Instructions to use Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1 with Transformers:

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

pipe = pipeline("text-generation", model="Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1")
model = AutoModelForCausalLM.from_pretrained("Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1", 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 Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1

SGLang

How to use Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1 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 "Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1" \
    --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": "Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1",
		"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 "Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1" \
        --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": "Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1 with Docker Model Runner:
```
docker model run hf.co/Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1
```

Qwen2.5-METACODER 22.1B (mergekit-model1) by Solshine (Caleb DeLeeuw)

merge

This is an expirimental merge of pre-trained language models created using mergekit. No Fine-tuning, nor benchmarking, has been done with this model.

License

Hippocratic License 3.0 + Ecocide module, + Extractive Industries module, + Copyleft https://firstdonoharm.dev/version/3/0/cl-eco-extr.txt

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Qwen/Qwen2.5-Coder-7B-Instruct
        layer_range: [0, 16]
  - sources:
      - model: Qwen/Qwen2.5-Math-7B-Instruct
        layer_range: [3, 4]
  - sources:
      - model: Qwen/Qwen2.5-Coder-7B
        layer_range: [4, 20]
  - sources:
      - model: Qwen/Qwen2.5-Math-7B
        layer_range: [8, 24]
  - sources:
      - model: Qwen/Qwen2.5-Coder-7B
        layer_range: [10, 24]
  - sources:
      - model: Qwen/Qwen2.5-Coder-7B
        layer_range: [10, 14]
  - sources:
      - model: Qwen/Qwen2.5-Coder-7B-Instruct
        layer_range: [6, 26]
  - sources:
      - model: Qwen/Qwen2.5-Math-7B-Instruct
        layer_range: [25, 26]
  - sources:
      - model: Qwen/Qwen2.5-Coder-7B-Instruct
        layer_range: [26, 28]
merge_method: passthrough
dtype: float16

Downloads last month: 7

Safetensors

Model size

22B params

Tensor type

F16

Model tree for Solshine/Qwen2.5-METACODER-22.1B-mergekit-model1

Qwen/Qwen2.5-Coder-7B

Qwen/Qwen2.5-Coder-7B-Instruct

Qwen/Qwen2.5-Math-7B

Qwen/Qwen2.5-Math-7B-Instruct

Merge model

this model