Downloads · 30 days
4
11% of all-time downloads
qwen3-0.6b-datasetB-T2
COMPUTATION-NOT-FOUND/qwen3-0.6b-datasetB-T2
qwen3-0.6b-datasetB-T2 is a text generation model from COMPUTATION-NOT-FOUND. 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.
LoRA supervised fine-tuning of Qwen/Qwen3-0.6B on nvidia/OpenMathReasoning, merged into a standalone full model (16-bit). Part of an IBA NLP Assignment 04 LoRA ablation study (trials T1-T5).
All-time downloads
38
Public
Parameters
596M
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 GB · 99%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Jun 5, 2026
- Updated
- Jun 5, 2026
- SHA
- 16ffa6d6
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Qwen3-0.6B -- Dataset B SFT (Trial T2)
LoRA supervised fine-tuning of Qwen/Qwen3-0.6B on nvidia/OpenMathReasoning, merged into a
standalone full model (16-bit). Part of an IBA NLP Assignment 04 LoRA ablation
study (trials T1-T5).
Trial T2: Data efficiency -- 50% of 500 (250 rows)
| Hyperparameter | Value |
|---|---|
| LoRA rank | 16 |
| Data fraction | 50% of 500 rows |
| Learning rate | 0.0002 |
| Epochs | 1 |
| Target modules | q_proj, k_proj, v_proj, o_proj |
| Max seq length | 2048 |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("COMPUTATION-NOT-FOUND/qwen3-0.6b-datasetB-T2")
tok = AutoTokenizer.from_pretrained("COMPUTATION-NOT-FOUND/qwen3-0.6b-datasetB-T2")
msgs = [{"role": "user", "content": "What is 2+2?"}]
ids = tok.apply_chat_template(msgs, return_tensors="pt",
add_generation_prompt=True, enable_thinking=True)
print(tok.decode(model.generate(ids, max_new_tokens=512)[0]))
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- License
- apache-2.0
- Languages
- en
- Created
- Jun 5, 2026
- Updated
- Jun 5, 2026