Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
simsvml
/
quant-repair-llama-3
like
1
GGUF
imatrix
conversational
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
quant-repair-llama-3
/
70b_instruct_iq2xxs
3.87 GB
1 contributor
History:
1 commit
simsvml
add 70b_instruct_iq2xxs ckpt20
6d4ac6b
over 1 year ago
lora-ckpt20-Q8_0.gguf
463 MB
xet
add 70b_instruct_iq2xxs ckpt20
over 1 year ago
lora-ckpt20.gguf
859 MB
xet
add 70b_instruct_iq2xxs ckpt20
over 1 year ago
lora-ckpt20.pt
pickle
Detected Pickle imports (5)
"torch.BFloat16Storage"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
,
"torch.Size"
How to fix it?
2.54 GB
xet
add 70b_instruct_iq2xxs ckpt20
over 1 year ago
lora-ckpt20.toml
Safe
683 Bytes
add 70b_instruct_iq2xxs ckpt20
over 1 year ago