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
```

Qwen-2.5-7b-S1k / README.md

bunnycore

Adding Evaluation Results (#1)

05842d0 verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

3.89 kB

	---
	library_name: transformers
	tags:
	- mergekit
	- merge
	base_model:
	- bunnycore/Qwen-2.5-7B-Deep-Stock-v4
	- bunnycore/Qwen-2.5-7b-s1k-lora_model
	model-index:
	- name: Qwen-2.5-7b-S1k
	results:
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: IFEval (0-Shot)
	type: HuggingFaceH4/ifeval
	args:
	num_few_shot: 0
	metrics:
	- type: inst_level_strict_acc and prompt_level_strict_acc
	value: 71.62
	name: strict accuracy
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen-2.5-7b-S1k
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: BBH (3-Shot)
	type: BBH
	args:
	num_few_shot: 3
	metrics:
	- type: acc_norm
	value: 36.69
	name: normalized accuracy
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen-2.5-7b-S1k
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: MATH Lvl 5 (4-Shot)
	type: hendrycks/competition_math
	args:
	num_few_shot: 4
	metrics:
	- type: exact_match
	value: 47.81
	name: exact match
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen-2.5-7b-S1k
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: GPQA (0-shot)
	type: Idavidrein/gpqa
	args:
	num_few_shot: 0
	metrics:
	- type: acc_norm
	value: 4.59
	name: acc_norm
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen-2.5-7b-S1k
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: MuSR (0-shot)
	type: TAUR-Lab/MuSR
	args:
	num_few_shot: 0
	metrics:
	- type: acc_norm
	value: 9.26
	name: acc_norm
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen-2.5-7b-S1k
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: MMLU-PRO (5-shot)
	type: TIGER-Lab/MMLU-Pro
	config: main
	split: test
	args:
	num_few_shot: 5
	metrics:
	- type: acc
	value: 37.58
	name: accuracy
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen-2.5-7b-S1k
	name: Open LLM Leaderboard
	---

	### 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:

	```yaml

	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

	```

	# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
	Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/bunnycore__Qwen-2.5-7b-S1k-details)

	\| Metric \|Value\|
	\|-------------------\|----:\|
	\|Avg. \|34.59\|
	\|IFEval (0-Shot) \|71.62\|
	\|BBH (3-Shot) \|36.69\|
	\|MATH Lvl 5 (4-Shot)\|47.81\|
	\|GPQA (0-shot) \| 4.59\|
	\|MuSR (0-shot) \| 9.26\|
	\|MMLU-PRO (5-shot) \|37.58\|