Models
BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. You can use this model for text summarization.
BAAI general embedding (Base) model that transforms any given text into a 768-dimensional vector
BAAI general embedding (Large) model that transforms any given text into a 1024-dimensional vector
BAAI general embedding (Small) model that transforms any given text into a 384-dimensional vector
Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese.
Deepseek Coder is composed of a series of code language models, each trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese.
DeepSeekMath-Instruct 7B is a mathematically instructed tuning model derived from DeepSeekMath-Base 7B. DeepSeekMath is initialized with DeepSeek-Coder-v1.5 7B and continues pre-training on math-related tokens sourced from Common Crawl, together with natural language and code data for 500B tokens.
DEtection TRansformer (DETR) model trained end-to-end on COCO 2017 object detection (118k annotated images).
DiscoLM German 7b is a Mistral-based large language model with a focus on German-language applications. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.
distilbert-sst-2-int8Distilled BERT model that was finetuned on SST-2 for sentiment classification
Stable Diffusion model that has been fine-tuned to be better at photorealism without sacrificing range.
Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by TII based on Falcon-7B and finetuned on a mixture of chat/instruct datasets.
FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions.
gemma-2b-it-loraBetaThis is a Gemma-2B base model that Cloudflare dedicates for inference with LoRA adapters. 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.
- LoRA
gemma-7b-it-loraBetaThis is a Gemma-7B base model that Cloudflare dedicates for inference with LoRA adapters. 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.
- LoRA
gemma-7b-itBetaGemma 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. They are text-to-text, decoder-only large language models, available in English, with open weights, pre-trained variants, and instruction-tuned variants.
- LoRA
Hermes 2 Pro on Mistral 7B is the new flagship 7B Hermes! Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
- Function calling
Llama 2 13B Chat AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Llama 2 variant.
llama-2-7b-chat-fp16Full precision (fp16) generative text model with 7 billion parameters from Meta
This is a Llama2 base model that Cloudflare dedicated for inference with LoRA adapters. Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format.
- LoRA
llama-2-7b-chat-int8Quantized (int8) generative text model with 7 billion parameters from Meta
llama-3-8b-instruct-awqQuantized (int4) generative text model with 8 billion parameters from Meta.
llama-3-8b-instructGeneration over generation, Meta Llama 3 demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.
llama-3.1-70b-instructBetaThe Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models. The Llama 3.1 instruction tuned text only models are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.
llama-3.1-8b-instruct-awqQuantized (int4) generative text model with 8 billion parameters from Meta.
llama-3.1-8b-instruct-fastBeta[Fast version] The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models. The Llama 3.1 instruction tuned text only models are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.
llama-3.1-8b-instruct-fp8Llama 3.1 8B quantized to FP8 precision
llama-3.1-8b-instructThe Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models. The Llama 3.1 instruction tuned text only models are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.
llama-3.2-11b-vision-instructThe Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image.
llama-3.2-1b-instructThe Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.
llama-3.2-3b-instructThe Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks.
llama-3.3-70b-instruct-fp8-fastLlama 3.3 70B quantized to fp8 precision, optimized to be faster.
Llama Guard is a model for classifying the safety of LLM prompts and responses, using a taxonomy of safety risks.
LLaVA is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture.
m2m100-1.2bMultilingual encoder-decoder (seq-to-seq) model trained for Many-to-Many multilingual translation
Generation over generation, Meta Llama 3 demonstrates state-of-the-art performance on a wide range of industry benchmarks and offers new capabilities, including improved reasoning.
Mistral 7B Instruct v0.1 AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Mistral variant.
mistral-7b-instruct-v0.1Instruct fine-tuned version of the Mistral-7b generative text model with 7 billion parameters
- LoRA
mistral-7b-instruct-v0.2-loraBetaThe Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.
- LoRA
mistral-7b-instruct-v0.2BetaThe Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2. Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1: 32k context window (vs 8k context in v0.1), rope-theta = 1e6, and no Sliding-Window Attention.
- LoRA
This model is a fine-tuned 7B parameter LLM on the Intel Gaudi 2 processor from the mistralai/Mistral-7B-v0.1 on the open source dataset Open-Orca/SlimOrca.
OpenChat is an innovative library of open-source language models, fine-tuned with C-RLFT - a strategy inspired by offline reinforcement learning.
OpenHermes 2.5 Mistral 7B is a state of the art Mistral Fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.
phi-2BetaPhi-2 is a Transformer-based model with a next-word prediction objective, trained on 1.4T tokens from multiple passes on a mixture of Synthetic and Web datasets for NLP and coding.
Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.
Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud.
Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.
Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization.
resnet-5050 layers deep image classification CNN trained on more than 1M images from ImageNet
This model is intended to be used by non-technical users to understand data inside their SQL databases.
Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images. Img2img generate a new image from an input image with Stable Diffusion.
Stable Diffusion Inpainting is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input, with the extra capability of inpainting the pictures by using a mask.
stable-diffusion-xl-base-1.0BetaDiffusion-based text-to-image generative model by Stability AI. Generates and modify images based on text prompts.
SDXL-Lightning is a lightning-fast text-to-image generation model. It can generate high-quality 1024px images in a few steps.
We introduce Starling-LM-7B-beta, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF). Starling-LM-7B-beta is trained from Openchat-3.5-0106 with our new reward model Nexusflow/Starling-RM-34B and policy optimization method Fine-Tuning Language Models from Human Preferences (PPO).
The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. This is the chat model finetuned on top of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T.
UForm-Gen is a small generative vision-language model primarily designed for Image Captioning and Visual Question Answering. The model was pre-trained on the internal image captioning dataset and fine-tuned on public instructions datasets: SVIT, LVIS, VQAs datasets.
Cybertron 7B v2 is a 7B MistralAI based model, best on it's series. It was trained with SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets.
whisper-large-v3-turboBetaWhisper is a pre-trained model for automatic speech recognition (ASR) and speech translation.
whisper-tiny-enBetaWhisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalize to many datasets and domains without the need for fine-tuning. This is the English-only version of the Whisper Tiny model which was trained on the task of speech recognition.
whisperWhisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.
Zephyr 7B Beta AWQ is an efficient, accurate and blazing-fast low-bit weight quantized Zephyr model variant.