Downloads · 30 days
0
chess-coach-lora-v5
suman-kalavagunta/chess-coach-lora-v5
chess-coach-lora-v5 is a machine learning model from suman-kalavagunta. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Upload these files to the root of the LoRA adapter model repo:
Access
Public
Updated Jul 3, 2026
Repo size
92.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors80.8 MB · 88%
At a glance
- Access
- Public
- Created
- Jul 3, 2026
- Updated
- Jul 3, 2026
- SHA
- 318bd9ea
Model card
From the Hugging Face model README
Custom Handler for Chess Coach LoRA Endpoint
Upload these files to the root of the LoRA adapter model repo:
handler.pyrequirements.txt
Target repo:
suman-kalavagunta/chess-coach-lora-v5
The handler loads:
Qwen/Qwen2.5-7B-Instruct
+
suman-kalavagunta/chess-coach-lora-v5
Example request:
{
"inputs": "PROMPT_SCHEMA_VERSION: 5\nTask: Generate one high-quality chess coaching label...",
"parameters": {
"max_new_tokens": 450,
"temperature": 0.2
}
}
Example response:
{
"generated_text": "1) Theme\n..."
}
Use a GPU endpoint. A10G may work; A100 is safer for 7B inference.
- Created
- Jul 3, 2026
- Updated
- Jul 3, 2026