library

llama3

Meta Llama 3: The most capable openly available LLM to date

441.1K Pulls 67 Tags Updated 4 days ago

phi3

Phi-3 Mini is a 3.8B parameters, lightweight, state-of-the-art open model by Microsoft.

39.2K Pulls 6 Tags Updated 3 days ago

wizardlm2

State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.

29.7K Pulls 22 Tags Updated 10 days ago

mistral

The 7B model released by Mistral AI, updated to version 0.2.

656.3K Pulls 68 Tags Updated 4 weeks ago

gemma

Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1

990.2K Pulls 102 Tags Updated 2 weeks ago

mixtral

A set of Mixture of Experts (MoE) model with open weights by Mistral AI in 8x7b and 8x22b parameter sizes.

195.2K Pulls 56 Tags Updated 9 days ago

llama2

Llama 2 is a collection of foundation language models ranging from 7B to 70B parameters.

1.3M Pulls 102 Tags Updated 2 months ago

CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks like fill-in-the-middle code completion, code generation, natural language understanding, mathematical reasoning, and instruction following.

29.4K Pulls 53 Tags Updated 10 days ago

command-r

Command R is a Large Language Model optimized for conversational interaction and long context tasks.

26.4K Pulls 17 Tags Updated 4 weeks ago

command-r-plus

Command R+ is a powerful, scalable large language model purpose-built to excel at real-world enterprise use cases.

22.5K Pulls 6 Tags Updated 10 days ago

llava

🌋 LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna for general-purpose visual and language understanding. Updated to version 1.6.

156K Pulls 98 Tags Updated 2 months ago

dbrx

DBRX is an open, general-purpose LLM created by Databricks.

3,151 Pulls 7 Tags Updated 10 days ago

codellama

A large language model that can use text prompts to generate and discuss code.

361.2K Pulls 199 Tags Updated 2 months ago

qwen

Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 110B parameters

216.6K Pulls 379 Tags Updated 17 hours ago

dolphin-mixtral

An uncensored, fine-tuned model based on the Mixtral mixture of experts model that excels at coding tasks. Created by Eric Hartford.

204.2K Pulls 70 Tags Updated 3 months ago

llama2-uncensored

Uncensored Llama 2 model by George Sung and Jarrad Hope.

161.7K Pulls 34 Tags Updated 5 months ago

mistral-openorca

Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.

119.4K Pulls 17 Tags Updated 6 months ago

deepseek-coder

DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.

106K Pulls 102 Tags Updated 4 months ago

phi

Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.

87.4K Pulls 18 Tags Updated 2 months ago

dolphin-mistral

The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.

74.8K Pulls 120 Tags Updated 3 weeks ago

nomic-embed-text

A high-performing open embedding model with a large token context window.

73.9K Pulls 3 Tags Updated 8 weeks ago

nous-hermes2

The powerful family of models by Nous Research that excels at scientific discussion and coding tasks.

72.8K Pulls 33 Tags Updated 3 months ago

orca-mini

A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.

71.8K Pulls 119 Tags Updated 5 months ago

llama2-chinese

Llama 2 based model fine tuned to improve Chinese dialogue ability.

50.6K Pulls 35 Tags Updated 6 months ago

zephyr

Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants.

48.5K Pulls 40 Tags Updated 11 days ago

wizard-vicuna-uncensored

Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.

47.3K Pulls 49 Tags Updated 5 months ago

openhermes

OpenHermes 2.5 is a 7B model fine-tuned by Teknium on Mistral with fully open datasets.

41.9K Pulls 35 Tags Updated 3 months ago

vicuna

General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.

38.9K Pulls 111 Tags Updated 5 months ago

tinyllama

The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.

37K Pulls 36 Tags Updated 3 months ago

tinydolphin

An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.

36.1K Pulls 18 Tags Updated 2 months ago

openchat

A family of open-source models trained on a wide variety of data, surpassing ChatGPT on various benchmarks. Updated to version 3.5-0106.

34K Pulls 50 Tags Updated 3 months ago

starcoder2

StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.

33.5K Pulls 49 Tags Updated 7 weeks ago

wizardcoder

State-of-the-art code generation model

28.8K Pulls 67 Tags Updated 3 months ago

stable-code

Stable Code 3B is a coding model with instruct and code completion variants on par with models such as Code Llama 7B that are 2.5x larger.

28.6K Pulls 36 Tags Updated 4 weeks ago

starcoder

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

28.5K Pulls 100 Tags Updated 6 months ago

neural-chat

A fine-tuned model based on Mistral with good coverage of domain and language.

24K Pulls 50 Tags Updated 4 weeks ago

yi

A high-performing, bilingual language model.

23.1K Pulls 78 Tags Updated 4 months ago

phind-codellama

Code generation model based on Code Llama.

22.2K Pulls 49 Tags Updated 4 months ago

starling-lm

Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.

19.6K Pulls 36 Tags Updated 3 weeks ago

wizard-math

Model focused on math and logic problems

19K Pulls 64 Tags Updated 4 months ago

falcon

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

19K Pulls 38 Tags Updated 6 months ago

dolphin-phi

2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.

18.9K Pulls 15 Tags Updated 4 months 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.

18.8K Pulls 33 Tags Updated 5 months ago

dolphincoder

A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.

16.2K Pulls 35 Tags Updated 2 weeks ago

mxbai-embed-large

State-of-the-art large embedding model from mixedbread.ai

15.3K Pulls 3 Tags Updated 4 weeks ago

nous-hermes

General use models based on Llama and Llama 2 from Nous Research.

15K Pulls 63 Tags Updated 5 months ago

solar

A compact, yet powerful 10.7B large language model designed for single-turn conversation.

13.8K Pulls 32 Tags Updated 4 months ago

bakllava

BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.

13.7K Pulls 17 Tags Updated 4 months ago

sqlcoder

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

13.6K Pulls 48 Tags Updated 2 months ago

medllama2

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

13.5K Pulls 17 Tags Updated 6 months ago

nous-hermes2-mixtral

The Nous Hermes 2 model from Nous Research, now trained over Mixtral.

13K Pulls 18 Tags Updated 3 months ago

wizardlm-uncensored

Uncensored version of Wizard LM model

12.7K Pulls 18 Tags Updated 6 months ago

codeup

Great code generation model based on Llama2.

11.7K Pulls 19 Tags Updated 5 months ago

dolphin-llama3

Dolphin 2.9 is a new model by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills.

11.5K Pulls 19 Tags Updated 6 days ago

stablelm2

Stable LM 2 is a state-of-the-art 1.6B parameter language model trained on multilingual data in English, Spanish, German, Italian, French, Portuguese, and Dutch.

11.1K Pulls 51 Tags Updated 2 weeks ago

everythinglm

Uncensored Llama2 based model with support for a 16K context window.

11.1K Pulls 18 Tags Updated 4 months ago

all-minilm

Embedding models on very large sentence level datasets.

10.6K Pulls 8 Tags Updated 2 months ago

samantha-mistral

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

9,571 Pulls 49 Tags Updated 6 months ago

yarn-mistral

An extension of Mistral to support context windows of 64K or 128K.

9,232 Pulls 33 Tags Updated 4 months ago

stable-beluga

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

8,985 Pulls 49 Tags Updated 5 months ago

meditron

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

8,980 Pulls 22 Tags Updated 4 months ago

yarn-llama2

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

8,773 Pulls 67 Tags Updated 5 months ago

deepseek-llm

An advanced language model crafted with 2 trillion bilingual tokens.

8,719 Pulls 64 Tags Updated 4 months ago

llama-pro

An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.

8,037 Pulls 33 Tags Updated 3 months ago

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.

7,837 Pulls 18 Tags Updated 4 months ago

stablelm-zephyr

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

7,747 Pulls 17 Tags Updated 4 months ago

codebooga

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

7,272 Pulls 16 Tags Updated 5 months ago

codeqwen

CodeQwen1.5 is a large language model pretrained on a large amount of code data.

6,810 Pulls 21 Tags Updated 10 days ago

mistrallite

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

6,800 Pulls 17 Tags Updated 5 months ago

wizard-vicuna

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

6,612 Pulls 17 Tags Updated 6 months ago

nexusraven

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

5,927 Pulls 32 Tags Updated 3 months ago

goliath

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

5,061 Pulls 16 Tags Updated 5 months ago

xwinlm

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

4,906 Pulls 80 Tags Updated 5 months ago

open-orca-platypus2

Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.

4,797 Pulls 17 Tags Updated 6 months ago

wizardlm

General use model based on Llama 2.

4,508 Pulls 73 Tags Updated 11 days ago

notux

A top-performing mixture of experts model, fine-tuned with high-quality data.

4,268 Pulls 18 Tags Updated 3 months ago

megadolphin

MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.

4,050 Pulls 19 Tags Updated 3 months ago

duckdb-nsql

7B parameter text-to-SQL model made by MotherDuck and Numbers Station.

3,849 Pulls 17 Tags Updated 2 months ago

alfred

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

3,781 Pulls 7 Tags Updated 5 months ago

notus

A 7B chat model fine-tuned with high-quality data and based on Zephyr.

3,324 Pulls 18 Tags Updated 3 months ago

snowflake-arctic-embed

A suite of text embedding models by Snowflake, optimized for performance.

2,262 Pulls 16 Tags Updated 10 days ago

Models