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

Libraries

How to use jk200201/qwen2.5-coder-7b-bird-cot with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jk200201/qwen2.5-coder-7b-bird-cot")
model = AutoModelForCausalLM.from_pretrained("jk200201/qwen2.5-coder-7b-bird-cot", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

docker model run hf.co/jk200201/qwen2.5-coder-7b-bird-cot

SGLang

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

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

jk200201 commited on Jul 15

Commit

78cadc9

verified ·

1 Parent(s): d5b49d3

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +11 -9

README.md CHANGED Viewed

@@ -38,21 +38,23 @@ model-index:
 A 7B text-to-SQL model that reasons step by step over a database schema and then writes the SQL. It is fine-tuned from `Qwen/Qwen2.5-Coder-7B-Instruct` by distilling execution-verified chain-of-thought solutions.
-On BIRD dev (realistic, messy schemas, the harder text-to-SQL benchmark) it reaches **52.1% greedy** result accuracy and **58.5% with self-consistency** (Best-of-N, K=8). The self-consistency score surpasses single-shot frontier models at a fraction of the size.
 ![BIRD dev results](bird_results.png)
 ## Results: BIRD dev (execution result accuracy)
-| Model | Result accuracy |
-|:--|--:|
-| Base Qwen2.5-Coder-7B-Instruct | 27.0% |
-| **This model, greedy (1 sample)** | **52.1%** |
-| DeepSeek-V3 (single-shot) | 54.7% |
-| Grok-4 (single-shot) | 55.4% |
-| **This model, self-consistency (K=8)** | **58.5%** |
-Result accuracy is the fraction of queries whose SQL executes to the same rows as the gold query (BIRD's official execution metric). Frontier numbers are single-shot. The 58.5% figure uses K=8 self-consistency, which costs roughly 8x inference.
 ## Usage

 A 7B text-to-SQL model that reasons step by step over a database schema and then writes the SQL. It is fine-tuned from `Qwen/Qwen2.5-Coder-7B-Instruct` by distilling execution-verified chain-of-thought solutions.
+On BIRD dev (realistic, messy schemas, the harder text-to-SQL benchmark) it reaches **52.1% greedy** result accuracy and **58.5% with self-consistency** (Best-of-N, K=8). With self-consistency it matches DeepSeek V4-Pro (1.6T parameters) at roughly 0.4% of the size, running locally.
 ![BIRD dev results](bird_results.png)
 ## Results: BIRD dev (execution result accuracy)
+All models use a single chain-of-thought sample unless noted, so the comparison is like for like.
+| Model | Params | Result accuracy |
+|:--|--:|--:|
+| Base Qwen2.5-Coder-7B-Instruct | 7B | 27.0% |
+| **This model, greedy** | **7B** | **52.1%** |
+| **This model, self-consistency (K=8)** | **7B** | **58.5%** |
+| DeepSeek V4-Pro | 1.6T | 58.7% |
+| GLM 5.2 | 744B | 63.0% |
+Result accuracy is the fraction of queries whose SQL executes to the same rows as the gold query (BIRD's official execution metric). The larger frontier models score higher, as expected. The point is that a 7B reaches their accuracy band at a fraction of the size and cost. The 58.5% figure uses K=8 self-consistency (roughly 8x inference).
 ## Usage