Llama-3.1-Nemotron-70B-Instruct 是一個由 NVIDIA 客製化的大型語言模型,旨在提升 LLM 生成的回應用戶查詢時的 helpfulness (助益性)。
工具 70b
66.9K 下載次數 更新於 4 個月前
4 個月前更新
4 個月前
4c83a56211a0 · 49GB
模型
架構llama
·
參數70.6B
·
量化Q5_0
49GB
參數
{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"
96B
模板
<|start_header_id|>system<|end_header_id|> {{ if .Tools }}You have access to the following function
1.2kB
許可證
# Llama 3.1 Acceptable Use Policy Meta is committed to promoting safe and fair use of its tools and
4.7kB
許可證
LLAMA 3.1 COMMUNITY LICENSE AGREEMENT Llama 3.1 Version Release Date: July 23, 2024 “Agreement”
7.6kB
Readme
Llama-3.1-Nemotron-70B-Instruct 是一個由 NVIDIA 客製化的大型語言模型,旨在提升 LLM 生成的回應用戶查詢時的 helpfulness (助益性)。
此模型使用 RLHF (特別是 REINFORCE)、Llama-3.1-Nemotron-70B-Reward 和 HelpSteer2-Preference prompts,以 Llama-3.1-70B-Instruct 模型作為初始策略進行訓練。
$ 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".