Downloads · 30 days
4
7% of all-time downloads
qwen3-4b-nothink-s1-full-sft
modrill/qwen3-4b-nothink-s1-full-sft
qwen3-4b-nothink-s1-full-sft is a text generation model from modrill. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Full-parameter supervised fine-tuning (SFT) of Qwen/Qwen3-4B-Base on ocinothink50k (50k OpenCodeInstruct samples) using the qwen3nothink chat template (direct answers, no extended think blocks).
All-time downloads
54
Public
Parameters
4.4B
8.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors8.8 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Jun 10, 2026
- Updated
- Jun 10, 2026
- SHA
- f08aa179
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-4B No-Think S1 (Full SFT)
Full-parameter supervised fine-tuning (SFT) of Qwen/Qwen3-4B-Base on oci_nothink_50k (50k OpenCodeInstruct samples) using the qwen3_nothink chat template (direct answers, no extended think blocks).
Model description
- Method: full SFT (all weights trainable), DeepSpeed ZeRO-2, 4 GPUs
- Dataset: oci_nothink_50k (50,000 examples)
- Template: qwen3_nothink
- Not LoRA / not QLoRA: entire 4B model was updated
Note: The final training save was interrupted by disk full; published weights were restored from checkpoint-782 (same step count as training completion).
Training details
| Field | Value |
|---|---|
| Epochs | 1 |
| Seed | 42 |
| cutoff_len | 4096 |
| packing | false |
| per_device_train_batch_size | 4 |
| gradient_accumulation_steps | 4 |
| effective_batch_size | 64 (4 x 4 x 4 GPUs) |
| learning_rate | 3e-5 |
| train_loss | 0.1572 |
| train_steps | 782 |
| finished_at | 2026-06-10 06:18 CST |
| runtime | ~53 min |
Related models
- Think SFT (same project): modrill/qwen3-4b-think-s1-ep23-full-sft - ocr_think_50k, qwen3 template
- Base: Qwen/Qwen3-4B-Base
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
repo_id = "modrill/qwen3-4b-nothink-s1-full-sft"
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
repo_id,
torch_dtype="auto",
device_map="auto",
trust_remote_code=True,
)
License
Released under Apache 2.0 (see upstream Qwen model card if not bundled here).
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Created
- Jun 10, 2026
- Updated
- Jun 10, 2026