library

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.

7,028 Pulls 75 Tags Updated 13 days ago

falcon

A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.

6,646 Pulls 38 Tags Updated 6 weeks ago

stable-beluga

Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.

6,268 Pulls 49 Tags Updated 4 weeks ago

codeup

Great code generation model based on Llama2.

5,930 Pulls 19 Tags Updated 4 weeks ago

orca2

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.

5,601 Pulls 33 Tags Updated 2 weeks ago

everythinglm

Uncensored Llama2 based model with 16k context size.

4,979 Pulls 18 Tags Updated 4 weeks ago

medllama2

Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.

4,592 Pulls 17 Tags Updated 5 weeks ago

wizardlm-uncensored

Uncensored version of Wizard LM model

4,490 Pulls 18 Tags Updated 6 weeks ago

starcoder

StarCoder is a code generation model trained on 80+ programming languages.

3,573 Pulls 100 Tags Updated 6 weeks ago

dolphin2.2-mistral

An instruct-tuned model based on Mistral. Version 2.2 is fine-tuned for improved conversation and empathy.

3,523 Pulls 17 Tags Updated 10 days ago

wizard-vicuna

Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.

3,475 Pulls 17 Tags Updated 5 weeks ago

openchat

A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks.

3,334 Pulls 18 Tags Updated 3 weeks ago

open-orca-platypus2

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

openhermes2.5-mistral

OpenHermes 2.5 Mistral 7B is a Mistral 7B fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.

2,882 Pulls 17 Tags Updated 4 weeks ago

yarn-mistral

An extension of Mistral to support a context of up to 128k tokens.

2,715 Pulls 33 Tags Updated 4 weeks ago

samantha-mistral

A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.

2,153 Pulls 49 Tags Updated 7 weeks ago

sqlcoder

SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks

1,930 Pulls 33 Tags Updated 4 weeks ago

yarn-llama2

An extension of Llama 2 that supports a context of up to 128k tokens.

1,867 Pulls 67 Tags Updated 4 weeks ago

openhermes2-mistral

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

meditron

Open-source medical large language model adapted from Llama 2 to the medical domain.

1,478 Pulls 22 Tags Updated 4 days ago

wizardlm

General use 70 billion parameter model based on Llama 2.

1,369 Pulls 73 Tags Updated 5 weeks ago

mistrallite

MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.

1,318 Pulls 17 Tags Updated 4 weeks ago

dolphin2.1-mistral

An instruct-tuned model based on Mistral and trained on a dataset filtered to remove alignment and bias.

1,279 Pulls 17 Tags Updated 4 weeks ago

deepseek-llm

An advanced language model crafted with 2 trillion bilingual tokens.

1,257 Pulls 43 Tags Updated 9 days ago

codebooga

A high-performing code instruct model created by merging two existing code models.

1,218 Pulls 16 Tags Updated 4 weeks ago

goliath

A language model created by combining two fine-tuned Llama 2 70B models into one.

906 Pulls 16 Tags Updated 3 weeks ago

nexusraven

Nexus Raven is a 13B instruction tuned model for function calling tasks.

833 Pulls 32 Tags Updated 3 days ago

alfred

A robust conversational model designed to be used for both chat and instruct use cases.

778 Pulls 7 Tags Updated 2 weeks ago

xwinlm

Conversational model based on Llama 2 that performs competitively on various benchmarks.

697 Pulls 80 Tags Updated 4 weeks ago

stablelm-zephyr

A lightweight chat model allowing accurate, and responsive output without requiring high-end hardware.

661 Pulls 17 Tags Updated yesterday

magicoder

🎩 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.

658 Pulls 18 Tags Updated 3 days ago

Models

starling-lm

neural-chat

mistral

yi

llama2

codellama

llama2-uncensored

orca-mini

vicuna

wizard-vicuna-uncensored

phind-codellama

zephyr

wizardcoder

mistral-openorca

nous-hermes

wizard-math

llama2-chinese

deepseek-coder