Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.
117.3M Pulls 93 Tags Updated 1 year ago
Meta's Llama 3.2 goes small with 1B and 3B models.
76.8M 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.
4.9M Pulls 9 Tags Updated 1 year ago
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to the Llama 3.1 405B model.
4M Pulls 14 Tags Updated 1 year ago
This model extends LLama-3 8B's context length from 8k to over 1m tokens.
967.7K Pulls 35 Tags Updated 2 years 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.
3.9M 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.
595.9K 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.
3.5M Pulls 49 Tags Updated 1 year ago
This are Llama3.1 models with Anthropic's Claude Sonnet 3.5 system prompt.
104.6K Pulls 2 Tags Updated 1 year ago
Lexi Uncensored Llama3.1 8b
4,903 Pulls 1 Tag Updated 1 year ago
Vikhr-Llama3.1-8B-Instruct-R-21-09-24
1,080 Pulls 2 Tags Updated 1 year ago
https://huggingface.co/cognitivecomputations/Dolphin3.0-Llama3.1-8B-GGUF
541 Pulls 1 Tag Updated 1 year ago
Custom modelfile updated from llama3.1:8b into wangrongsheng/Llama3.1-8B-Chinese-Chat-Q4_0-GGUF
220 Pulls 1 Tag Updated 1 year ago
1 Pull 1 Tag Updated 1 year ago
llama.31 using cladue sonnets prompting system
1,097 Pulls 1 Tag Updated 4 months ago
a model i made that uses llama 3.1 but changes everything to be grok like.
383 Pulls 1 Tag Updated 4 months ago
216 Pulls 1 Tag Updated 4 months ago
99 Pulls 39 Tags Updated yesterday
Optimized for real-world data science decisions. It delivers method selection, alternative comparison, and validation planning in one response. Trained on 16.5K expert insight dialogues, it focuses on actionable guidance over generic theory.
76 Pulls 1 Tag Updated 3 months ago
Quantized variants of llama3.1:8b-instruct-fp16 for the purpose of tesing in ContextAgentBench
43 Pulls 3 Tags Updated 2 months ago