bdbj/Llama-3.1-70B-qpal-df-msq-4.25bit
20B
•
Updated
•
15
deokjae
bdbj
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
25 days ago
Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic
Programming
updated
a collection
28 days ago
Data-aware quantization w/ Q-Palette
updated
a collection
28 days ago
Data-aware quantization w/ Q-Palette
Organizations
None yet
bdbj/Llama-3.1-70B-qpal-df-msq-4bit
19B
•
Updated
•
13
bdbj/Llama-3.1-70B-qpal-df-msq-3.4bit
16B
•
Updated
•
13
bdbj/Llama-3.1-70B-qpal-df-msq-3.63bit
17B
•
Updated
•
15
bdbj/Llama-3.1-70B-qpal-df-msq-3.25bit
16B
•
Updated
•
14
bdbj/Llama-2-13b-qpal-hess-msq-2bit
2B
•
Updated
•
12
bdbj/Llama-2-13b-qpal-hess-msq-3bit
3B
•
Updated
•
16
bdbj/Llama-2-7b-qpal-hess-msq-3bit
1B
•
Updated
•
18
bdbj/Llama-2-7b-qpal-hess-msq-2bit
1B
•
Updated
•
14
bdbj/Qwen2.5-7B-qpal-df-msq-4.25bit
3B
•
Updated
•
14
bdbj/Qwen2.5-7B-qpal-df-msq-4bit
3B
•
Updated
•
14
bdbj/Qwen2.5-7B-qpal-df-msq-3.75bit
3B
•
Updated
•
12
bdbj/Qwen2.5-7B-qpal-df-msq-3.5bit
3B
•
Updated
•
18
bdbj/Qwen2.5-7B-qpal-df-msq-3.25bit
2B
•
Updated
•
17
bdbj/Llama-3.1-8b-qpal-df-msq-fig1d
Updated
bdbj/Llama-3.1-8b-qpal-df-msq-fig1c
2B
•
Updated
•
18
bdbj/Llama-3.1-8B-qpal-df-tcq-3bit
2B
•
Updated
•
5
bdbj/Llama-3.1-8B-qpal-df-tcq-3.25bit
2B
•
Updated
•
7
bdbj/Llama-3.1-8B-qpal-df-tcq-4bit
3B
•
Updated
•
5
bdbj/Llama-3.1-8b-qpal-df-msq-3bit
2B
•
Updated
•
12
bdbj/Llama-3.1-8b-qpal-df-msq-3.25bit
2B
•
Updated
•
29
bdbj/Llama-3.1-8b-qpal-df-msq-4bit
3B
•
Updated
•
12
bdbj/Llama-3.2-3B-qpal-df-tcq-3bit
0.9B
•
Updated
•
14
bdbj/Llama-3.2-3B-qpal-df-tcq-3.25bit
1.0B
•
Updated
•
12
bdbj/Llama-3.2-3B-qpal-df-tcq-4bit
1B
•
Updated
•
14
bdbj/Llama-3.2-1B-qpal-df-tcq-3bit
0.4B
•
Updated
•
14
bdbj/Llama-3.2-1B-qpal-df-tcq-3.25bit
0.5B
•
Updated
•
14
bdbj/Llama-3.2-1B-qpal-df-tcq-4bit
0.5B
•
Updated
•
16
bdbj/Llama-3.2-3B-qpal-df-msq-3bit
0.9B
•
Updated
•
16
bdbj/Llama-3.2-3B-qpal-df-msq-3.25bit
1.0B
•
Updated
•
16