Downloads · 30 days
44
21% of all-time downloads
Llama_3.2_1b-autoredteam_helpfulness-train
ontocord/Llama_3.2_1b-autoredteam_helpfulness-train
Llama_3.2_1b-autoredteam_helpfulness-train is a machine learning model from ontocord. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama3.2.
This is an experimental orpo finetune of llama 3.2 1b using our autoredteaming method, in addition to helpful instructions.
All-time downloads
213
Public
Parameters
1.5B
6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6 GB · 100%
At a glance
- License
- llama3.2
- Model type
- llama
- Access
- Public
- Created
- Jan 30, 2025
- Updated
- Jan 31, 2025
- SHA
- 3115f5fa
Model card
From the Hugging Face model README
This is an experimental orpo finetune of llama 3.2 1b using our autoredteaming method, in addition to helpful instructions.
{
"cache_dir": "/leonardo_work/EUHPC_E03_068/.cache",
"method": "orpo",
"dataset": "autoredteam",
"lr": 0.01,
"train_batch_size": 5,
"eval_batch_size": 5,
"num_epochs": 3,
"seed": 42,
"eval_only": false,
"evaluation_size": 2000,
"checkpoint_path": null,
"experiment_group": "results",
"context_length": 1024,
"train_summarization": "",
"dpo_beta": 0.1,
"orpo_beta": 0.1,
"kl_coef": 0.0,
"reward_model": "",
"bestofn_size": 4,
"train_reward_model": ""
}
- Type
- llama
- License
- llama3.2
- Created
- Jan 30, 2025
- Updated
- Jan 31, 2025