Text Generation
PEFT
Safetensors
English
qwen2
text-to-cypher
neo4j
cypher
unsloth
qwen2.5
conversational
Instructions to use KRadim/Qwen2.5-Coder-3B-text2cypher-Merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use KRadim/Qwen2.5-Coder-3B-text2cypher-Merged with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Unsloth Model Card
Browse files
README.md
CHANGED
|
@@ -1,50 +1,21 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
- KRadim/multilingual-text2cypher-2025
|
| 4 |
-
language: en
|
| 5 |
-
library_name: peft
|
| 6 |
-
license: apache-2.0
|
| 7 |
-
pipeline_tag: text-generation
|
| 8 |
tags:
|
| 9 |
-
- text-
|
| 10 |
-
-
|
| 11 |
-
- cypher
|
| 12 |
- unsloth
|
| 13 |
-
- qwen2
|
|
|
|
|
|
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
-
#
|
| 17 |
-
|
| 18 |
-
This model is a fine-tuned version of **unsloth/Qwen2.5-Coder-3B-Instruct** optimized for translating natural language questions into accurate **Neo4j Cypher queries** using a structured database schema.
|
| 19 |
-
|
| 20 |
-
Number of samples used: `70000`
|
| 21 |
-
|
| 22 |
-
## Model Details
|
| 23 |
-
|
| 24 |
-
- **Base Architecture:** Qwen2.5-Coder-3B-Instruct
|
| 25 |
-
- **Fine-Tuning Method:** QLoRA (Rank 16, Alpha 16)
|
| 26 |
-
- **Dataset Used:** `KRadim/multilingual-text2cypher-2025` (35000 examples)
|
| 27 |
-
- **Epochs:** 1
|
| 28 |
-
- **Frameworks:** Unsloth, Hugging Face TRL, PEFT, PyTorch
|
| 29 |
-
|
| 30 |
-
## Prompts & Schema Usage
|
| 31 |
-
|
| 32 |
-
The model expects system prompts containing the Neo4j schema structure:
|
| 33 |
-
|
| 34 |
-
```text
|
| 35 |
-
<|im_start|>system
|
| 36 |
-
You are an expert in Neo4j databases and the Cypher query language. Your task is to convert natural language queries into accurate and efficient Cypher queries based on the provided database schema.
|
| 37 |
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
[YOUR NATURAL LANGUAGE QUESTION]<|im_end|>
|
| 42 |
-
<|im_start|>assistant
|
| 43 |
-
```
|
| 44 |
|
| 45 |
-
|
| 46 |
-
You can run the exported GGUF model (KRadim/Qwen2.5-Coder-3B-text2cypher-GGUF) directly in Ollama:
|
| 47 |
|
| 48 |
-
|
| 49 |
-
ollama run hf.co/KRadim/Qwen2.5-Coder-3B-text2cypher-GGUF:Q4_K_M
|
| 50 |
-
```
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
+
- text-generation-inference
|
| 5 |
+
- transformers
|
|
|
|
| 6 |
- unsloth
|
| 7 |
+
- qwen2
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
language:
|
| 10 |
+
- en
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# Uploaded finetuned model
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
+
- **Developed by:** KRadim
|
| 16 |
+
- **License:** apache-2.0
|
| 17 |
+
- **Finetuned from model :** unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
+
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
|
|
|
| 20 |
|
| 21 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
|
|