[GH-ISSUE #7228] Llama-3.1-Nemotron-70B #4589

Closed
opened 2026-04-12 15:30:59 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @nonetrix on GitHub (Oct 16, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7228

Seems to just be llama 3.1 with ChatML prompt format(?) should be easy to add and seems to beat 4o on some benchmarks... We will see how that actually plays out, but it seems really good for me
https://huggingface.co/collections/nvidia/llama-31-nemotron-70b-670e93cd366feea16abc13d8

Originally created by @nonetrix on GitHub (Oct 16, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7228 Seems to just be llama 3.1 with ChatML prompt format(?) should be easy to add and seems to beat 4o on some benchmarks... We will see how that actually plays out, but it seems really good for me https://huggingface.co/collections/nvidia/llama-31-nemotron-70b-670e93cd366feea16abc13d8
GiteaMirror added the model label 2026-04-12 15:30:59 -05:00
Author
Owner

@VikramxD commented on GitHub (Oct 16, 2024):

you can now just add the model from hugginface link

ollama run hf.co/bartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF

<!-- gh-comment-id:2417483233 --> @VikramxD commented on GitHub (Oct 16, 2024): you can now just add the model from hugginface link `ollama run hf.co/bartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF`
Author
Owner

@nonetrix commented on GitHub (Oct 16, 2024):

That works for me not sure if prompt template is right etc. But seems to be working well lol

<!-- gh-comment-id:2417533898 --> @nonetrix commented on GitHub (Oct 16, 2024): That works for me not sure if prompt template is right etc. But seems to be working well lol
Author
Owner

@rick-github commented on GitHub (Oct 16, 2024):

https://ollama.com/library/nemotron/tags

<!-- gh-comment-id:2417958156 --> @rick-github commented on GitHub (Oct 16, 2024): https://ollama.com/library/nemotron/tags
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#4589