Instructions to use finalform/allrun_script_Qwen3-Coder-30B-A3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use finalform/allrun_script_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/allrun_script_Qwen3-Coder-30B-A3B-Instruct")

Transformers

How to use finalform/allrun_script_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/allrun_script_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/allrun_script_Qwen3-Coder-30B-A3B-Instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use finalform/allrun_script_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/allrun_script_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/allrun_script_Qwen3-Coder-30B-A3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/finalform/allrun_script_Qwen3-Coder-30B-A3B-Instruct

SGLang

How to use finalform/allrun_script_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/allrun_script_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/allrun_script_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/allrun_script_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/allrun_script_Qwen3-Coder-30B-A3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use finalform/allrun_script_Qwen3-Coder-30B-A3B-Instruct with Docker Model Runner:
```
docker model run hf.co/finalform/allrun_script_Qwen3-Coder-30B-A3B-Instruct
```

allrun_script_Qwen3-Coder-30B-A3B-Instruct / trainer_log.jsonl

finalform

Upload folder using huggingface_hub

b98f126 verified 21 days ago

raw

history blame contribute delete

1.52 kB

	{"current_steps": 2, "total_steps": 15, "loss": 0.1443, "lr": 0.0004, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "0:03:24", "remaining_time": "0:22:08"}
	{"current_steps": 4, "total_steps": 15, "loss": 0.1237, "lr": 0.00036923076923076927, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "0:05:27", "remaining_time": "0:15:01"}
	{"current_steps": 6, "total_steps": 15, "loss": 0.0406, "lr": 0.0003076923076923077, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "0:07:39", "remaining_time": "0:11:29"}
	{"current_steps": 8, "total_steps": 15, "loss": 0.025, "lr": 0.0002461538461538462, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "0:09:31", "remaining_time": "0:08:20"}
	{"current_steps": 10, "total_steps": 15, "loss": 0.0225, "lr": 0.00018461538461538463, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:11:25", "remaining_time": "0:05:42"}
	{"current_steps": 10, "total_steps": 15, "eval_loss": 0.016629977151751518, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:12:36", "remaining_time": "0:06:18"}
	{"current_steps": 12, "total_steps": 15, "loss": 0.0154, "lr": 0.0001230769230769231, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "0:15:55", "remaining_time": "0:03:58"}
	{"current_steps": 14, "total_steps": 15, "loss": 0.0166, "lr": 6.153846153846155e-05, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "0:17:38", "remaining_time": "0:01:15"}
	{"current_steps": 15, "total_steps": 15, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:19:30", "remaining_time": "0:00:00"}