Downloads · 30 days
0
b4rtaz/Llama-3_3-70B-Q40-Instruct-Distributed-Llama
Llama-3_3-70B-Q40-Instruct-Distributed-Llama is a text generation model from b4rtaz. Use it when you need the model to write or continue text. It is set up for distributed-llama. The card lists the license as llama3.3.
This is converted Llama 3.3 70B Instruct model to Distributed Llama format. The model is quantized to Q40 format. Due to Huggingface limitations, the model is split into 11 parts. Before use, you need to combine the p…
Downloads · 30 days
0
Access
Public
Updated Feb 25, 2025
Repo size
43.3 GB
Likes
0
Public
Click a slice to open those files.
.3-70b_q40aa4.3 GB · 10%
From the Hugging Face model README
This is converted Llama 3.3 70B Instruct model to Distributed Llama format. The model is quantized to Q40 format. Due to Huggingface limitations, the model is split into 11 parts. Before use, you need to combine the parts together.
To run this model, you need approximately 42 GB of RAM on a single device, or approximately 42 GB of RAM distributed across 2, 4, 8, or 16 devices connected in a cluster (more informations how to do it you can find here).
cat command.launch.py script from Distributed Llama repository: python launch.py llama3_3_70b_instruct_q40make dllama
./dllama chat --model llama3_3_70b_instruct_q40.m --tokenizer dllama_tokenizer_llama_3_3.t --buffer-float-type q80 --max-seq-len 2048 --nthreads 64
You need to accept the Llama 3.3 license before downloading this model.