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

Libraries

How to use prettyvampire/poemma with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prettyvampire/poemma")
model = AutoModelForCausalLM.from_pretrained("prettyvampire/poemma")
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 prettyvampire/poemma with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/prettyvampire/poemma

SGLang

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

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

prettyvampire commited on Dec 6, 2024

Commit

4d4563a

verified ·

1 Parent(s): 123da48

Update README.md

Browse files

Files changed (1) hide show

README.md +20 -20

README.md CHANGED Viewed

@@ -56,26 +56,26 @@ Large Language model for interpretation of poetry.
 **Input example:**
-You are given the poem "Song of Beren and Lúthien" by J. R. R. Tolkien.
-    <poem>
-    One moment stood she, and a spell
-His voice laid on her: Beren came,
-And doom fell on Tinúviel
-That in his arms lay glistening.
-As Beren looked into her eyes
-Within the shadows of her hair,
-The trembling starlight of the skies
-He saw there mirrored shimmering.
-Tinúviel the elven-fair,
-Immortal maiden elven-wise,
-About him cast her shadowy hair
-And arms like silver glimmering.
-    Long was the way that fate them bore,
-    O'er stony mountains cold and grey,
-Through halls of iron and darkling door,
-And woods of nightshade morrowless.
-    </poem>
-    Explain the meaning of the following lines: "Long was the way that fate them bore,"
 **Output example:**

 **Input example:**
+You are given the poem "Song of Beren and Lúthien" by J. R. R. Tolkien.
+    <poem>
+    One moment stood she, and a spell
+His voice laid on her: Beren came,
+And doom fell on Tinúviel
+That in his arms lay glistening.
+As Beren looked into her eyes
+Within the shadows of her hair,
+The trembling starlight of the skies
+He saw there mirrored shimmering.
+Tinúviel the elven-fair,
+Immortal maiden elven-wise,
+About him cast her shadowy hair
+And arms like silver glimmering.
+    Long was the way that fate them bore,
+    O'er stony mountains cold and grey,
+Through halls of iron and darkling door,
+And woods of nightshade morrowless.
+    </poem>
+    Explain the meaning of the following lines: "Long was the way that fate them bore,"
 **Output example:**