You can deploy this model and start earning money today!

residuals/
qwen3-1.7b

Name: qwen3-1.7b
Availability: InStock

Views

No views yet

Instruction Residuals

This repository contains instruction residuals (delta weights) computed as the parameter-wise difference between Qwen/Qwen3-1.7B and Qwen/Qwen3-1.7B-Base.

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

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer
from residuals import Residuals

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-1.7B-Base")
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-1.7B-Base")

res = Residuals.from_pretrained("residuals/qwen3-1.7b")
res.apply(base, base_tokenizer=tok)

Provenance

Created at: 2025-10-25T18:00:44.295450+00:00
DType: float32
Parameters: 311
Shapes hash: c5f7430aa5078846eb1e7b6df0b59a9736f76cdc6fbe8566d8fbcc586ba1051c
Names hash: 17f783d5d8f115eb5cf5c88fd284d191b841870eeffb9c845f51180afc4370ac
Base model: Qwen/Qwen3-1.7B-Base
Instruction model: Qwen/Qwen3-1.7B

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