Instructions to use Columbidae/qwen-depth-upscaled-72 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Columbidae/qwen-depth-upscaled-72 with Transformers:

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

pipe = pipeline("text-generation", model="Columbidae/qwen-depth-upscaled-72")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Columbidae/qwen-depth-upscaled-72")
model = AutoModelForCausalLM.from_pretrained("Columbidae/qwen-depth-upscaled-72")
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

vLLM

How to use Columbidae/qwen-depth-upscaled-72 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Columbidae/qwen-depth-upscaled-72"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Columbidae/qwen-depth-upscaled-72",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Columbidae/qwen-depth-upscaled-72

SGLang

How to use Columbidae/qwen-depth-upscaled-72 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 "Columbidae/qwen-depth-upscaled-72" \
    --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": "Columbidae/qwen-depth-upscaled-72",
		"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 "Columbidae/qwen-depth-upscaled-72" \
        --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": "Columbidae/qwen-depth-upscaled-72",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Columbidae/qwen-depth-upscaled-72 with Docker Model Runner:
```
docker model run hf.co/Columbidae/qwen-depth-upscaled-72
```

qwen72l

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Passthrough merge method.

Models Merged

The following models were included in the merge:

ToastyPigeon/qwen2.5-14b-1m-unalign-v2

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [0,30]
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [30,31]
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [30,31]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [30,31]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [31,32]
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [31,32]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [31,32]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [32,33]
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [32,33]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [32,33]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [33,34]
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [33,34]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [33,34]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [34,35]
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [34,35]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [34,35]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [35,36]
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [35,36]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [35,36]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [36,37]
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [36,37]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [36,37]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [37,38]
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [37,38]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [37,38]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [38,39]
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [38,39]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [38,39]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [39,40]
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [39,40]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [39,40]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [40,41]
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [40,41]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [40,41]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [41,42]
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [41,42]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [41,42]
      parameters:
        scale:
        - filter: o_proj
          value: 0.0
        - filter: down_proj
          value: 0.0
        - value: 1.0
  - sources:
    - model: ToastyPigeon/qwen2.5-14b-1m-unalign-v2
      layer_range: [42,48]
merge_method: passthrough

Downloads last month: 2

Safetensors

Model size

21B params

Tensor type

BF16

Model tree for Columbidae/qwen-depth-upscaled-72

Base model

ToastyPigeon/qwen2.5-14b-1m-unalign-v2

Finetuned

(4)

this model