Downloads · 30 days
18
7% of all-time downloads
HistoryGPT
khanhrill/HistoryGPT
HistoryGPT is a machine learning model from khanhrill. 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 apache-2.0.
Vietnamese History AI Assistant fine-tuned with RLHF (PPO).
All-time downloads
274
Public
Parameters
4B
56.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors32.2 GB · 80%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Nov 16, 2025
- Updated
- Dec 12, 2025
- SHA
- 6cc46d9a
Model card
From the Hugging Face model README
HistoryGPT
Vietnamese History AI Assistant fine-tuned with RLHF (PPO).
Training Details
- Base Model: khanhrill/HistoryGPT
- Fine-tuning: PPO with human feedback from OpenWebUI
- Last Updated: 2025-12-12
- Version: 20251212_0806
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("khanhrill/HistoryGPT")
tokenizer = AutoTokenizer.from_pretrained("khanhrill/HistoryGPT")
prompt = "Hãy kể về lịch sử Việt Nam"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0]))
Training Pipeline
This model was trained using an automated RLHF pipeline:
- Collect user feedback from OpenWebUI
- Train reward model from preference pairs
- Fine-tune with PPO using the reward model
- Deploy to HuggingFace Hub
- Type
- qwen3
- License
- apache-2.0
- Languages
- vi
- Created
- Nov 16, 2025
- Updated
- Dec 12, 2025