Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.
2,098 Pulls 18 Tags Updated 10 days ago
A fine-tuned model based on Mistral with good coverage of domain and language.
2,839 Pulls 34 Tags Updated 6 days ago
The Mistral 7B model released by Mistral AI
68.6K Pulls 36 Tags Updated 6 weeks ago
A high-performing, bilingual base model.
2,539 Pulls 62 Tags Updated 12 days ago
The most popular model for general use.
138.6K Pulls 102 Tags Updated 3 weeks ago
A large language model that can use text prompts to generate and discuss code.
70.2K Pulls 150 Tags Updated 6 weeks ago
Uncensored Llama 2 model by George Sung and Jarrad Hope.
30.4K Pulls 34 Tags Updated 4 weeks ago
A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.
25.7K Pulls 119 Tags Updated 4 weeks ago
General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.
21.7K Pulls 111 Tags Updated 4 weeks ago
Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.
13.5K Pulls 49 Tags Updated 4 weeks ago
Code generation model based on CodeLlama.
10.6K Pulls 49 Tags Updated 5 weeks ago
Zephyr beta is a fine-tuned 7B version of mistral that was trained on on a mix of publicly available, synthetic datasets.
9,986 Pulls 34 Tags Updated 10 days ago
Llama based code generation model focused on Python.
9,800 Pulls 50 Tags Updated 3 weeks ago
Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.
9,168 Pulls 17 Tags Updated 8 weeks ago
General use models based on Llama and Llama 2 from Nous Research.
8,796 Pulls 63 Tags Updated 4 weeks ago
Model focused on math and logic problems
7,790 Pulls 49 Tags Updated 4 weeks ago
Llama 2 based model fine tuned to improve Chinese dialogue ability.
7,337 Pulls 35 Tags Updated 5 weeks ago
DeepSeek Coder is trained from scratch on both 87% code and 13% natural language in English and Chinese. Each of the models are pre-trained on 2 trillion tokens.
7,020 Pulls 75 Tags Updated 13 days ago
A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.
6,642 Pulls 38 Tags Updated 6 weeks ago
Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.
6,267 Pulls 49 Tags Updated 4 weeks ago
Great code generation model based on Llama2.
5,928 Pulls 19 Tags Updated 4 weeks ago
Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoning.
5,597 Pulls 33 Tags Updated 2 weeks ago
Uncensored Llama2 based model with 16k context size.
4,977 Pulls 18 Tags Updated 4 weeks ago
Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.
4,591 Pulls 17 Tags Updated 5 weeks ago
Uncensored version of Wizard LM model
4,490 Pulls 18 Tags Updated 6 weeks ago
StarCoder is a code generation model trained on 80+ programming languages.
3,571 Pulls 100 Tags Updated 6 weeks ago
An instruct-tuned model based on Mistral. Version 2.2 is fine-tuned for improved conversation and empathy.
3,520 Pulls 17 Tags Updated 10 days ago
Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.
3,475 Pulls 17 Tags Updated 5 weeks ago
A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks.
3,324 Pulls 18 Tags Updated 3 weeks ago
Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.
3,134 Pulls 17 Tags Updated 5 weeks ago
OpenHermes 2.5 Mistral 7B is a Mistral 7B fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.
2,881 Pulls 17 Tags Updated 4 weeks ago
An extension of Mistral to support a context of up to 128k tokens.
2,711 Pulls 33 Tags Updated 4 weeks ago
A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.
2,153 Pulls 49 Tags Updated 7 weeks ago
SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks
1,928 Pulls 33 Tags Updated 4 weeks ago
An extension of Llama 2 that supports a context of up to 128k tokens.
1,866 Pulls 67 Tags Updated 4 weeks ago
OpenHermes 2 Mistral is a 7B model fine-tuned on Mistral with 900,000 entries of primarily GPT-4 generated data from open datasets.
1,680 Pulls 17 Tags Updated 7 weeks ago
Open-source medical large language model adapted from Llama 2 to the medical domain.
1,464 Pulls 22 Tags Updated 3 days ago
General use 70 billion parameter model based on Llama 2.
1,369 Pulls 73 Tags Updated 5 weeks ago
MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.
1,317 Pulls 17 Tags Updated 4 weeks ago
An instruct-tuned model based on Mistral and trained on a dataset filtered to remove alignment and bias.
1,277 Pulls 17 Tags Updated 4 weeks ago
An advanced language model crafted with 2 trillion bilingual tokens.
1,256 Pulls 43 Tags Updated 9 days ago
A high-performing code instruct model created by merging two existing code models.
1,218 Pulls 16 Tags Updated 4 weeks ago
A language model created by combining two fine-tuned Llama 2 70B models into one.
906 Pulls 16 Tags Updated 3 weeks ago
Nexus Raven is a 13B instruction tuned model for function calling tasks.
832 Pulls 32 Tags Updated 3 days ago
A robust conversational model designed to be used for both chat and instruct use cases.
777 Pulls 7 Tags Updated 2 weeks ago
Conversational model based on Llama 2 that performs competitively on various benchmarks.
697 Pulls 80 Tags Updated 4 weeks ago
🎩 Magicoder is a family of 7B parameter models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets.
653 Pulls 18 Tags Updated 3 days ago
A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.
648 Pulls 17 Tags Updated yesterday