Instructions to use leafspark/magnum-72b-v1-llamaify with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use leafspark/magnum-72b-v1-llamaify with Transformers:

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

pipe = pipeline("text-generation", model="leafspark/magnum-72b-v1-llamaify")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("leafspark/magnum-72b-v1-llamaify")
model = AutoModelForCausalLM.from_pretrained("leafspark/magnum-72b-v1-llamaify", 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 leafspark/magnum-72b-v1-llamaify with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/leafspark/magnum-72b-v1-llamaify

SGLang

How to use leafspark/magnum-72b-v1-llamaify 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 "leafspark/magnum-72b-v1-llamaify" \
    --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": "leafspark/magnum-72b-v1-llamaify",
		"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 "leafspark/magnum-72b-v1-llamaify" \
        --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": "leafspark/magnum-72b-v1-llamaify",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use leafspark/magnum-72b-v1-llamaify with Docker Model Runner:
```
docker model run hf.co/leafspark/magnum-72b-v1-llamaify
```

leafspark commited on Aug 13, 2024

Commit

3638dde

verified ·

1 Parent(s): 0b7cf05

model: add chunks 33-37

Browse files

Files changed (5) hide show

model-00033-of-00038.safetensors +3 -0
model-00034-of-00038.safetensors +3 -0
model-00035-of-00038.safetensors +3 -0
model-00036-of-00038.safetensors +3 -0
model-00037-of-00038.safetensors +3 -0

model-00033-of-00038.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:77ccde7d3261bf0faad274c56ff872371e0c15de6949c8c566be41d1f34ed30f
+size 3995216952

model-00034-of-00038.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:34729bb99f05afa1fdca1dc0865ea27740c7fb3f3d959c7683fe1e98636c9135
+size 3995235608

model-00035-of-00038.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7688739785288dcd41887bdc330a5b26a97937b367055f59a55ad1f929a1f95a
+size 3812816720

model-00036-of-00038.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3edb364c06b99bbbfb6e0744979ebce12517ccac70e43dd2e9fc4a1f0d3b3da7
+size 3812802400

model-00037-of-00038.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:018c570cb9dbec2c43e96258b6064f3b51eec4e207b29581c42ac93a96b01046
+size 3208747040