Instructions to use finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct 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, "finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct")

Transformers

How to use finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct

SGLang

How to use finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct with Docker Model Runner:
```
docker model run hf.co/finalform/rewrite_plan_Qwen3-Coder-30B-A3B-Instruct
```

rewrite_plan_Qwen3-Coder-30B-A3B-Instruct / trainer_log.jsonl

finalform

Upload folder using huggingface_hub

7876911 verified about 1 month ago

raw

history blame contribute delete

2.57 kB

	{"current_steps": 5, "total_steps": 56, "loss": 1.071, "lr": 0.0004, "epoch": 0.35714285714285715, "percentage": 8.93, "elapsed_time": "0:11:36", "remaining_time": "1:58:19"}
	{"current_steps": 10, "total_steps": 56, "loss": 0.7765, "lr": 0.00036862745098039214, "epoch": 0.7142857142857143, "percentage": 17.86, "elapsed_time": "0:21:30", "remaining_time": "1:38:58"}
	{"current_steps": 15, "total_steps": 56, "loss": 0.6828, "lr": 0.0003294117647058824, "epoch": 1.0714285714285714, "percentage": 26.79, "elapsed_time": "0:31:22", "remaining_time": "1:25:46"}
	{"current_steps": 20, "total_steps": 56, "loss": 0.5171, "lr": 0.00029019607843137256, "epoch": 1.4285714285714286, "percentage": 35.71, "elapsed_time": "0:41:25", "remaining_time": "1:14:33"}
	{"current_steps": 25, "total_steps": 56, "loss": 0.4798, "lr": 0.00025098039215686274, "epoch": 1.7857142857142856, "percentage": 44.64, "elapsed_time": "0:51:03", "remaining_time": "1:03:18"}
	{"current_steps": 25, "total_steps": 56, "eval_loss": 0.48145776987075806, "epoch": 1.7857142857142856, "percentage": 44.64, "elapsed_time": "0:55:47", "remaining_time": "1:09:10"}
	{"current_steps": 30, "total_steps": 56, "loss": 0.42, "lr": 0.00021176470588235295, "epoch": 2.142857142857143, "percentage": 53.57, "elapsed_time": "1:07:03", "remaining_time": "0:58:07"}
	{"current_steps": 35, "total_steps": 56, "loss": 0.3501, "lr": 0.00017254901960784316, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "1:16:20", "remaining_time": "0:45:48"}
	{"current_steps": 40, "total_steps": 56, "loss": 0.3359, "lr": 0.00013333333333333334, "epoch": 2.857142857142857, "percentage": 71.43, "elapsed_time": "1:26:09", "remaining_time": "0:34:27"}
	{"current_steps": 45, "total_steps": 56, "loss": 0.2673, "lr": 9.411764705882353e-05, "epoch": 3.2142857142857144, "percentage": 80.36, "elapsed_time": "1:35:41", "remaining_time": "0:23:23"}
	{"current_steps": 50, "total_steps": 56, "loss": 0.2373, "lr": 5.490196078431373e-05, "epoch": 3.571428571428571, "percentage": 89.29, "elapsed_time": "1:44:57", "remaining_time": "0:12:35"}
	{"current_steps": 50, "total_steps": 56, "eval_loss": 0.458571195602417, "epoch": 3.571428571428571, "percentage": 89.29, "elapsed_time": "1:50:06", "remaining_time": "0:13:12"}
	{"current_steps": 55, "total_steps": 56, "loss": 0.25, "lr": 1.568627450980392e-05, "epoch": 3.928571428571429, "percentage": 98.21, "elapsed_time": "2:01:14", "remaining_time": "0:02:12"}
	{"current_steps": 56, "total_steps": 56, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "2:04:31", "remaining_time": "0:00:00"}