Instructions to use ClaudioItaly/PulzeWriter-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ClaudioItaly/PulzeWriter-9B with Transformers:

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

pipe = pipeline("text-generation", model="ClaudioItaly/PulzeWriter-9B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ClaudioItaly/PulzeWriter-9B")
model = AutoModelForCausalLM.from_pretrained("ClaudioItaly/PulzeWriter-9B")
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 ClaudioItaly/PulzeWriter-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ClaudioItaly/PulzeWriter-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ClaudioItaly/PulzeWriter-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ClaudioItaly/PulzeWriter-9B

SGLang

How to use ClaudioItaly/PulzeWriter-9B 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 "ClaudioItaly/PulzeWriter-9B" \
    --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": "ClaudioItaly/PulzeWriter-9B",
		"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 "ClaudioItaly/PulzeWriter-9B" \
        --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": "ClaudioItaly/PulzeWriter-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ClaudioItaly/PulzeWriter-9B with Docker Model Runner:
```
docker model run hf.co/ClaudioItaly/PulzeWriter-9B
```

PulzeWriter-9B / README.md

ClaudioItaly

Upload folder using huggingface_hub

705e74e verified over 1 year ago

preview code

raw

history blame contribute delete

1.75 kB

	---
	base_model:
	- sam-paech/Delirium-v1
	- lemon07r/Gemma-2-Ataraxy-v4c-9B
	- princeton-nlp/gemma-2-9b-it-SimPO
	- ClaudioItaly/Vangelus-Secundus
	- nbeerbower/gemma2-gutenberg-9B
	library_name: transformers
	tags:
	- mergekit
	- merge

	---
	# merge

	This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

	## Merge Details
	### Merge Method

	This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [ClaudioItaly/Vangelus-Secundus](https://huggingface.co/ClaudioItaly/Vangelus-Secundus) as a base.

	### Models Merged

	The following models were included in the merge:
	* [sam-paech/Delirium-v1](https://huggingface.co/sam-paech/Delirium-v1)
	* [lemon07r/Gemma-2-Ataraxy-v4c-9B](https://huggingface.co/lemon07r/Gemma-2-Ataraxy-v4c-9B)
	* [princeton-nlp/gemma-2-9b-it-SimPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO)
	* [nbeerbower/gemma2-gutenberg-9B](https://huggingface.co/nbeerbower/gemma2-gutenberg-9B)

	### Configuration

	The following YAML configuration was used to produce this model:

	```yaml
	models:
	- model: sam-paech/Delirium-v1
	parameters:
	density: [1, 0.7, 0.1] # density gradient
	weight: 1.0
	- model: lemon07r/Gemma-2-Ataraxy-v4c-9B
	parameters:
	density: [1, 0.5, 0.1] # density gradient
	weight: 1.0
	- model: princeton-nlp/gemma-2-9b-it-SimPO
	parameters:
	density: 0.5
	weight: [0, 0.3, 0.7, 1] # weight gradient
	- model: nbeerbower/gemma2-gutenberg-9B
	parameters:
	density: 0.33
	weight:
	- filter: mlp
	value: 0.5
	- value: 0
	merge_method: ties
	base_model: ClaudioItaly/Vangelus-Secundus
	parameters:
	normalize: true
	int8_mask: true
	dtype: float16

	```