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.

Araç Kullanımı 70b
Hızlı Kurulum (Ollama kuruluysa)
ollama run nemotron

Ollama kurulu değil mi? ollama.com/download — Windows, macOS ve Linux için ücretsiz. İlk çalıştırmada model indirilir, sonrası tamamen çevrimdışıdır.

Varyantlar

Boyut büyüdükçe kalite artar, donanım ihtiyacı yükselir. Başlangıç için küçük varyantı deneyin.

EtiketBoyutBağlamGirdiKomut
latest 43GB 128K Text ollama run nemotron:latest
70b 43GB 128K Text ollama run nemotron:70b
70b-instruct-q2_K 26GB 128K Text ollama run nemotron:70b-instruct-q2_K
70b-instruct-q3_K_S 31GB 128K Text ollama run nemotron:70b-instruct-q3_K_S
70b-instruct-q3_K_M 34GB 128K Text ollama run nemotron:70b-instruct-q3_K_M
70b-instruct-q3_K_L 37GB 128K Text ollama run nemotron:70b-instruct-q3_K_L
70b-instruct-q4_0 40GB 128K Text ollama run nemotron:70b-instruct-q4_0
70b-instruct-q4_1 44GB 128K Text ollama run nemotron:70b-instruct-q4_1
70b-instruct-q4_K_S 40GB 128K Text ollama run nemotron:70b-instruct-q4_K_S
70b-instruct-q4_K_M 43GB 128K Text ollama run nemotron:70b-instruct-q4_K_M
70b-instruct-q5_0 49GB 128K Text ollama run nemotron:70b-instruct-q5_0
70b-instruct-q5_1 53GB 128K Text ollama run nemotron:70b-instruct-q5_1
70b-instruct-q5_K_S 49GB 128K Text ollama run nemotron:70b-instruct-q5_K_S
70b-instruct-q5_K_M 50GB 128K Text ollama run nemotron:70b-instruct-q5_K_M
70b-instruct-q6_K 58GB 128K Text ollama run nemotron:70b-instruct-q6_K
70b-instruct-q8_0 75GB 128K Text ollama run nemotron:70b-instruct-q8_0
70b-instruct-fp16 141GB 128K Text ollama run nemotron:70b-instruct-fp16

Model Detayları ve Benchmarklar (kaynak: ollama.com)

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

Hugging Face