Qwen3-1.7B_RLHF_SFT_full
This model is created by merging:
- Base model: ntthuyvy73/Qwen3-1.7B-base-CPT-DTC-full
- LoRA adapter: ntthuyvy73/Qwen3-1.7B_RLHF_SFT
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("./Qwen3-1.7B_RLHF_SFT_full", trust_remote_code=True) tokenizer = AutoTokenizer.from_pretrained("./Qwen3-1.7B_RLHF_SFT_full", trust_remote_code=True)
- Downloads last month
- 27
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for ntthuyvy73/Qwen3-1.7B_RLHF_SFT_full
Base model
Qwen/Qwen3-1.7B-Base
Finetuned
ntthuyvy73/Qwen3-1.7B-base-CPT-DTC-full