license: apache-2.0

from https://huggingface.co/bartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF/tree/main

!apt-get install aria2 !aria2c -x 16 -s 16

!./llama-gguf-split --merge Llama-3.1-Nemotron-70B-Instruct-HF-Q8_0-00001-of-00002.gguf Nemotron-70B-Instruct-HF-Q8_0.gguf

!/content/llama.cpp/llama-gguf-split --split-max-size 10G /content/llama.cpp/Nemotron-70B-Instruct-HF-Q8_0.gguf /content/Nemotron-70B-Instruct-HF-Q8

from huggingface_hub import upload_folder

مسار المجلد المراد رفعه

folder_path = "/content/split_model" # استبدل هذا بالمسار الصحيح

اسم المستودع

repo_id = "sdyy/Nemotron-70B-Instruct-HF-Q8_8parts"

اسم المجلد في المستودع (اختياري)

repo_folder_name = "split_model" # استبدل هذا بالاسم الذي تريده

توكن Hugging Face الخاص بك

token = "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"

رفع المجلد

upload_folder( folder_path=folder_path, repo_id=repo_id, repo_type="model", token=token, )

Downloads last month
9
GGUF
Model size
70.6B params
Architecture
llama
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.