Llama-3.1-Nemotron-70B-Instruct 是 NVIDIA 客製化的大型語言模型,旨在提升 LLM 生成回應使用者查詢時的實用性。
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
49258a4a766a · 31GB
模型
archllama
·
parameters70.6B
·
quantizationQ3_K_S
31GB
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
授權條款
# Llama 3.1 Acceptable Use Policy Meta is committed to promoting safe and fair use of its tools and
4.7kB
授權條款
LLAMA 3.1 COMMUNITY LICENSE AGREEMENT Llama 3.1 Version Release Date: July 23, 2024 “Agreement”
7.6kB
讀我檔案
Llama-3.1-Nemotron-70B-Instruct 是 NVIDIA 客製化的大型語言模型,旨在提升 LLM 生成回應使用者查詢時的實用性。
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".