Pipeline Dashboard

Code-Trainer V6 · RTX 5060 Ti 16GB (Blackwell)

Pipeline Progress 2/6 phases
01 Data Collection 02 Preprocessing 03 Vision Model 04 Qwen Fine-tuning 05 GGUF Deployment 06 Inference Agent

Dataset

32,658

Total Samples

26,126

Train Split

3,265

Validation Split

3,267

Test Split

Language Distribution

Python
5,800
JavaScript
4,900
TypeScript
4,700
Java
4,200
Go
3,800
Rust
3,500
C++
3,100
C#
2,658

Phases

01

Data Collection

Complete

Scrape high-quality GitHub repositories, filter code files, and capture Monaco Editor screenshots with 8 VS Code themes across 8 programming languages.

repos scraped

4000

captures

32727

languages

8

themes

8

PlaywrightGitPythonSQLiteasyncio
View docs →
02

Preprocessing

Complete

Convert screenshot captures to HuggingFace datasets in Qwen chat format, apply quality filtering, compute statistics, and upload to HF Hub.

total samples

32658

train samples

26126

val samples

3265

test samples

3267

HuggingFace DatasetsPillowWebP encoding
View docs →
03

Vision Model

Ready

Train a Swin-B vision encoder + MLP projector + Qwen2.5-Coder-1.5B decoder with LoRA adapters locally on RTX 5060 Ti. Establishes multimodal baseline.

vision encoder

Swin-B (frozen)

decoder

Qwen2.5-Coder-1.5B

lora r

16

batch size

2

epochs

10

PyTorchTransformersPEFTTRLW&B
View docs →
04

Qwen Fine-tuning

Ready

Fine-tune Qwen2.5-Coder-14B with LoRA on HuggingFace Skills A100 GPU. Runs 3 parallel sweep configs (conservative / standard / aggressive) then full training on top-2.

model

Qwen2.5-Coder-14B-Instruct

hardware

A100 80GB (cloud)

sweep configs

3

lora r range

16–64

HF Skills APIPEFT LoRAbitsandbytesA100 80GB
View docs →
05

GGUF Deployment

Ready

Merge LoRA weights into base model, quantize to GGUF Q4_K_M via llama.cpp, and upload to HF Hub for local serving via llama.cpp or Ollama.

quantization

Q4_K_M

context length

4096

serve port

8080

llama.cppGGUF Q4_K_MHF Hub
View docs →
06

Inference Agent

Planned

vLLM + Qwen-Agent + MCP tool integration for production inference. Planned architecture includes screenshot ingestion endpoint, code generation API, and IDE plugin.

vLLMQwen-AgentMCPFastAPI
View docs →

Model Config

Base Model

Qwen2.5-Coder-14B-Instruct

Hardware

RTX 5060 Ti 16GB (Blackwell)

HF Dataset

cmndcntrlcyber/code-trainer-v6-dataset

HF Model

cmndcntrlcyber/qwen14b-code-trainer-v6

W&B Project

code-trainer-v6

Version

6.0.0