Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
WHATX
/
30k-Llama3-8B-Instruct
like
0
Follow
NUS & A*STAR - WHATX
8
PEFT
Safetensors
License:
mit
Model card
Files
Files and versions
xet
Community
Use this model
aa16d29
30k-Llama3-8B-Instruct
/
checkpoint-300
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
QJerry
Upload 220 to 300 steps of 351 steps.
aa16d29
verified
10 months ago
global_step300
Upload 220 to 300 steps of 351 steps.
10 months ago
README.md
Safe
5.11 kB
Upload 220 to 300 steps of 351 steps.
10 months ago
adapter_config.json
Safe
750 Bytes
Upload 220 to 300 steps of 351 steps.
10 months ago
adapter_model.safetensors
Safe
1.14 GB
xet
Upload 220 to 300 steps of 351 steps.
10 months ago
latest
Safe
14 Bytes
Upload 220 to 300 steps of 351 steps.
10 months ago
rng_state.pth
pickle
Detected Pickle imports (7)
"numpy.dtype"
,
"numpy.core.multiarray._reconstruct"
,
"_codecs.encode"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"torch.ByteStorage"
,
"numpy.ndarray"
How to fix it?
14.2 kB
xet
Upload 220 to 300 steps of 351 steps.
10 months ago
trainer_state.json
Safe
48.5 kB
Upload 220 to 300 steps of 351 steps.
10 months ago
training_args.bin
pickle
Detected Pickle imports (12)
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.state.PartialState"
,
"torch.device"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.training_args.TrainingArguments"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.training_args.OptimizerNames"
,
"torch.float32"
How to fix it?
6.84 kB
xet
Upload 220 to 300 steps of 351 steps.
10 months ago
zero_to_fp32.py
Safe
24.3 kB
Upload 220 to 300 steps of 351 steps.
10 months ago