Meta's Llama 3.2 goes small with 1B and 3B models.

281.5K  Pulls 63 Tags Updated  7 days ago

Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.

5.8M  Pulls 94 Tags Updated  2 weeks ago

Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B.

1.4M  Pulls 94 Tags Updated  2 weeks ago

Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.

652.8K  Pulls 133 Tags Updated  2 weeks ago

A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger sized models.

69.2K  Pulls 17 Tags Updated  6 weeks ago

A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.

13.4K  Pulls 17 Tags Updated  13 days ago

Mistral Small is a lightweight model designed for cost-effective use in tasks like translation and summarization.

14.9K  Pulls 17 Tags Updated  2 weeks ago

A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.

256.8K  Pulls 17 Tags Updated  11 days ago

An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.

330.4K  Pulls 65 Tags Updated  3 months ago

The 7B model released by Mistral AI, updated to version 0.3.

3.6M  Pulls 84 Tags Updated  4 months ago

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

434.9K  Pulls 69 Tags Updated  5 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.

309K  Pulls 85 Tags Updated  5 months ago

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

219K  Pulls 32 Tags Updated  4 weeks ago

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

97.8K  Pulls 21 Tags Updated  4 weeks ago

🌋 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.

1.3M  Pulls 98 Tags Updated  8 months ago

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

6.3M  Pulls 68 Tags Updated  4 months ago

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

4.1M  Pulls 102 Tags Updated  5 months ago

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

4M  Pulls 379 Tags Updated  3 months ago

Qwen2 is a new series of large language models from Alibaba group

3.8M  Pulls 97 Tags Updated  3 months ago

Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsoft.

2.5M  Pulls 72 Tags Updated  4 months ago

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

2.2M  Pulls 102 Tags Updated  7 months ago

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

1.4M  Pulls 199 Tags Updated  4 months ago

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

604.3K  Pulls 3 Tags Updated  7 months ago

Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.

403.1K  Pulls 87 Tags Updated  5 months ago

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

378.2K  Pulls 4 Tags Updated  6 months ago

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

340.9K  Pulls 18 Tags Updated  8 months ago

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

324.6K  Pulls 102 Tags Updated  9 months ago

Uncensored Llama 2 model by George Sung and Jarrad Hope.

320.1K  Pulls 34 Tags Updated  11 months ago

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

299K  Pulls 67 Tags Updated  4 weeks ago

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

228.5K  Pulls 120 Tags Updated  6 months ago

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

213.1K  Pulls 40 Tags Updated  5 months ago

Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills.

210.8K  Pulls 53 Tags Updated  4 weeks ago

Yi 1.5 is a high-performing, bilingual language model.

210.5K  Pulls 174 Tags Updated  4 months ago

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

207.2K  Pulls 119 Tags Updated  11 months ago

A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.

170.9K  Pulls 4 Tags Updated  4 months ago

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

155.8K  Pulls 17 Tags Updated  11 months ago

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

144.7K  Pulls 100 Tags Updated  12 months ago

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.

144.4K  Pulls 67 Tags Updated  2 weeks ago

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

142.5K  Pulls 36 Tags Updated  9 months ago

Codestral is Mistral AI’s first-ever code model designed for code generation tasks.

137.5K  Pulls 17 Tags Updated  4 weeks ago

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

137.4K  Pulls 111 Tags Updated  11 months ago

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

128.9K  Pulls 35 Tags Updated  11 months ago

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

122.7K  Pulls 49 Tags Updated  11 months ago

A versatile model for AI software development scenarios, including code completion.

116.3K  Pulls 17 Tags Updated  2 months ago

A family of open foundation models by IBM for Code Intelligence

114.9K  Pulls 162 Tags Updated  4 weeks ago

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

108.4K  Pulls 33 Tags Updated  9 months ago

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

107K  Pulls 16 Tags Updated  5 months ago

Embedding models on very large sentence level datasets.

104.1K  Pulls 10 Tags Updated  7 months ago

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

104K  Pulls 50 Tags Updated  8 months ago

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

102.9K  Pulls 30 Tags Updated  5 months ago

Aya 23, released by Cohere, is a new family of state-of-the-art, multilingual models that support 23 languages.

102.9K  Pulls 33 Tags Updated  4 weeks ago

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

97K  Pulls 22 Tags Updated  5 months ago

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

94.1K  Pulls 18 Tags Updated  8 months ago

State-of-the-art code generation model

93.4K  Pulls 67 Tags Updated  9 months ago

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.

91.8K  Pulls 36 Tags Updated  6 months ago

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

90.6K  Pulls 35 Tags Updated  9 months ago

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

87.2K  Pulls 17 Tags Updated  9 months ago

Qwen2 Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o).

87.1K  Pulls 52 Tags Updated  4 weeks ago

Stable LM 2 is a state-of-the-art 1.6B and 12B parameter language model trained on multilingual data in English, Spanish, German, Italian, French, Portuguese, and Dutch.

82.7K  Pulls 84 Tags Updated  4 months ago

This model extends LLama-3 8B's context length from 8k to over 1m tokens.

82.5K  Pulls 35 Tags Updated  5 months ago

An advanced language model crafted with 2 trillion bilingual tokens.

79.9K  Pulls 64 Tags Updated  10 months ago

Model focused on math and logic problems

78.6K  Pulls 64 Tags Updated  9 months ago

A strong multi-lingual general language model with competitive performance to Llama 3.

73.2K  Pulls 32 Tags Updated  2 months ago

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

73.1K  Pulls 50 Tags Updated  6 months ago

A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).

69.5K  Pulls 35 Tags Updated  4 months ago

moondream2 is a small vision language model designed to run efficiently on edge devices.

68.7K  Pulls 18 Tags Updated  4 months ago

A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course.

68.4K  Pulls 17 Tags Updated  3 weeks ago

Code generation model based on Code Llama.

66.2K  Pulls 49 Tags Updated  9 months ago

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

66K  Pulls 80 Tags Updated  11 months ago

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

65.9K  Pulls 63 Tags Updated  11 months ago

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

65.1K  Pulls 48 Tags Updated  11 months ago

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

63.9K  Pulls 35 Tags Updated  5 months ago

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

62.6K  Pulls 67 Tags Updated  11 months ago

Mistral Large 2 is Mistral's new flagship model that is significantly more capable in code generation, mathematics, and reasoning with 128k context window and support for dozens of languages.

61K  Pulls 17 Tags Updated  2 months ago

🪐 A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset.

60.9K  Pulls 94 Tags Updated  6 weeks ago

General use model based on Llama 2.

60.5K  Pulls 73 Tags Updated  5 months ago

A strong, economical, and efficient Mixture-of-Experts language model.

57.9K  Pulls 34 Tags Updated  4 weeks ago

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

55.8K  Pulls 36 Tags Updated  10 months ago

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

53.3K  Pulls 38 Tags Updated  11 months ago

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

52.9K  Pulls 49 Tags Updated  11 months ago

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

51.7K  Pulls 32 Tags Updated  9 months 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.

51.3K  Pulls 33 Tags Updated  10 months ago

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

47.1K  Pulls 49 Tags Updated  11 months ago

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

44K  Pulls 15 Tags Updated  9 months ago

Hermes 3 is the latest version of the flagship Hermes series of LLMs by Nous Research

40.4K  Pulls 49 Tags Updated  5 weeks ago

A new small LLaVA model fine-tuned from Phi 3 Mini.

40.2K  Pulls 4 Tags Updated  4 months ago

Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.

40.1K  Pulls 67 Tags Updated  4 weeks ago

Uncensored version of Wizard LM model

38.8K  Pulls 18 Tags Updated  13 months ago

InternLM2.5 is a 7B parameter model tailored for practical scenarios with outstanding reasoning capability.

38.3K  Pulls 65 Tags Updated  3 months ago

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

36.8K  Pulls 33 Tags Updated  9 months ago

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

36.1K  Pulls 33 Tags Updated  8 months ago

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

35K  Pulls 17 Tags Updated  11 months ago

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

33.5K  Pulls 22 Tags Updated  10 months ago

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

33K  Pulls 32 Tags Updated  10 months ago

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

31.7K  Pulls 18 Tags Updated  8 months ago

Great code generation model based on Llama2.

29.9K  Pulls 19 Tags Updated  11 months ago

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

28.2K  Pulls 18 Tags Updated  9 months ago

A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.

27.6K  Pulls 33 Tags Updated  2 months 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.

25.5K  Pulls 18 Tags Updated  10 months ago

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

24.9K  Pulls 17 Tags Updated  10 months ago

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

24.5K  Pulls 16 Tags Updated  11 months ago

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

23.1K  Pulls 17 Tags Updated  11 months ago

Falcon2 is an 11B parameters causal decoder-only model built by TII and trained over 5T tokens.

22.8K  Pulls 17 Tags Updated  4 months ago

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

21.5K  Pulls 17 Tags Updated  8 months ago

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

21.4K  Pulls 17 Tags Updated  11 months ago

A series of multimodal LLMs (MLLMs) designed for vision-language understanding.

20.3K  Pulls 17 Tags Updated  3 weeks ago

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

20.1K  Pulls 19 Tags Updated  8 months ago

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

19.3K  Pulls 18 Tags Updated  9 months ago

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

18.7K  Pulls 16 Tags Updated  10 months ago

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

18.7K  Pulls 17 Tags Updated  13 months ago

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

18.5K  Pulls 18 Tags Updated  9 months ago

BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.

18.1K  Pulls 3 Tags Updated  8 weeks ago

MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.

16.3K  Pulls 17 Tags Updated  2 months ago

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

14.9K  Pulls 7 Tags Updated  5 months ago

A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, based on Phi-3.

12.9K  Pulls 17 Tags Updated  2 months ago

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

11.6K  Pulls 7 Tags Updated  10 months ago

Solar Pro Preview: an advanced large language model (LLM) with 22 billion parameters designed to fit into a single GPU

11.5K  Pulls 18 Tags Updated  2 weeks ago

An open weights function calling model based on Llama 3, competitive with GPT-4o function calling capabilities.

10.6K  Pulls 17 Tags Updated  2 months ago

A series of models that convert HTML content to Markdown content, which is useful for content conversion tasks.

8,763  Pulls 33 Tags Updated  3 weeks ago

Embedding model from BAAI mapping texts to vectors.

6,900  Pulls 3 Tags Updated  8 weeks ago

An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.

5,443  Pulls 7 Tags Updated  3 weeks ago

A state-of-the-art fact-checking model developed by Bespoke Labs.

4,173  Pulls 17 Tags Updated  2 weeks ago

Sentence-transformers model that can be used for tasks like clustering or semantic search.

3,908  Pulls 3 Tags Updated  8 weeks ago