Instructions to use kromcomp/L3.1-Skywalkerv3-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kromcomp/L3.1-Skywalkerv3-12B with Transformers:

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

pipe = pipeline("text-generation", model="kromcomp/L3.1-Skywalkerv3-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kromcomp/L3.1-Skywalkerv3-12B")
model = AutoModelForCausalLM.from_pretrained("kromcomp/L3.1-Skywalkerv3-12B", 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 kromcomp/L3.1-Skywalkerv3-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kromcomp/L3.1-Skywalkerv3-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kromcomp/L3.1-Skywalkerv3-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kromcomp/L3.1-Skywalkerv3-12B

SGLang

How to use kromcomp/L3.1-Skywalkerv3-12B 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 "kromcomp/L3.1-Skywalkerv3-12B" \
    --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": "kromcomp/L3.1-Skywalkerv3-12B",
		"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 "kromcomp/L3.1-Skywalkerv3-12B" \
        --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": "kromcomp/L3.1-Skywalkerv3-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kromcomp/L3.1-Skywalkerv3-12B with Docker Model Runner:
```
docker model run hf.co/kromcomp/L3.1-Skywalkerv3-12B
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

skywalker

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

Merge Details

Merge Method

This model was merged using the NuSLERP merge method.

Models Merged

The following models were included in the merge:

merge/slice
merge/wedge

Configuration

The following YAML configuration was used to produce this model:

chat_template: llama3
dtype: float32
merge_method: nuslerp
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 50]
        model: merge/wedge
        parameters:
          weight:
          - filter: self_attn
            value: [1.0, 0.7, 0.5, 0.3, 0.0]
          - filter: mlp
            value: [0.0, 0.3, 0.5, 0.7, 1.0]
          - value: 0.7
      - layer_range: [0, 50]
        model: merge/slice
        parameters:
          weight:
          - filter: self_attn
            value: [0.0, 0.3, 0.5, 0.7, 1.0]
          - filter: mlp
            value: [1.0, 0.7, 0.5, 0.3, 0.0]
          - value: 0.3
tokenizer:
  pad_to_multiple_of: 32
  source: merge/wedge

Downloads last month: -

Safetensors

Model size

12B params

Tensor type

F32

Model tree for kromcomp/L3.1-Skywalkerv3-12B

Finetunes

2 models