Instructions to use bharathmuppa/angular-coder-30b-a3b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use bharathmuppa/angular-coder-30b-a3b-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-Coder-30B-A3B-Instruct") model = PeftModel.from_pretrained(base_model, "bharathmuppa/angular-coder-30b-a3b-lora") - Notebooks
- Google Colab
- Kaggle
Download train_summary.json from bharathmuppa/angular-coder-30b-a3b-lora: direct link, hf CLI and curl.
- Browser
- Download file 323 Bytes
-
https://huggingface.co/bharathmuppa/angular-coder-30b-a3b-lora/resolve/main/train_summary.json
- Command line
-
hf download hf://bharathmuppa/angular-coder-30b-a3b-lora/train_summary.json
-
curl -L -o train_summary.json https://huggingface.co/bharathmuppa/angular-coder-30b-a3b-lora/resolve/main/train_summary.json
323 Bytes
| { | |
| "base": "Qwen/Qwen3-Coder-30B-A3B-Instruct", | |
| "global_step": 796, | |
| "epoch": 2.0, | |
| "train_loss": 1.1279, | |
| "eval_loss": 1.1662, | |
| "max_minutes": 170.0, | |
| "epochs_target": 2.0, | |
| "batch": 1, | |
| "grad_accum": 8, | |
| "max_len": 4096, | |
| "rank": 16, | |
| "targets": [ | |
| "q_proj", | |
| "k_proj", | |
| "v_proj", | |
| "o_proj" | |
| ] | |
| } |