KRadim commited on
Commit
1ceefdf
·
verified ·
1 Parent(s): 59722b2

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -13,17 +13,17 @@ tags:
13
  - qwen2.5
14
  ---
15
 
16
- # Qwen2.5-Coder-3B Text-to-Cypher (Neo4j) - Run #6
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: `210000`
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
 
 
13
  - qwen2.5
14
  ---
15
 
16
+ # Qwen2.5-Coder-3B Text-to-Cypher (Neo4j) - Run #7
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: `245000`
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` (8074 examples)
27
  - **Epochs:** 1
28
  - **Frameworks:** Unsloth, Hugging Face TRL, PEFT, PyTorch
29