Instructions to use ldlfighting/reczero-qwen2.5-7b-music-step100 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ldlfighting/reczero-qwen2.5-7b-music-step100 with Transformers:

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

pipe = pipeline("text-generation", model="ldlfighting/reczero-qwen2.5-7b-music-step100")
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("ldlfighting/reczero-qwen2.5-7b-music-step100")
model = AutoModelForCausalLM.from_pretrained("ldlfighting/reczero-qwen2.5-7b-music-step100", 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 ldlfighting/reczero-qwen2.5-7b-music-step100 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ldlfighting/reczero-qwen2.5-7b-music-step100"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ldlfighting/reczero-qwen2.5-7b-music-step100",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ldlfighting/reczero-qwen2.5-7b-music-step100

SGLang

How to use ldlfighting/reczero-qwen2.5-7b-music-step100 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 "ldlfighting/reczero-qwen2.5-7b-music-step100" \
    --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": "ldlfighting/reczero-qwen2.5-7b-music-step100",
		"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 "ldlfighting/reczero-qwen2.5-7b-music-step100" \
        --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": "ldlfighting/reczero-qwen2.5-7b-music-step100",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ldlfighting/reczero-qwen2.5-7b-music-step100 with Docker Model Runner:
```
docker model run hf.co/ldlfighting/reczero-qwen2.5-7b-music-step100
```

RecZero Qwen2.5-7B Music, step 100

Full-parameter Music rating-prediction checkpoint after 100 training updates, initialized from Qwen2.5-7B-Instruct. BF16 weights; actor KL coefficient 0.001.

The model follows the RecZero structured reasoning and <rate> output format. This repository contains model weights, configuration, and tokenizer files. Optimizer state is retained locally and is not included.

Saved validation results (400 examples, greedy vLLM inference, 1,024-token cap): MAE 0.727375; RMSE 1.121107; parse rate 100%. These are validation metrics, not full-test results. Full-test evaluation was still running when this upload was prepared.

Downloads last month: 180

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for ldlfighting/reczero-qwen2.5-7b-music-step100

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

(3148)

this model