Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.
109.5M Pulls 93 Tags Updated 1 year ago
Meta's Llama 3.2 goes small with 1B and 3B models.
55.3M Pulls 63 Tags Updated 1 year ago
Llama 3.2 Vision is a collection of instruction-tuned image reasoning generative models in 11B and 90B sizes.
3.7M Pulls 9 Tags Updated 8 months ago
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.
3.2M Pulls 14 Tags Updated 1 year ago
This model extends LLama-3 8B's context length from 8k to over 1m tokens.
305.6K Pulls 35 Tags Updated 1 year ago
Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
3.6M Pulls 5 Tags Updated 1 year ago
Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.
215.8K Pulls 17 Tags Updated 1 year ago
SmolLM2 is a family of compact language models available in three size: 135M, 360M, and 1.7B parameters.
2.4M Pulls 49 Tags Updated 1 year ago
https://huggingface.co/pansophic/pansophic-1-preview-LLaMA3.1-8b
66 Pulls 2 Tags Updated 1 year ago
base on llama3.1:8b
14 Pulls 1 Tag Updated 5 days ago
Claude 3.7 Sonnet based on llama 3.2. Inspired by incept5/llama3.1-claude
6,777 Pulls 1 Tag Updated 11 months ago
Deepseek R1 with the Claude 3.7 Sonnet system prompt. Inspired by incept5/llama3.1-claude
5,210 Pulls 1 Tag Updated 11 months ago
Typhoon2 8B Instruct - 8B parameters Thai / English bilingual LLM.
3,874 Pulls 1 Tag Updated 11 months ago
Claude 3.7 Sonnet based on llama 3.1. Inspired by incept5/llama3.1-claude
3,211 Pulls 1 Tag Updated 11 months ago
Deepseek R1 with the Claude 3.5 Sonnet system prompt. Inspired by incept5/llama3.1-claude
828 Pulls 1 Tag Updated 11 months ago
17 Pulls 1 Tag Updated 3 months ago
notConfucius.v2 is a fine-tuning experiment. llama3.1:8b base with a better designed dataset to reflect a particular cognitive persona - wiser, more coherent, less maddening, and still occasionally enlightening. it’s less a model and more a vibe.
16 Pulls 1 Tag Updated 5 months ago
https://huggingface.co/cognitivecomputations/Dolphin3.0-Llama3.1-8B-GGUF
340 Pulls 1 Tag Updated 11 months ago
304 Pulls 1 Tag Updated 10 months ago
218 Pulls 2 Tags Updated 6 months ago