Instructions to use webnizam/gemma-unintended-consequences-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use webnizam/gemma-unintended-consequences-2b with Transformers:

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

pipe = pipeline("text-generation", model="webnizam/gemma-unintended-consequences-2b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("webnizam/gemma-unintended-consequences-2b")
model = AutoModelForCausalLM.from_pretrained("webnizam/gemma-unintended-consequences-2b", 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 webnizam/gemma-unintended-consequences-2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "webnizam/gemma-unintended-consequences-2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "webnizam/gemma-unintended-consequences-2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/webnizam/gemma-unintended-consequences-2b

SGLang

How to use webnizam/gemma-unintended-consequences-2b 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 "webnizam/gemma-unintended-consequences-2b" \
    --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": "webnizam/gemma-unintended-consequences-2b",
		"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 "webnizam/gemma-unintended-consequences-2b" \
        --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": "webnizam/gemma-unintended-consequences-2b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use webnizam/gemma-unintended-consequences-2b with Docker Model Runner:
```
docker model run hf.co/webnizam/gemma-unintended-consequences-2b
```

Model Card for Gemma 2b - Unintended Consequences

This model is a Gemma-based model fine-tuned for generating text related to the unintended consequences of various actions or decisions.

Model Details

Model Description

This is a Gemma model fine-tuned for the task of generating text about unintended consequences. The model has been trained on a dataset of text examples that describe various actions and their unintended consequences.

Developed by: Falcons.AI
Model type: GemmaForCausalLM
Language(s) (NLP): English
Finetuned from model: gemma-2b-it

Model Sources

Repository: webnizam/gemma-unintended-consequences-2b

Uses

Direct Use

This model can be used directly to generate text about unintended consequences of various actions or decisions. It can be useful for brainstorming, risk assessment, or educational purposes.

How to Get Started with the Model

Use the following code to get started with the model:

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("webnizam/gemma-unintended-consequences-2b")
model = AutoModelForCausalLM.from_pretrained("webnizam/gemma-unintended-consequences-2b")

text = "<start_of_text> Outsourcing Manufacturing to Low-Cost Countries"
inputs = tokenizer(text, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 5

Safetensors

Model size

3B params

Tensor type

F32