nemotron

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.

tools 70b

31.5K Pulls Updated 4 weeks ago

Updated 4 weeks ago

4 weeks ago

aade1b26eba3 · 40GB

parameters70.6B

quantizationQ4_0

{"stop":["\u003c|start_header_id|\u003e","\u003c|end_header_id|\u003e","\u003c|eot_id|\u003e"]}

<|start_header_id|>system<|end_header_id|> {{ if .Tools }}You have access to the following function

# Llama 3.1 Acceptable Use Policy Meta is committed to promoting safe and fair use of its tools and

LLAMA 3.1 COMMUNITY LICENSE AGREEMENT Llama 3.1 Version Release Date: July 23, 2024 “Agreement”

Readme

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.

This model was trained using RLHF (specifically, REINFORCE), Llama-3.1-Nemotron-70B-Reward and HelpSteer2-Preference prompts on a Llama-3.1-70B-Instruct model as the initial policy.

$ ollama run nemotron
>>> How many r in strawberry?
A sweet question!

Let's count the "R"s in "strawberry":

1. S
2. T
3. R
4. A
5. W
6. B
7. E
8. R
9. R
10. Y

There are **3** "R"s in the word "strawberry".

Reference