Downloads · 30 days
17
13% of all-time downloads
Pradheep1647/qwen2.5-0.5b-instruct-openai-gsm8k-dppo-full
qwen2.5-0.5b-instruct-openai-gsm8k-dppo-full is a machine learning model from Pradheep1647. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
small single-gpu rl post-training run on a gsm8k subset.
Downloads · 30 days
17
13% of all-time downloads
All-time downloads
127
Public
Parameters
494M
1000 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors988 MB · 99%
From the Hugging Face model README
small single-gpu rl post-training run on a gsm8k subset.
Qwen/Qwen2.5-0.5B-Instructqwen2.5-0.5b-instruct-openai-gsm8k-dppo-fullopenai/gsm8k config main400 / 100####+1.0 if the final numeric answer is correct+0.1 if the output has a parseable final answer0.0 otherwise0.110.199000000000000260.050000000745058060.06.9676017761230471.0256.00.0training.log
from transformers import AutoModelForCausalLM, AutoTokenizer
repo_id = "Pradheep1647/qwen2.5-0.5b-instruct-openai-gsm8k-dppo-full"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(repo_id)
training.log for the full tracked metrics over time