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

Libraries

How to use junmingg/qwen2.5-coder-7b-text2sql 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")
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")
model = AutoModelForCausalLM.from_pretrained("junmingg/qwen2.5-coder-7b-text2sql")
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 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

Unsloth Studio

How to use junmingg/qwen2.5-coder-7b-text2sql 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 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 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 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",
    max_seq_length=2048,
)

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

junmingg commited on 18 days ago

Commit

7667c11

verified ·

1 Parent(s): 7ad1299

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -102,7 +102,7 @@ GGUF quants (`q4_k_m`, `q8_0`) for llama.cpp / Ollama: `junmingg/qwen2.5-coder-7
 | | |
 |---|---|
 | Base | `Qwen/Qwen2.5-Coder-7B-Instruct` (4-bit QLoRA) |
-| Data | [`b-mc2/sql-create-context`](https://huggingface.co/datasets/b-mc2/sql-create-context), 25k train / 500 held-out test (seed 42) |
 | LoRA | r=16, α=16, dropout=0, all linear layers |
 | Schedule | 1 epoch (~1,557 steps), effective batch 16, lr 2e-4 cosine, warmup 0.03 |
 | Precision / optim | bf16, `adamw_8bit`, `max_seq_length=2048` |

 | | |
 |---|---|
 | Base | `Qwen/Qwen2.5-Coder-7B-Instruct` (4-bit QLoRA) |
+| Data | [`b-mc2/sql-create-context`](https://huggingface.co/datasets/b-mc2/sql-create-context) (~78.6k rows total). Shuffled (seed 42), then a **25k train subset** + a fixed **500 held-out test** set. The remaining ~53k rows were intentionally unused — 1 epoch over 25k already saturates this task; adding the rest gives negligible lift while ~doubling/tripling train time. |
 | LoRA | r=16, α=16, dropout=0, all linear layers |
 | Schedule | 1 epoch (~1,557 steps), effective batch 16, lr 2e-4 cosine, warmup 0.03 |
 | Precision / optim | bf16, `adamw_8bit`, `max_seq_length=2048` |