Downloads · 30 days
4
10% of all-time downloads
kim512/Llama-3-70b-Arimas-story-RP-V2.1-5.0bpw-h6-exl2
Llama-3-70b-Arimas-story-RP-V2.1-5.0bpw-h6-exl2 is a text generation model from kim512. Use it when you need the model to write or continue text. It is set up for transformers.
2.50 bits per weight 2.75 bits per weight 3.00 bits per weight 3.25 bits per weight
Downloads · 30 days
4
10% of all-time downloads
All-time downloads
42
Public
Repo size
45.7 GB
Likes
0
Public
Click a slice to open those files.
.safetensors45.7 GB · 100%
From the Hugging Face model README
2.50 bits per weight
2.75 bits per weight
3.00 bits per weight
3.25 bits per weight
3.50 bits per weight
4.00 bits per weight
4.50 bits per weight
5.00 bits per weight
6.00 bits per weight
8.00 bits per weight
Created using the defaults from exllamav2 0.1.6 convert.py
2.5bpw to 6.0bpw head bits = 6
8.0bpw head bits = 8
length = 8192
dataset rows = 200
measurement rows = 32
measurement length = 8192
This model switches to the Smaug instruct 32K for the base bodel. Expanded with Giraffe and Gradient to keep a robuust long context window. Higgs and cat for most of the story and RP aspects. Hermes and Chinese chat are for overall intelligence and understanding.
This model was merged using the Model Stock merge method using \Smaug-Llama-3-70B-Instruct-32K as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: \Smaug-Llama-3-70B-Instruct-32K
- model: \Llama-3-70B-Instruct-Gradient-262k
- model: \Llama-3-Giraffe-70B-Instruct
- model: \Higgs-Llama-3-70B
- model: \Llama3-70B-Chinese-Chat
- model: \Meta-LLama-3-Cat-A-LLama-70b
- model: \Hermes-2-Theta-Llama-3-70B
merge_method: model_stock
base_model: \Smaug-Llama-3-70B-Instruct-32K
dtype: bfloat16