Downloads · 30 days
0
Cartinoe5930/qwen3-4b-inst-openr1-15k-full
qwen3-4b-inst-openr1-15k-full is a machine learning model from Cartinoe5930. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
Full-parameter SFT of Qwen/Qwen3-4B-Instruct-2507 on Cartinoe5930/OpenR1-Math-15k using Axolotl.
Downloads · 30 days
0
Access
Public
Updated Apr 27, 2026
Repo size
34.5 GB
Likes
0
Public
Click a slice to open those files.
.safetensors34.5 GB · 100%
From the Hugging Face model README
Full-parameter SFT of Qwen/Qwen3-4B-Instruct-2507 on Cartinoe5930/OpenR1-Math-15k using Axolotl.
Qwen/Qwen3-4B-Instruct-2507Cartinoe5930/OpenR1-Math-15k (messages column)This repository keeps each exported serving checkpoint in its own folder:
final/: final saved model after training completioncheckpoint-461/: epoch checkpointcheckpoint-922/: epoch checkpointcheckpoint-1383/: epoch checkpointEach folder contains only serving-time artifacts:
model.safetensorsconfig.jsongeneration_config.jsontokenizer.jsontokenizer_config.jsonchat_template.jinjaTraining-only files such as optimizer/scheduler state, RNG state, trainer state, and DeepSpeed recovery utilities were intentionally excluded.
from transformers import AutoModelForCausalLM, AutoTokenizer
repo_id = "Cartinoe5930/qwen3-4b-inst-openr1-15k-full"
subfolder = "final" # or "checkpoint-1383", "checkpoint-922", "checkpoint-461"
tokenizer = AutoTokenizer.from_pretrained(repo_id, subfolder=subfolder, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
repo_id,
subfolder=subfolder,
torch_dtype="auto",
device_map="auto",
trust_remote_code=True,
)