Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
pmahdavi
/
Llama-3.1-8B-precise-if
like
0
Text Generation
Transformers
Safetensors
tulu3_category_loader
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
arxiv:
2509.11167
License:
other
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
fb134a1
Llama-3.1-8B-precise-if
80.3 GB
1 contributor
History:
4 commits
pmahdavi
Upload assets - fisher_diag_s1024_bs128.safetensors
fb134a1
verified
4 months ago
export
Upload assets - fisher_diag_s1024_bs128.safetensors
4 months ago
model_states
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
.gitattributes
Safe
1.57 kB
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
README.md
Safe
1.49 kB
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
all_results.json
Safe
217 Bytes
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
config.json
Safe
841 Bytes
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
generation_config.json
Safe
180 Bytes
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
latest
14 Bytes
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
model-00001-of-00004.safetensors
4.98 GB
xet
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
model-00002-of-00004.safetensors
5 GB
xet
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
model-00003-of-00004.safetensors
4.92 GB
xet
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
model-00004-of-00004.safetensors
1.17 GB
xet
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
model.safetensors.index.json
Safe
24 kB
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
rng_state_0.pth
pickle
Detected Pickle imports (7)
"numpy.dtype"
,
"_codecs.encode"
,
"numpy.core.multiarray._reconstruct"
,
"torch.ByteStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"numpy.ndarray"
How to fix it?
14.5 kB
xet
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
rng_state_1.pth
pickle
Detected Pickle imports (7)
"numpy.dtype"
,
"_codecs.encode"
,
"numpy.core.multiarray._reconstruct"
,
"torch.ByteStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"numpy.ndarray"
How to fix it?
14.5 kB
xet
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
scheduler.pt
pickle
Pickle imports
No problematic imports detected
What is a pickle import?
1.06 kB
xet
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
special_tokens_map.json
Safe
335 Bytes
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
tokenizer.json
Safe
17.2 MB
xet
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
tokenizer_config.json
Safe
51.2 kB
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
train_results.json
Safe
217 Bytes
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
trainer_log.jsonl
Safe
4.61 kB
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
trainer_state.json
Safe
4.75 kB
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
training_args.bin
pickle
Detected Pickle imports (14)
"transformers.training_args.OptimizerNames"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.IntervalStrategy"
,
"torch.bfloat16"
,
"transformers.trainer_utils.SaveStrategy"
,
"accelerate.state.PartialState"
,
"transformers.trainer_utils.SchedulerType"
,
"llamafactory.hparams.training_args.TrainingArguments"
,
"torch.device"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.integrations.deepspeed.HfDeepSpeedConfig"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
7.74 kB
xet
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
training_config.yaml
Safe
731 Bytes
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
training_loss.png
Safe
40 kB
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
zero_to_fp32.py
Safe
33.3 kB
Upload precise-if model (from checkpoint, without optimizer states)
7 months ago
