Instructions to use jk200201/qwen2.5-coder-7b-sql-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jk200201/qwen2.5-coder-7b-sql-dpo with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "jk200201/qwen2.5-coder-7b-sql-dpo")

Transformers

How to use jk200201/qwen2.5-coder-7b-sql-dpo with Transformers:

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

pipe = pipeline("text-generation", model="jk200201/qwen2.5-coder-7b-sql-dpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jk200201/qwen2.5-coder-7b-sql-dpo", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jk200201/qwen2.5-coder-7b-sql-dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jk200201/qwen2.5-coder-7b-sql-dpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jk200201/qwen2.5-coder-7b-sql-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jk200201/qwen2.5-coder-7b-sql-dpo

SGLang

How to use jk200201/qwen2.5-coder-7b-sql-dpo 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 "jk200201/qwen2.5-coder-7b-sql-dpo" \
    --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": "jk200201/qwen2.5-coder-7b-sql-dpo",
		"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 "jk200201/qwen2.5-coder-7b-sql-dpo" \
        --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": "jk200201/qwen2.5-coder-7b-sql-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jk200201/qwen2.5-coder-7b-sql-dpo with Docker Model Runner:
```
docker model run hf.co/jk200201/qwen2.5-coder-7b-sql-dpo
```

qwen2.5-coder-7b-sql-dpo / trainer_log.jsonl

jk200201

Upload folder using huggingface_hub

9240ae4 verified about 1 month ago

raw

history blame contribute delete

3.17 kB

	{"current_steps": 10, "total_steps": 130, "loss": 0.4812039852142334, "accuracy": 0.737500011920929, "lr": 3.461538461538462e-05, "epoch": 0.15384615384615385, "percentage": 7.69, "elapsed_time": "0:04:14", "remaining_time": "0:50:58"}
	{"current_steps": 20, "total_steps": 130, "loss": 0.38157622814178466, "accuracy": 0.8062500357627869, "lr": 4.967625656594782e-05, "epoch": 0.3076923076923077, "percentage": 15.38, "elapsed_time": "0:08:44", "remaining_time": "0:48:04"}
	{"current_steps": 30, "total_steps": 130, "loss": 0.31204392910003664, "accuracy": 0.824999988079071, "lr": 4.77281074950681e-05, "epoch": 0.46153846153846156, "percentage": 23.08, "elapsed_time": "0:13:04", "remaining_time": "0:43:36"}
	{"current_steps": 40, "total_steps": 130, "loss": 0.26097993850708007, "accuracy": 0.8687500357627869, "lr": 4.415111107797445e-05, "epoch": 0.6153846153846154, "percentage": 30.77, "elapsed_time": "0:17:23", "remaining_time": "0:39:08"}
	{"current_steps": 50, "total_steps": 130, "loss": 0.2709719896316528, "accuracy": 0.862500011920929, "lr": 3.920161866827889e-05, "epoch": 0.7692307692307693, "percentage": 38.46, "elapsed_time": "0:21:54", "remaining_time": "0:35:03"}
	{"current_steps": 60, "total_steps": 130, "loss": 0.4293703079223633, "accuracy": 0.8125, "lr": 3.323434381080199e-05, "epoch": 0.9230769230769231, "percentage": 46.15, "elapsed_time": "0:25:56", "remaining_time": "0:30:15"}
	{"current_steps": 70, "total_steps": 130, "loss": 0.22459855079650878, "accuracy": 0.893750011920929, "lr": 2.667694110977506e-05, "epoch": 1.0769230769230769, "percentage": 53.85, "elapsed_time": "0:30:16", "remaining_time": "0:25:56"}
	{"current_steps": 80, "total_steps": 130, "loss": 0.10246082544326782, "accuracy": 0.981249988079071, "lr": 1.9999357655598893e-05, "epoch": 1.2307692307692308, "percentage": 61.54, "elapsed_time": "0:34:24", "remaining_time": "0:21:30"}
	{"current_steps": 90, "total_steps": 130, "loss": 0.07779874801635742, "accuracy": 0.981249988079071, "lr": 1.3680153490759073e-05, "epoch": 1.3846153846153846, "percentage": 69.23, "elapsed_time": "0:38:56", "remaining_time": "0:17:18"}
	{"current_steps": 100, "total_steps": 130, "loss": 0.09446020126342773, "accuracy": 0.9750000238418579, "lr": 8.172204814310742e-06, "epoch": 1.5384615384615383, "percentage": 76.92, "elapsed_time": "0:43:13", "remaining_time": "0:12:58"}
	{"current_steps": 110, "total_steps": 130, "loss": 0.08398746848106384, "accuracy": 0.987500011920929, "lr": 3.8702478614051355e-06, "epoch": 1.6923076923076923, "percentage": 84.62, "elapsed_time": "0:47:27", "remaining_time": "0:08:37"}
	{"current_steps": 120, "total_steps": 130, "loss": 0.06980652809143066, "accuracy": 1.0, "lr": 1.0825894793143721e-06, "epoch": 1.8461538461538463, "percentage": 92.31, "elapsed_time": "0:51:48", "remaining_time": "0:04:19"}
	{"current_steps": 130, "total_steps": 130, "loss": 0.081082022190094, "accuracy": 0.96875, "lr": 9.011808227865625e-09, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:56:19", "remaining_time": "0:00:00"}
	{"current_steps": 130, "total_steps": 130, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:56:20", "remaining_time": "0:00:00"}