Instructions to use Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM with Transformers:

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

pipe = pipeline("text-generation", model="Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM")
model = AutoModelForCausalLM.from_pretrained("Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM

SGLang

How to use Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM 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 "Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM" \
    --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": "Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM",
		"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 "Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM" \
        --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": "Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM with Docker Model Runner:
```
docker model run hf.co/Pinkstack/PARM-v2-ULTRA-o1-3B-vLLM
```

Pinkstack commited on Dec 26, 2024

Commit

7595a23

verified ·

1 Parent(s): 5f47611

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -17,4 +17,5 @@ base_model:
 ---
 # Highly advanced based model for training:
-Parm 2 ultra: trained for 2 hours on 1 Million OpenO1 chats, 180k sonnet 3.5, 130k qwq messages.

 ---
 # Highly advanced based model for training:
+- context length: 131072, GGUF version would be 524288
+- Parm 2 ultra: trained for 2 hours on 1 Million OpenO1 chats, 180k sonnet 3.5, 130k qwq messages.