Instructions to use ronantakizawa/codereview-qwen32b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ronantakizawa/codereview-qwen32b with Transformers:

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

pipe = pipeline("text-generation", model="ronantakizawa/codereview-qwen32b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ronantakizawa/codereview-qwen32b")
model = AutoModelForCausalLM.from_pretrained("ronantakizawa/codereview-qwen32b")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ronantakizawa/codereview-qwen32b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ronantakizawa/codereview-qwen32b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ronantakizawa/codereview-qwen32b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ronantakizawa/codereview-qwen32b

SGLang

How to use ronantakizawa/codereview-qwen32b 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 "ronantakizawa/codereview-qwen32b" \
    --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": "ronantakizawa/codereview-qwen32b",
		"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 "ronantakizawa/codereview-qwen32b" \
        --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": "ronantakizawa/codereview-qwen32b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ronantakizawa/codereview-qwen32b with Docker Model Runner:
```
docker model run hf.co/ronantakizawa/codereview-qwen32b
```

CodeReview-Qwen32B (Merged)

A Qwen2.5-Coder-32B-Instruct model fine-tuned for code review.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "ronantakizawa/codereview-qwen32b-merged",
    device_map="auto",
    torch_dtype="auto",
)
tokenizer = AutoTokenizer.from_pretrained("ronantakizawa/codereview-qwen32b-merged")

Details

See the adapter model card for full training details, evaluation results, and prompt format.

Metric	Base Model (Zero-Shot)	Fine-Tuned	Change
BLEU-4	3.82	16.91	+343%
ROUGE-L F1	0.081	0.216	+167%
Sentence-BERT Cosine Sim	0.477	0.526	+10%
Comment Type Accuracy	0.00	0.640	--

Format: bf16 safetensors (14 shards, ~64GB)
Training: QLoRA SFT on 48K real code review examples from 504 GitHub repos
Dataset: ronantakizawa/github-codereview

Downloads last month: 48

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for ronantakizawa/codereview-qwen32b

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/Qwen2.5-Coder-32B

Finetuned

Qwen/Qwen2.5-Coder-32B-Instruct

Finetuned

(130)

this model

ronantakizawa
/

codereview-qwen32b

CodeReview-Qwen32B (Merged)

Usage

Details

Model tree for ronantakizawa/codereview-qwen32b

Dataset used to train ronantakizawa/codereview-qwen32b