Instructions to use bunnycore/Qwen-2.5-7b-S1k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bunnycore/Qwen-2.5-7b-S1k with Transformers:

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

pipe = pipeline("text-generation", model="bunnycore/Qwen-2.5-7b-S1k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bunnycore/Qwen-2.5-7b-S1k")
model = AutoModelForCausalLM.from_pretrained("bunnycore/Qwen-2.5-7b-S1k")
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 Settings

vLLM

How to use bunnycore/Qwen-2.5-7b-S1k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bunnycore/Qwen-2.5-7b-S1k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bunnycore/Qwen-2.5-7b-S1k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bunnycore/Qwen-2.5-7b-S1k

SGLang

How to use bunnycore/Qwen-2.5-7b-S1k 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 "bunnycore/Qwen-2.5-7b-S1k" \
    --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": "bunnycore/Qwen-2.5-7b-S1k",
		"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 "bunnycore/Qwen-2.5-7b-S1k" \
        --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": "bunnycore/Qwen-2.5-7b-S1k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bunnycore/Qwen-2.5-7b-S1k with Docker Model Runner:
```
docker model run hf.co/bunnycore/Qwen-2.5-7b-S1k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

System Prompt

Think about the reasoning process in the mind first, then provide the answer. The reasoning process should detailed and should be wrapped within <think> </think> tags, then provide the answer after that, i.e., <think> reasoning process here </think> answer here.

Configuration

The following YAML configuration was used to produce this model:


base_model: bunnycore/Qwen-2.5-7B-Deep-Stock-v4+bunnycore/Qwen-2.5-7b-s1k-lora_model
dtype: bfloat16
merge_method: passthrough
models:
  - model: bunnycore/Qwen-2.5-7B-Deep-Stock-v4+bunnycore/Qwen-2.5-7b-s1k-lora_model
tokenizer_source: bunnycore/Qwen-2.5-7B-Deep-Stock-v4