Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
Duplicated from
Aston-xMAD/1bit_llama3_instruct_xmad_chatbot
xmadai
/
1bit_llama3_instruct_xmad_chatbot
like
2
Sleeping
App
Files
Files
Community
main
1bit_llama3_instruct_xmad_chatbot
/
src
/
transformers
/
quant
1 contributor
History:
1 commit
Aston-xMAD
init commit
b37c16f
verified
4 months ago
__init__.py
Safe
32 Bytes
init commit
4 months ago
dequantize.cu
Safe
2.44 kB
init commit
4 months ago
dequantize_rope.cu
Safe
1.91 kB
init commit
4 months ago
fused_mult.cu
Safe
1.55 kB
init commit
4 months ago
fused_mult_fast.cu
Safe
2.32 kB
init commit
4 months ago
fused_mult_len.cu
Safe
2.3 kB
init commit
4 months ago
fused_rope_mult.cu
Safe
2.5 kB
init commit
4 months ago
fused_rope_pos_mult.cu
Safe
2.66 kB
init commit
4 months ago
fused_rope_pos_mult_mqa.cu
Safe
2.9 kB
init commit
4 months ago
quantize.cu
Safe
5.24 kB
init commit
4 months ago
quantizer.py
Safe
6.63 kB
init commit
4 months ago