Instructions to use hf-internal-testing/tiny-random-GraniteMoeForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-random-GraniteMoeForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="hf-internal-testing/tiny-random-GraniteMoeForCausalLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hf-internal-testing/tiny-random-GraniteMoeForCausalLM")
model = AutoModelForCausalLM.from_pretrained("hf-internal-testing/tiny-random-GraniteMoeForCausalLM")
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 hf-internal-testing/tiny-random-GraniteMoeForCausalLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hf-internal-testing/tiny-random-GraniteMoeForCausalLM

SGLang

How to use hf-internal-testing/tiny-random-GraniteMoeForCausalLM 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 "hf-internal-testing/tiny-random-GraniteMoeForCausalLM" \
    --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": "hf-internal-testing/tiny-random-GraniteMoeForCausalLM",
		"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 "hf-internal-testing/tiny-random-GraniteMoeForCausalLM" \
        --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": "hf-internal-testing/tiny-random-GraniteMoeForCausalLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hf-internal-testing/tiny-random-GraniteMoeForCausalLM with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-random-GraniteMoeForCausalLM
```

Xenova HF Staff commited on Oct 31, 2024

Commit

4037537

verified ·

1 Parent(s): 071235d

Update README.md

Browse files

Files changed (1) hide show

README.md +20 -0

README.md CHANGED Viewed

@@ -11,6 +11,26 @@ tags: []
 ## Model Details
 ### Model Description
 <!-- Provide a longer summary of what this model is. -->

 ## Model Details
+### Code to generate the model
+```py
+from transformers import GraniteMoeConfig, GraniteMoeForCausalLM, AutoTokenizer
+model = GraniteMoeForCausalLM(GraniteMoeConfig(
+    hidden_size=32,
+    intermediate_size=64,
+    num_attention_heads=4,
+    num_hidden_layers=2,
+    num_key_value_heads=4,
+    pad_token_id=0,
+    vocab_size=49155,
+))
+tokenizer = AutoTokenizer.from_pretrained('ibm-granite/granite-3.0-1b-a400m-instruct')
+model.push_to_hub('hf-internal-testing/tiny-random-GraniteMoeForCausalLM')
+tokenizer.push_to_hub('hf-internal-testing/tiny-random-GraniteMoeForCausalLM')
+```
 ### Model Description
 <!-- Provide a longer summary of what this model is. -->