qwen3-0.6b

Instruction Residuals

This repository contains instruction residuals (delta weights) computed as the parameter-wise difference between Qwen/Qwen3-0.6B and Qwen/Qwen3-0.6B-Base.

Apply these residuals to the base model to reconstruct the instruction-tuned weights without retraining.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from residuals import Residuals

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B-Base")
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-0.6B-Base")

res = Residuals.from_pretrained("residuals/qwen3-0.6b")
res.apply(base, base_tokenizer=tok)

Provenance

• Created at: 2025-10-25T17:59:58.856127+00:00
• DType: float32
• Parameters: 311
• Shapes hash: a24a72d28c65d986a1537975e25867880c7ba603637058fceda763bcb730b2b8
• Names hash: 17f783d5d8f115eb5cf5c88fd284d191b841870eeffb9c845f51180afc4370ac
• Base model: Qwen/Qwen3-0.6B-Base
• Instruction model: Qwen/Qwen3-0.6B

Files

• model.safetensors: Serialized residual tensors (safetensors format).
• (optional) model.safetensors.index.json + shard files model-00001-of-000N.safetensors, ... for multi-part weights.
• config.json: Residuals metadata and provenance.
• tokenizer files: Saved tokenizer for compatibility.

About this format

These are additive residuals (task vectors). Applying them to the base model's parameters reconstructs the instruction-tuned model.

Tools

Generated with the residuals Python package. Install via: pip install residuals.

• PyPI: https://pypi.org/project/residuals/
• Source: https://github.com/omarish/residuals