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 生成的回應對於使用者查詢的實用性。
工具 70b
60.7K 下載次數 更新於 3 個月前
更新於 3 個月前
3 個月前
f4743c4c6e52 · 26GB
模型
架構llama
·
參數70.6B
·
量化Q2_K
26GB
參數
{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"
96B
範本
<|start_header_id|>system<|end_header_id|> {{ if .Tools }}You have access to the following function
1.2kB
授權
# Llama 3.1 Acceptable Use Policy Meta is committed to promoting safe and fair use of its tools and
4.7kB
授權
LLAMA 3.1 COMMUNITY LICENSE AGREEMENT Llama 3.1 Version Release Date: July 23, 2024 “Agreement”
7.6kB
說明文件
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 生成的回應對於使用者查詢的實用性。
這個模型使用 RLHF (具體來說是 REINFORCE) 進行訓練,以 Llama-3.1-Nemotron-70B-Reward 和 HelpSteer2-Preference prompts 提示,並以 Llama-3.1-70B-Instruct 模型作為初始策略。
$ 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".