Instructions to use batuhne/customer-support-llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use batuhne/customer-support-llm with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("batuhne/customer-support-llm") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use batuhne/customer-support-llm with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "batuhne/customer-support-llm" --prompt "Once upon a time"
- Atomic Chat
Commit History
-
Retrained adapter, 5000 iters, all 7 projections, ROUGE-L 0.41
Verified signature3ef576a -
Update adapter_config for 5000-iter retrain (LR 2e-4, all 7 projections)
Verified signature27df773 -
Update model card with 2026-05-12 retrain metrics
Verified signaturef7e3f65
-
Add adapter config
Verified signaturece3d8cb -
Update adapter: LoRA rank-16, 1500 iters, full Bitext dataset (27 intents)
Verified signature30c3b9a
-
Initial commit: LoRA adapter + model card
846c771