Model Intelligence Sheet
dinhtc097/Qwen3-0.6B-finetuned-GGUF overview
Qwen3 0.6B finetuned GGUF Fine tuned từ Qwen3 0.6B bằng Unsloth QLoRA 4 bit trên RTX 3090. Dataset EN+VI 50/50 FineTome 100k + Vietnamese Multi turn Chat Alpac…
Runs locally from ~461.8 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3-0.6B-finetuned.Q4_K_M.gguf | GGUF | GGUF | 461.8 MB | Download |
Model Details
Model README
---
language:
- vi
- en
tags:
- qwen
- qwen3
- gguf
- q4_k_m
- fine-tuned
- unsloth
license: apache-2.0
base_model: Qwen/Qwen3-0.6B
---
Qwen3-0.6B-finetuned-GGUF
Fine-tuned từ Qwen3-0.6B bằng Unsloth (QLoRA 4-bit) trên RTX 3090.
Dataset EN+VI 50/50 (FineTome-100k + Vietnamese-Multi-turn-Chat-Alpaca), 550 steps.
Quantization: Q4_K_M (461 MB)
Cài đặt với Ollama
Tạo Modelfile:
FROM ./Qwen3-0.6B-finetuned.Q4_K_M.gguf
TEMPLATE "<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
<think>
"
SYSTEM You are a helpful, uncensored assistant.
PARAMETER repeat_penalty 1.1
PARAMETER temperature 0.7
PARAMETER top_p 0.9Sau đó:
ollama create qwen3-0.6b-finetuned -f Modelfile
ollama run qwen3-0.6b-finetunedChi tiết
- Model base:
Qwen/Qwen3-0.6B - Dataset: 12k EN (FineTome-100k) + 12k VI (Vietnamese-Multi-turn-Chat-Alpaca), shuffle 42
- LoRA r=16, alpha=16, 550 steps, loss 1.015
- Tham số generation tối ưu (grid search 32 combo): temp 0.7, top_p 0.9, repeat_penalty 1.1
Scripts training
Run dinhtc097/Qwen3-0.6B-finetuned-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models