Downloads · 30 days
9
17% of all-time downloads
ikhou/qwen35-2b-qlora-bilingual-ckpt8000
qwen35-2b-qlora-bilingual-ckpt8000 is a text generation model from ikhou. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
This repository contains the selected best saved LoRA adapter checkpoint from an in-progress Ikhou supervised fine-tuning run on Qwen/Qwen3.5-2B.
Downloads · 30 days
9
17% of all-time downloads
All-time downloads
54
Public
Repo size
63.7 MB
Likes
0
Public
Click a slice to open those files.
.safetensors43.7 MB · 69%
From the Hugging Face model README
This repository contains the selected best saved LoRA adapter checkpoint from an in-progress Ikhou supervised fine-tuning run on Qwen/Qwen3.5-2B.
The original run was configured for a very long wall-clock duration, so the checkpoint was selected early from the saved checkpoints based on validation loss instead of waiting for the full run to complete.
checkpoint-8000Qwen/Qwen3.5-2Br=16, alpha=32, dropout=0.05q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_projAmong the checkpoints still available locally, checkpoint-8000 had the best validation loss.
checkpoint-8000: eval_loss = 0.09412checkpoint-8500: eval_loss = 0.10018checkpoint-9000: eval_loss = 0.09798Earlier checkpoints achieved slightly lower validation loss during the same run, but they were no longer retained locally because the training job used a limited checkpoint retention policy.
This adapter is intended for short bilingual dictionary-style glosses and translation-style responses in the Ikhou workflow.
Because this is a PEFT adapter repo, you should load it on top of the base model rather than treat it as a full standalone model snapshot.
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base_model_id = "Qwen/Qwen3.5-2B"
adapter_id = "ikhou/qwen35-2b-qlora-bilingual-ckpt8000"
tokenizer = AutoTokenizer.from_pretrained(adapter_id, trust_remote_code=True)
base_model = AutoModelForCausalLM.from_pretrained(
base_model_id,
trust_remote_code=True,
device_map="auto",
)
model = PeftModel.from_pretrained(base_model, adapter_id)
If you need a merged standalone model, merge the adapter into the base model after loading.