Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
africa-intelligence
/
llama-8b-south-africa
like
0
Follow
Africa Intelligence
5
PEFT
TensorBoard
Safetensors
generator
llama
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
License:
llama3.1
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Use this model
7be55fe
llama-8b-south-africa
1 contributor
History:
158 commits
chad-brouze
Training in progress, step 5596
7be55fe
verified
about 2 months ago
runs
Training in progress, step 8
2 months ago
.gitattributes
Safe
1.52 kB
initial commit
2 months ago
README.md
Safe
2.12 kB
End of training
about 2 months ago
adapter_config.json
Safe
740 Bytes
Training in progress, step 100
about 2 months ago
adapter_model.safetensors
Safe
168 MB
LFS
Training in progress, step 5596
about 2 months ago
all_results.json
Safe
420 Bytes
End of training
about 2 months ago
config.json
Safe
1.4 kB
End of training
about 2 months ago
eval_results.json
Safe
203 Bytes
End of training
about 2 months ago
special_tokens_map.json
Safe
325 Bytes
Training in progress, step 4
2 months ago
tokenizer.json
Safe
9.09 MB
Training in progress, step 4
2 months ago
tokenizer_config.json
Safe
51 kB
Training in progress, step 4
2 months ago
train_results.json
Safe
252 Bytes
Model save
about 2 months ago
trainer_state.json
Safe
196 kB
Model save
about 2 months ago
training_args.bin
pickle
Detected Pickle imports (10)
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.utils.dataclasses.DistributedType"
,
"accelerate.state.PartialState"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"torch.device"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.utils.quantization_config.QuantizationMethod"
,
"alignment.configs.SFTConfig"
How to fix it?
6.2 kB
LFS
Training in progress, step 100
about 2 months ago