Instructions to use junmingg/qwen2.5-coder-7b-text2sql-filtered with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use junmingg/qwen2.5-coder-7b-text2sql-filtered with Transformers:

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

pipe = pipeline("text-generation", model="junmingg/qwen2.5-coder-7b-text2sql-filtered")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("junmingg/qwen2.5-coder-7b-text2sql-filtered")
model = AutoModelForCausalLM.from_pretrained("junmingg/qwen2.5-coder-7b-text2sql-filtered")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use junmingg/qwen2.5-coder-7b-text2sql-filtered with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use junmingg/qwen2.5-coder-7b-text2sql-filtered with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "junmingg/qwen2.5-coder-7b-text2sql-filtered"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "junmingg/qwen2.5-coder-7b-text2sql-filtered",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/junmingg/qwen2.5-coder-7b-text2sql-filtered

SGLang

How to use junmingg/qwen2.5-coder-7b-text2sql-filtered 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 "junmingg/qwen2.5-coder-7b-text2sql-filtered" \
    --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": "junmingg/qwen2.5-coder-7b-text2sql-filtered",
		"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 "junmingg/qwen2.5-coder-7b-text2sql-filtered" \
        --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": "junmingg/qwen2.5-coder-7b-text2sql-filtered",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use junmingg/qwen2.5-coder-7b-text2sql-filtered with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for junmingg/qwen2.5-coder-7b-text2sql-filtered to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for junmingg/qwen2.5-coder-7b-text2sql-filtered to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for junmingg/qwen2.5-coder-7b-text2sql-filtered to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="junmingg/qwen2.5-coder-7b-text2sql-filtered",
    max_seq_length=2048,
)

Docker Model Runner
How to use junmingg/qwen2.5-coder-7b-text2sql-filtered with Docker Model Runner:
```
docker model run hf.co/junmingg/qwen2.5-coder-7b-text2sql-filtered
```

Qwen2.5-Coder-7B Text-to-SQL — filtered-train variant (QLoRA)

Same recipe as junmingg/qwen2.5-coder-7b-text2sql, but the 80 training rows whose gold SQL is unparseable (0.32% — WikiSQL label noise) were dropped before fine-tuning (24,920 train rows). This is the label-noise ablation described in the main model card.

Results (held-out 500 examples — identical references)

Model	Exact match	Semantic equiv.	SQL validity
Base (zero-shot)	3.8%	67.0%	100.0%
Main model (full 25k train)	78.8%	86.2%	99.2%
This model (filtered 24.9k train)	78.6%	85.4%	99.8%

On the valid-reference subset (497 rows) this model reaches 100% validity. Cleaning the noisy labels moved validity, not accuracy — exact-match and semantic-equivalence are unchanged within run-to-run noise.

Use the main model unless you specifically want this ablation. Usage, training details, evaluation methodology, and limitations are identical to the main model card. Code + harness: https://github.com/junmingg/Unsloth-Qwen2.5-Coder-7b-Text-to-SQL-SFT

License & attribution

Apache-2.0 (base model). Training data: b-mc2/sql-create-context (CC-BY-4.0).

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for junmingg/qwen2.5-coder-7b-text2sql-filtered

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Finetuned

Qwen/Qwen2.5-Coder-7B-Instruct

Finetuned

(405)

this model

junmingg
/

qwen2.5-coder-7b-text2sql-filtered

Qwen2.5-Coder-7B Text-to-SQL — filtered-train variant (QLoRA)

Results (held-out 500 examples — identical references)

License & attribution

Model tree for junmingg/qwen2.5-coder-7b-text2sql-filtered

Dataset used to train junmingg/qwen2.5-coder-7b-text2sql-filtered