques.

7B-parameter version of the large language model series, Qwen (abbr. Tongyi Qianwen), proposed by Aibaba Cloud. Qwen-7B is a Transformer-based large language model, which is pretrained on a large volume of data, including web texts, books, codes, etc.

Chat model fine-tuned using data from Dolly 2.0 and Open Assistant over the RedPajama-INCITE-Base-7B-v1 base model.

Base model that aims to replicate the LLaMA recipe as closely as possible (blog post).

Pretrained model on English language using a masked language modeling (MLM) objective. The embedding dimension is 768, and the number of model parameters is 110M. This model is uncased: it does not make a difference between english and English.

This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and was designed for semantic search. It has been trained on 500K (query, answer) pairs from the MS MARCO dataset. Its embedding dimension is 768 with 512 max context length.

This model can be used to moderate other chatbot models. Built using GPT-JT model fine-tuned on Ontocord.ai's OIG-moderation dataset v0.1.

Fork of GPT-J instruction tuned to excel at few-shot prompts (blog post).

Chat model fine-tuned from EleutherAI’s GPT-NeoX with over 40 million instructions on carbon reduced compute.

An auto-regressive language model, based on the transformer architecture. The model comes in different sizes: 7B, 13B, 33B and 65B parameters.

Falcon-40B-Instruct is a causal decoder-only model built by TII based on Falcon-40B and finetuned on a mixture of Baize.

Falcon-40B is a causal decoder-only model built by TII and trained on 1,000B tokens of RefinedWeb enhanced with curated corpora.

An open source Stable Diffusion model fine tuned model on Midjourney images.

Chat model based on EleutherAI’s Pythia-7B model, and is fine-tuned with data focusing on dialog-style interactions.

Dreambooth model trained on a diverse set of analog photographs to provide an analog film effect.