Instructions to use renalpha/glm47-flash-typo3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use renalpha/glm47-flash-typo3 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/GLM-4.7-Flash") model = PeftModel.from_pretrained(base_model, "renalpha/glm47-flash-typo3") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
|
Download README.md from renalpha/glm47-flash-typo3: direct link, hf CLI and curl.
- Browser
- Download file 2.69 kB
-
https://huggingface.co/renalpha/glm47-flash-typo3/resolve/main/README.md
- Command line
-
hf download hf://renalpha/glm47-flash-typo3/README.md
-
curl -L -o README.md https://huggingface.co/renalpha/glm47-flash-typo3/resolve/main/README.md
2.69 kB
metadata
base_model: unsloth/GLM-4.7-Flash
language:
- en
license: other
tags:
- typo3
- finetuned
- lora
- peft
- unsloth
- glm
- cms
- php
GLM-4.7-Flash β TYPO3 v13.4 / v14 Finetuned
A LoRA adapter finetuned on top of GLM-4.7-Flash for TYPO3 CMS development β covering v13.4 LTS and v14.
What it knows
Trained on 17,649 Q&A pairs generated from the official TYPO3 documentation:
- Core API (TYPO3 Explained) β PSR-15 middleware, events, DI, site sets
- TCA Reference β all field types, column configs, type definitions
- TypoScript Reference β content objects, stdWrap, conditions, functions
- Fluid Templates β ViewHelpers, partials, layouts, standalone rendering
- TSconfig Reference β page and user TSconfig
- Sitepackage Tutorial β site package structure, configuration
- Getting Started Tutorial β installation, setup, basic concepts
- All sections covering both v13.4 LTS and v14 (main)
Training details
| Parameter | Value |
|---|---|
| Base model | GLM-4.7-Flash (30B MoE, 3B active) |
| Method | LoRA (16-bit) |
| LoRA rank | 32 |
| LoRA alpha | 32 |
| Training steps | 900 |
| Batch size | 8 (1 Γ 8 grad accum) |
| Learning rate | 2e-4 (cosine schedule) |
| Final loss | 1.032 |
| Training time | ~113 minutes on A100 80GB |
Usage
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained(
"renalpha/glm47-flash-typo3",
max_seq_length = 2048,
dtype = None,
load_in_4bit = False,
)
messages = [
{
"role": "system",
"content": "You are an expert TYPO3 13.4 developer."
},
{
"role": "user",
"content": "How do I create a custom TCA field type in TYPO3 v13.4?"
}
]
inputs = tokenizer.apply_chat_template(
messages,
tokenize=True,
add_generation_prompt=True,
return_tensors="pt",
).to("cuda")
outputs = model.generate(
input_ids=inputs,
max_new_tokens=512,
temperature=0.7,
do_sample=True,
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Dataset
Generated from the official TYPO3 GitHub documentation repos using GLM-4-32B-0414 as the synthetic data generator.
Repos used:
TYPO3-Documentation/TYPO3CMS-Reference-CoreApiTYPO3-Documentation/TYPO3CMS-Reference-TCATYPO3-Documentation/TYPO3CMS-Reference-TyposcriptTYPO3-Documentation/TYPO3CMS-Reference-ViewHelperTYPO3-Documentation/TYPO3CMS-Reference-TSconfigTYPO3-Documentation/TYPO3CMS-Tutorial-GettingStartedTYPO3-Documentation/TYPO3CMS-Tutorial-SitePackage