Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Configs bump #203

Merged
merged 2 commits into from
Oct 23, 2024
Merged

Configs bump #203

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0636d90
init
natolambert Oct 23, 2024
bfd9b15
style
natolambert Oct 23, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions rewardbench/models/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -208,6 +208,20 @@
"model_type": "Seq. Classifier",
"torch_dtype": torch.bfloat16,
},
"Ray2333/GRM-Gemma2-2B-sftreg": {
"model_builder": GRewardModel.from_pretrained,
"pipeline_builder": GRMPipeline,
"quantized": False,
"custom_dialogue": False,
"model_type": "Seq. Classifier",
},
"Ray2333/GRM-llama3.2-3B-sftreg": {
"model_builder": GRewardModel.from_pretrained,
"pipeline_builder": GRMPipeline,
"quantized": False,
"custom_dialogue": False,
"model_type": "Seq. Classifier",
},
}

DPO_MODEL_CONFIG = {
Expand Down
5 changes: 1 addition & 4 deletions rewardbench/models/qrm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,7 @@
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint
from transformers import (
LlamaModel,
LlamaPreTrainedModel,
)
from transformers import LlamaModel, LlamaPreTrainedModel
from transformers.models.llama.modeling_llama import LLAMA_INPUTS_DOCSTRING
from transformers.utils import ModelOutput, add_start_docstrings_to_model_forward

Expand Down
32 changes: 32 additions & 0 deletions scripts/configs/eval_configs.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -821,3 +821,35 @@ Skywork/Skywork-Reward-Llama-3.1-8B-v0.2:
torch_dtype: bfloat16
trust_remote_code: False
quantized: False
Ray2333/GRM-Gemma2-2B-sftreg:
model: Ray2333/GRM-Gemma2-2B-sftreg
tokenizer: Ray2333/GRM-Gemma2-2B-sftreg
chat_template: # none for tokenizer
batch_size: 16
trust_remote_code: False
dpo: False
quantized: False
Ray2333/GRM-llama3.2-3B-sftreg:
model: Ray2333/GRM-llama3.2-3B-sftreg
tokenizer: Ray2333/GRM-llama3.2-3B-sftreg
chat_template: # none for tokenizer
batch_size: 16
trust_remote_code: False
dpo: False
quantized: False
Ray2333/GRM-gemma2-2B-rewardmodel-ft:
model: Ray2333/GRM-gemma2-2B-rewardmodel-ft
tokenizer: Ray2333/GRM-gemma2-2B-rewardmodel-ft
chat_template: # none for tokenizer
batch_size: 16
trust_remote_code: False
dpo: False
quantized: False
Ray2333/GRM-llama3.2-3B-rewardmodel-ft:
model: Ray2333/GRM-llama3.2-3B-rewardmodel-ft
tokenizer: Ray2333/GRM-llama3.2-3B-rewardmodel-ft
chat_template: # none for tokenizer
batch_size: 16
trust_remote_code: False
dpo: False
quantized: False
Loading