GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
firfircelik
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
firfircelik
Model Tree
Qwen/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
ETL Error Explainer v2 is a domain-specific instruction-tuned language model designed to analyze ETL and data pipeline failures.
Given an ETL error message and execution context (environment, severity, cloud provider), the model produces a structured JSON response containing:
The model is intended to assist Data Engineers, Analytics Engineers, Platform Engineers, and DevOps teams during troubleshooting and incident response.
Fırat Çelik
Instruction-tuned causal language model
Qwen/Qwen2.5-1.5B-Instruct
QLoRA (4-bit NF4 Quantization + LoRA)
English
Apache-2.0
https://huggingface.co/firfircelik/etl-error-explainer-v2
Synthetic ETL troubleshooting instruction dataset created by the author.
The model is designed for structured ETL troubleshooting.
Example applications include:
Input:
markdown
Context:environment=prodseverity=Highcloud=AzureAnalyze the following Databricks failure:org.apache.spark.sql.AnalysisException:cannot resolve 'customer_email'
Output:
json
{"category": "...","root_cause": "...","immediate_fix": "...","long_term_fix": "..."}
The model can be integrated into:
The model is not intended for:
Outputs should always be reviewed before applying fixes to production environments.
The model has been trained specifically for ETL troubleshooting.
Limitations include:
Best performance is achieved when prompts include:
python
from transformers import AutoTokenizer, AutoModelForCausalLMmodel_id = "firfircelik/etl-error-explainer-v2"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id)prompt = """Context:environment=prodseverity=Highcloud=AzureAnalyze the following Databricks failure:org.apache.spark.sql.AnalysisException:cannot resolve 'customer_email'"""inputs = tokenizer(prompt, return_tensors="pt")outputs = model.generate(**inputs,max_new_tokens=256)print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Qwen/Qwen2.5-1.5B-Instruct
QLoRA
| Parameter | Value |
|---|---|
| r | 16 |
| alpha | 32 |
| dropout | 0.05 |
| target modules | q_proj, k_proj, v_proj, o_proj |
paged_adamw_8bit
| Parameter | Value |
|---|---|
| Epochs | 3 |
| Batch Size | 4 |
| Gradient Accumulation | 4 |
| Effective Batch Size | 16 |
| Learning Rate | 2e-4 |
| Sequence Length | 512 |
The model was trained on a synthetic instruction dataset covering realistic ETL failures.
Covered domains include:
Each sample contains:
A held-out validation split (10%) was used during training.
Additionally, the model was manually tested using unseen ETL failure scenarios.
Evaluation focused on:
NVIDIA Tesla T4
Kaggle Notebooks
QLoRA (4-bit)
Using QLoRA significantly reduces GPU memory usage and energy consumption compared to full fine-tuning.
Instruction-following generation of structured ETL troubleshooting responses.
Output format:
json
{"category": "...","root_cause": "...","immediate_fix": "...","long_term_fix": "..."}
| Domain | Supported |
|---|---|
| Apache Spark | ✅ |
| Databricks | ✅ |
| SQL | ✅ |
| Azure Data Factory | ✅ |
| Kafka | ✅ |
| Snowflake | ✅ |
| Delta Lake | ✅ |
| Schema Evolution | ✅ |
| Authentication | ✅ |
bibtex
@misc{celik2026etlexplainer,author = {Fırat Çelik},title = {ETL Error Explainer v2},year = {2026},publisher = {Hugging Face},howpublished = {\url{https://huggingface.co/firfircelik/etl-error-explainer-v2}}}
GitHub
https://github.com/firfircelik
Hugging Face
| Data Validation | ✅ |
| Cloud Storage | ✅ |