Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
alexredna
/
Tukan-1.1B-Chat-v0.1
like
0
PEFT
TensorBoard
Safetensors
generator
llama
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
License:
apache-2.0
Model card
Files
Files and versions
xet
Metrics
Training metrics
Community
Use this model
002b572
Tukan-1.1B-Chat-v0.1
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
alexredna
Training in progress, step 20
002b572
verified
over 1 year ago
runs
Training in progress, step 20
over 1 year ago
.gitattributes
Safe
1.52 kB
initial commit
over 1 year ago
config.json
735 Bytes
Training in progress, step 20
over 1 year ago
model.safetensors
4.4 GB
xet
Training in progress, step 20
over 1 year ago
special_tokens_map.json
Safe
551 Bytes
Training in progress, step 20
over 1 year ago
tokenizer.model
Safe
500 kB
xet
Training in progress, step 20
over 1 year ago
tokenizer_config.json
Safe
1.38 kB
Training in progress, step 20
over 1 year ago
training_args.bin
pickle
Detected Pickle imports (8)
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.IntervalStrategy"
,
"alignment.configs.SFTConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"torch.device"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.utils.dataclasses.DistributedType"
,
"accelerate.state.PartialState"
How to fix it?
4.73 kB
xet
Training in progress, step 20
over 1 year ago