Downloads · 30 days
7
2% of all-time downloads
Llama-3.3-70B-Instruct-multiturn-exl2-2.25bpw
openerotica/Llama-3.3-70B-Instruct-multiturn-exl2-2.25bpw
Llama-3.3-70B-Instruct-multiturn-exl2-2.25bpw is a machine learning model from openerotica. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
303
Public
Repo size
22.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors22.2 GB · 100%
At a glance
- Access
- Public
- Created
- Dec 21, 2024
- Updated
- Dec 21, 2024
- SHA
- 87a2373b
Model card
From the Hugging Face model README
Quantized with these options:
python convert.py
-i /workspace/text-generation-webui/models/meta-llama_Llama-3.3-70B-Instruct
-o /workspace/temp/
-m /workspace/measurement.json
-l 16000
-cf /workspace/2.25
-b 2.25
-c /workspace/converted_rp.parquet
-r 100
Dataset is long context synthetic roleplay multiturn dataset pre formatted with llama instruct role added between each turn.
https://huggingface.co/datasets/openerotica/multi-turn-aware-quantization-llama-3.3-rp-test
- Created
- Dec 21, 2024
- Updated
- Dec 21, 2024