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

Libraries

How to use newsmediabias/MBIAS with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("newsmediabias/MBIAS")
model = AutoModelForCausalLM.from_pretrained("newsmediabias/MBIAS", 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 newsmediabias/MBIAS with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/newsmediabias/MBIAS

SGLang

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

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

MBIAS

Commit History

Update README.md

a1cc2f7
verified

shainaraza commited on May 21, 2024

Update README.md

90cce91
verified

shainaraza commited on May 21, 2024

Update README.md

5be112d
verified

shainaraza commited on May 21, 2024

Create README.md

04a5470
verified

shainar commited on May 18, 2024

Mistral IFT Tuned model

c184ea3

AnanyaRaval commited on May 12, 2024

Delete model

c3b2fa4

AnanyaRaval commited on May 11, 2024

Add config.json for Mistral-IFT model

faf906d

AnanyaRaval commited on May 3, 2024

Add Mistral-IFT model

d99c98f

AnanyaRaval commited on May 3, 2024