Instructions to use mmoza32/ShadowLM-Final-Core with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mmoza32/ShadowLM-Final-Core with Transformers:

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

pipe = pipeline("text-generation", model="mmoza32/ShadowLM-Final-Core")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mmoza32/ShadowLM-Final-Core")
model = AutoModelForCausalLM.from_pretrained("mmoza32/ShadowLM-Final-Core")
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 mmoza32/ShadowLM-Final-Core with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mmoza32/ShadowLM-Final-Core"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mmoza32/ShadowLM-Final-Core",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mmoza32/ShadowLM-Final-Core

SGLang

How to use mmoza32/ShadowLM-Final-Core 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 "mmoza32/ShadowLM-Final-Core" \
    --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": "mmoza32/ShadowLM-Final-Core",
		"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 "mmoza32/ShadowLM-Final-Core" \
        --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": "mmoza32/ShadowLM-Final-Core",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mmoza32/ShadowLM-Final-Core with Docker Model Runner:
```
docker model run hf.co/mmoza32/ShadowLM-Final-Core
```

ShadowLM-Final-Core / mergekit_config.yml

mmoza32

Upload ShadowLM-Final-Core model weights and config

8c48a7b verified about 1 month ago

raw

history blame contribute delete

506 Bytes

	base_model: NousResearch/Hermes-3-Llama-3.1-8B
	dtype: bfloat16
	merge_method: linear
	modules:
	default:
	slices:
	- sources:
	- layer_range: [0, 32]
	model: NousResearch/Hermes-3-Llama-3.1-8B
	parameters:
	weight: 0.4
	- layer_range: [0, 32]
	model: mlabonne/Meta-Llama-3.1-8B-Instruct-Abliterated
	parameters:
	weight: 0.3
	- layer_range: [0, 32]
	model: unsloth/Meta-Llama-3.1-8B-Instruct
	parameters:
	weight: 0.3