Instructions to use bunnycore/Qwen2.5-7B-MixStock-V0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bunnycore/Qwen2.5-7B-MixStock-V0.1 with Transformers:

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

pipe = pipeline("text-generation", model="bunnycore/Qwen2.5-7B-MixStock-V0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bunnycore/Qwen2.5-7B-MixStock-V0.1")
model = AutoModelForCausalLM.from_pretrained("bunnycore/Qwen2.5-7B-MixStock-V0.1", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bunnycore/Qwen2.5-7B-MixStock-V0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bunnycore/Qwen2.5-7B-MixStock-V0.1"
# 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/Qwen2.5-7B-MixStock-V0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bunnycore/Qwen2.5-7B-MixStock-V0.1

SGLang

How to use bunnycore/Qwen2.5-7B-MixStock-V0.1 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/Qwen2.5-7B-MixStock-V0.1" \
    --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/Qwen2.5-7B-MixStock-V0.1",
		"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/Qwen2.5-7B-MixStock-V0.1" \
        --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/Qwen2.5-7B-MixStock-V0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bunnycore/Qwen2.5-7B-MixStock-V0.1 with Docker Model Runner:
```
docker model run hf.co/bunnycore/Qwen2.5-7B-MixStock-V0.1
```

Qwen2.5-7B-MixStock-V0.1 / README.md

bunnycore

Adding Evaluation Results (#1)

321dfd7 verified over 1 year ago

preview code

Raw

History Blame Contribute Delete

4.97 kB

	---
	library_name: transformers
	tags:
	- mergekit
	- merge
	base_model:
	- mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1
	- bunnycore/Qwen2.5-7B-RRP-1M
	- bunnycore/Qwen-2.5-7b-Cool-lora
	- bunnycore/Qwen2.5-7B-RRP-1M
	- bunnycore/Qwen2.5-7B-RRP-1M
	- bunnycore/Qwen-2.5-7B-1M-RRP-v1-lora
	- open-thoughts/OpenThinker-7B
	model-index:
	- name: Qwen2.5-7B-MixStock-V0.1
	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: 76.73
	name: strict accuracy
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen2.5-7B-MixStock-V0.1
	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: 35.87
	name: normalized accuracy
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen2.5-7B-MixStock-V0.1
	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: 28.85
	name: exact match
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen2.5-7B-MixStock-V0.1
	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: 6.71
	name: acc_norm
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen2.5-7B-MixStock-V0.1
	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: 14.9
	name: acc_norm
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen2.5-7B-MixStock-V0.1
	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: 36.18
	name: accuracy
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Qwen2.5-7B-MixStock-V0.1
	name: Open LLM Leaderboard
	---
	# merge

	This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

	## Merge Details
	### Merge Method

	This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [bunnycore/Qwen2.5-7B-RRP-1M](https://huggingface.co/bunnycore/Qwen2.5-7B-RRP-1M) as a base.

	### Models Merged

	The following models were included in the merge:
	* [mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1](https://huggingface.co/mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1)
	* [bunnycore/Qwen2.5-7B-RRP-1M](https://huggingface.co/bunnycore/Qwen2.5-7B-RRP-1M) + [bunnycore/Qwen-2.5-7b-Cool-lora](https://huggingface.co/bunnycore/Qwen-2.5-7b-Cool-lora)
	* [bunnycore/Qwen2.5-7B-RRP-1M](https://huggingface.co/bunnycore/Qwen2.5-7B-RRP-1M) + [bunnycore/Qwen-2.5-7B-1M-RRP-v1-lora](https://huggingface.co/bunnycore/Qwen-2.5-7B-1M-RRP-v1-lora)
	* [open-thoughts/OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B)

	### Configuration

	The following YAML configuration was used to produce this model:

	```yaml
	models:
	- model: open-thoughts/OpenThinker-7B
	- model: mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1
	- model: bunnycore/Qwen2.5-7B-RRP-1M+bunnycore/Qwen-2.5-7B-1M-RRP-v1-lora
	- model: bunnycore/Qwen2.5-7B-RRP-1M+bunnycore/Qwen-2.5-7b-Cool-lora

	merge_method: model_stock
	base_model: bunnycore/Qwen2.5-7B-RRP-1M
	parameters:
	normalize: true
	dtype: bfloat16
	tokenizer_source: bunnycore/Qwen2.5-7B-RRP-1M
	```

	# [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__Qwen2.5-7B-MixStock-V0.1-details)

	\| Metric \|Value\|
	\|-------------------\|----:\|
	\|Avg. \|33.21\|
	\|IFEval (0-Shot) \|76.73\|
	\|BBH (3-Shot) \|35.87\|
	\|MATH Lvl 5 (4-Shot)\|28.85\|
	\|GPQA (0-shot) \| 6.71\|
	\|MuSR (0-shot) \|14.90\|
	\|MMLU-PRO (5-shot) \|36.18\|