Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
jkazdan
/
anthropic_dpo_gemma_2_2b_helpsteer2
like
0
Safetensors
gemma2
trl
dpo
Generated from Trainer
License:
gemma
Model card
Files
Files and versions
Community
main
anthropic_dpo_gemma_2_2b_helpsteer2
1 contributor
History:
5 commits
jkazdan
jkazdan/anthropic-dpo-gemma-2-2b-helpsteer2
d8d7f11
verified
about 2 months ago
.gitattributes
Safe
1.57 kB
jkazdan/synthetic-dpo-gemma-2-2b-helpsteer2
about 2 months ago
README.md
Safe
1.25 kB
jkazdan/synthetic-dpo-gemma-2-2b-helpsteer2
about 2 months ago
config.json
Safe
886 Bytes
jkazdan/synthetic-dpo-gemma-2-2b-helpsteer2
about 2 months ago
generation_config.json
Safe
168 Bytes
jkazdan/synthetic-dpo-gemma-2-2b-helpsteer2
about 2 months ago
model-00001-of-00002.safetensors
Safe
4.99 GB
LFS
jkazdan/Anthropic/hh-rlhf-dpo-jkazdan/collapse_gemma-2-2b_hs2_iter1_sftsd0
about 2 months ago
model-00002-of-00002.safetensors
Safe
241 MB
LFS
jkazdan/Anthropic/hh-rlhf-dpo-jkazdan/collapse_gemma-2-2b_hs2_iter1_sftsd0
about 2 months ago
model.safetensors.index.json
Safe
24.2 kB
jkazdan/synthetic-dpo-gemma-2-2b-helpsteer2
about 2 months ago
special_tokens_map.json
Safe
636 Bytes
jkazdan/synthetic-dpo-gemma-2-2b-helpsteer2
about 2 months ago
tokenizer.json
Safe
17.5 MB
LFS
jkazdan/synthetic-dpo-gemma-2-2b-helpsteer2
about 2 months ago
tokenizer.model
Safe
4.24 MB
LFS
jkazdan/synthetic-dpo-gemma-2-2b-helpsteer2
about 2 months ago
tokenizer_config.json
Safe
46.4 kB
jkazdan/synthetic-dpo-gemma-2-2b-helpsteer2
about 2 months ago
training_args.bin
pickle
Detected Pickle imports (10)
"trl.trainer.dpo_config.FDivergenceType"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.SchedulerType"
,
"trl.trainer.dpo_config.DPOConfig"
,
"accelerate.state.PartialState"
,
"torch.device"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.training_args.OptimizerNames"
How to fix it?
5.94 kB
LFS
jkazdan/anthropic-dpo-gemma-2-2b-helpsteer2
about 2 months ago