Instructions to use finalform/generate_file_Qwen3-Coder-30B-A3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use finalform/generate_file_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/generate_file_Qwen3-Coder-30B-A3B-Instruct")

Transformers

How to use finalform/generate_file_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/generate_file_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/generate_file_Qwen3-Coder-30B-A3B-Instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use finalform/generate_file_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/generate_file_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/generate_file_Qwen3-Coder-30B-A3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/finalform/generate_file_Qwen3-Coder-30B-A3B-Instruct

SGLang

How to use finalform/generate_file_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/generate_file_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/generate_file_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/generate_file_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/generate_file_Qwen3-Coder-30B-A3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use finalform/generate_file_Qwen3-Coder-30B-A3B-Instruct with Docker Model Runner:
```
docker model run hf.co/finalform/generate_file_Qwen3-Coder-30B-A3B-Instruct
```

generate_file_Qwen3-Coder-30B-A3B-Instruct / trainer_log.jsonl

finalform

Upload folder using huggingface_hub

2459a3e verified 3 months ago

Raw

History Blame Contribute Delete

1.98 kB

	{"current_steps": 10, "total_steps": 90, "loss": 0.2185, "lr": 0.0003951219512195122, "epoch": 0.3333333333333333, "percentage": 11.11, "elapsed_time": "0:16:48", "remaining_time": "2:14:30"}
	{"current_steps": 20, "total_steps": 90, "loss": 0.0871, "lr": 0.00034634146341463415, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:31:22", "remaining_time": "1:49:47"}
	{"current_steps": 30, "total_steps": 90, "loss": 0.0658, "lr": 0.0002975609756097561, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:45:06", "remaining_time": "1:30:13"}
	{"current_steps": 40, "total_steps": 90, "loss": 0.052, "lr": 0.0002487804878048781, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "0:58:08", "remaining_time": "1:12:40"}
	{"current_steps": 50, "total_steps": 90, "loss": 0.0399, "lr": 0.0002, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "1:13:30", "remaining_time": "0:58:48"}
	{"current_steps": 50, "total_steps": 90, "eval_loss": 0.04152026027441025, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "1:23:03", "remaining_time": "1:06:26"}
	{"current_steps": 60, "total_steps": 90, "loss": 0.0318, "lr": 0.00015121951219512197, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:41:54", "remaining_time": "0:50:57"}
	{"current_steps": 70, "total_steps": 90, "loss": 0.0223, "lr": 0.0001024390243902439, "epoch": 2.3333333333333335, "percentage": 77.78, "elapsed_time": "1:58:20", "remaining_time": "0:33:48"}
	{"current_steps": 80, "total_steps": 90, "loss": 0.0238, "lr": 5.365853658536586e-05, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "2:15:40", "remaining_time": "0:16:57"}
	{"current_steps": 90, "total_steps": 90, "loss": 0.016, "lr": 4.8780487804878055e-06, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:28:55", "remaining_time": "0:00:00"}
	{"current_steps": 90, "total_steps": 90, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:30:12", "remaining_time": "0:00:00"}