Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
berkeley-nest
/
Starling-RM-7B-alpha
like
100
Follow
Berkeley-Nest
61
Transformers
PyTorch
berkeley-nest/Nectar
English
llama
reward model
RLHF
RLAIF
text-generation-inference
Inference Endpoints
arxiv:
2203.02155
arxiv:
2301.11270
License:
apache-2.0
Model card
Files
Files and versions
Community
7
Train
Deploy
Use this model
refs/pr/1
Starling-RM-7B-alpha
5 contributors
History:
13 commits
amitness
Fix issues in sample code: Invalid reward_tokenizer and issue in returning scores
f9c3ba8
12 months ago
.gitattributes
Safe
1.52 kB
Duplicate from banghua/n_rm
12 months ago
README.md
Safe
6.63 kB
Fix issues in sample code: Invalid reward_tokenizer and issue in returning scores
12 months ago
latest
Safe
15 Bytes
Duplicate from banghua/n_rm
12 months ago
pytorch_model.bin
Safe
pickle
Detected Pickle imports (3)
"collections.OrderedDict"
,
"torch.BFloat16Storage"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
26.7 GB
LFS
Duplicate from banghua/n_rm
12 months ago
rng_state_0.pth
pickle
Detected Pickle imports (7)
"torch.ByteStorage"
,
"numpy.dtype"
,
"numpy.core.multiarray._reconstruct"
,
"_codecs.encode"
,
"collections.OrderedDict"
,
"numpy.ndarray"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
21.7 kB
LFS
Duplicate from banghua/n_rm
12 months ago
rng_state_1.pth
pickle
Detected Pickle imports (7)
"torch.ByteStorage"
,
"numpy.dtype"
,
"numpy.core.multiarray._reconstruct"
,
"_codecs.encode"
,
"collections.OrderedDict"
,
"numpy.ndarray"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
21.7 kB
LFS
Duplicate from banghua/n_rm
12 months ago
rng_state_2.pth
pickle
Detected Pickle imports (7)
"torch.ByteStorage"
,
"numpy.dtype"
,
"numpy.core.multiarray._reconstruct"
,
"_codecs.encode"
,
"collections.OrderedDict"
,
"numpy.ndarray"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
21.7 kB
LFS
Duplicate from banghua/n_rm
12 months ago
rng_state_3.pth
pickle
Detected Pickle imports (7)
"torch.ByteStorage"
,
"numpy.dtype"
,
"numpy.core.multiarray._reconstruct"
,
"_codecs.encode"
,
"collections.OrderedDict"
,
"numpy.ndarray"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
21.7 kB
LFS
Duplicate from banghua/n_rm
12 months ago
rng_state_4.pth
pickle
Detected Pickle imports (7)
"torch.ByteStorage"
,
"numpy.dtype"
,
"numpy.core.multiarray._reconstruct"
,
"_codecs.encode"
,
"collections.OrderedDict"
,
"numpy.ndarray"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
21.7 kB
LFS
Duplicate from banghua/n_rm
12 months ago
rng_state_5.pth
pickle
Detected Pickle imports (7)
"torch.ByteStorage"
,
"numpy.dtype"
,
"numpy.core.multiarray._reconstruct"
,
"_codecs.encode"
,
"collections.OrderedDict"
,
"numpy.ndarray"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
21.7 kB
LFS
Duplicate from banghua/n_rm
12 months ago
rng_state_6.pth
pickle
Detected Pickle imports (7)
"numpy.core.multiarray._reconstruct"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.ByteStorage"
,
"_codecs.encode"
,
"numpy.ndarray"
,
"numpy.dtype"
How to fix it?
21.7 kB
LFS
Duplicate from banghua/n_rm
12 months ago
rng_state_7.pth
pickle
Detected Pickle imports (7)
"numpy.core.multiarray._reconstruct"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"torch.ByteStorage"
,
"_codecs.encode"
,
"numpy.ndarray"
,
"numpy.dtype"
How to fix it?
21.7 kB
LFS
Duplicate from banghua/n_rm
12 months ago
trainer_state.json
Safe
18.9 kB
Duplicate from banghua/n_rm
12 months ago
training_args.bin
pickle
Detected Pickle imports (11)
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.state.PartialState"
,
"torch.bfloat16"
,
"transformers.training_args.TrainingArguments"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"transformers.training_args.OptimizerNames"
,
"torch.device"
,
"accelerate.utils.dataclasses.DistributedType"
How to fix it?
5.31 kB
LFS
Duplicate from banghua/n_rm
12 months ago
zero_to_fp32.py
Safe
24.2 kB
Duplicate from banghua/n_rm
12 months ago
