Instructions to use lilmeaty/kaska with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lilmeaty/kaska with Transformers:

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

pipe = pipeline("text-generation", model="lilmeaty/kaska")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("lilmeaty/kaska")
model = AutoModelForCausalLM.from_pretrained("lilmeaty/kaska", 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 lilmeaty/kaska with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/lilmeaty/kaska

SGLang

How to use lilmeaty/kaska 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 "lilmeaty/kaska" \
    --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": "lilmeaty/kaska",
		"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 "lilmeaty/kaska" \
        --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": "lilmeaty/kaska",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lilmeaty/kaska with Docker Model Runner:
```
docker model run hf.co/lilmeaty/kaska
```

merge

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:

lilmeaty/ksksksk

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources: 
      - layer_range: [0, 40]
        model: lilmeaty/ksksksk
        parameters:
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
          quantization:
            method: int8
            value: 100
          quantization:
            method: int4
            value: 100
  - sources: 
      - layer_range: [0, 3]
        model: lilmeaty/ksksksk
        parameters:
          normalize: true
          int8_mask: true
          density: 0.5
          weight: 0.1
          random_seed: 0
          temperature: 0.5
          top_p: 0.65
          inference: true
          max_tokens: 999999999
          stream: true
          quantization:
            method: int8
            value: 100
          quantization:
            method: int4
            value: 100
parameters:
  normalize: true
  int8_mask: true
  density: 0.5
  weight: 0.1
  random_seed: 0
  temperature: 0.5
  top_p: 0.65
  inference: true
  max_tokens: 999999999
  stream: true
  convert_to:
    type: 
      - gguf
    value: 100.0
merge_method: passthrough

Downloads last month: 23

Safetensors

Model size

5B params

Tensor type

BF16

F16

Model tree for lilmeaty/kaska

Base model

lilmeaty/ksksksk

Finetuned

(1)

this model