llama3-gradient
This model extends LLama-3 8B's context length from 8k to over 1m tokens.
8b
70b
⬇ 985.1K indirme · 35 varyant · 05.2024
Açık Kaynak AI Modelleri
Kendi bilgisayarınızda veya sunucunuzda ücretsiz çalıştırabileceğiniz modeller. Katalog ollama.com kütüphanesiyle canlı senkrondur · Son senkron: 13.08.2026 22:48.
233 model
qwen
Qwen 1.5 is a series of large language models by Alibaba Cloud spanning from 0.5B to 110B parameters
0.5b
1.8b
4b
7b
⬇ 7.5M indirme · 379 varyant · 04.2024
snowflake-arctic-embed
A suite of text embedding models by Snowflake, optimized for performance.
Embedding
22m
33m
110m
137m
⬇ 3.1M indirme · 16 varyant · 04.2024
dbrx
DBRX is an open, general-purpose LLM created by Databricks.
132b
⬇ 362.1K indirme · 7 varyant · 04.2024
wizardlm2
State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.
7b
8x22b
⬇ 1.2M indirme · 22 varyant · 04.2024
zephyr
Zephyr is a series of fine-tuned versions of the Mistral and Mixtral models that are trained to act as helpful assistants.
7b
141b
⬇ 1.2M indirme · 40 varyant · 04.2024
gemma
Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1
2b
7b
⬇ 7.3M indirme · 102 varyant · 04.2024
dolphincoder
A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.
7b
15b
⬇ 991.7K indirme · 35 varyant · 04.2024
starling-lm
Starling is a large language model trained by reinforcement learning from AI feedback focused on improving chatbot helpfulness.
7b
⬇ 967.5K indirme · 36 varyant · 04.2024
dolphin-mistral
The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.
7b
⬇ 1.6M indirme · 120 varyant · 04.2024
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.
3b
⬇ 1M indirme · 36 varyant · 03.2024
nomic-embed-text
A high-performing open embedding model with a large token context window.
Embedding
⬇ 82.2M indirme · 3 varyant · 02.2024
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.
Görüntü
7b
13b
34b
⬇ 14.6M indirme · 98 varyant · 02.2024
sqlcoder
SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks
7b
15b
⬇ 1.5M indirme · 48 varyant · 02.2024
tinydolphin
An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.
1.1b
⬇ 714.7K indirme · 18 varyant · 01.2024
duckdb-nsql
7B parameter text-to-SQL model made by MotherDuck and Numbers Station.
7b
⬇ 518.8K indirme · 17 varyant · 01.2024
nexusraven
Nexus Raven is a 13B instruction tuned model for function calling tasks.
13b
⬇ 882.5K indirme · 32 varyant · 01.2024
megadolphin
MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.
120b
⬇ 560K indirme · 19 varyant · 01.2024
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.
7b
⬇ 1.3M indirme · 50 varyant · 01.2024
llama-pro
An expansion of Llama 2 that specializes in integrating both general language understanding and domain-specific knowledge, particularly in programming and mathematics.
⬇ 896.6K indirme · 33 varyant · 01.2024
phi
Phi-2: a 2.7B language model by Microsoft Research that demonstrates outstanding reasoning and language understanding capabilities.
2.7b
⬇ 1.5M indirme · 18 varyant · 01.2024
wizardcoder
State-of-the-art code generation model
33b
⬇ 1M indirme · 67 varyant · 01.2024
nous-hermes2
The powerful family of models by Nous Research that excels at scientific discussion and coding tasks.
10.7b
34b
⬇ 1.1M indirme · 33 varyant · 01.2024
tinyllama
The TinyLlama project is an open endeavor to train a compact 1.1B Llama model on 3 trillion tokens.
1.1b
⬇ 5.4M indirme · 36 varyant · 01.2024
Açık kaynak model nasıl çalıştırılır?
Bu modeller Ollama ile tek komutla bilgisayarınızda çalışır (Windows, macOS, Linux). Verileriniz cihazınızdan çıkmaz — gizlilik gerektiren işler için idealdir.
- ollama.com/download adresinden Ollama'yı kurun
- Model sayfasındaki
ollama run …komutunu terminale yapıştırın - İlk indirme sonrası model tamamen çevrimdışı çalışır