Instructions to use h4rz3rk4s3/TinyNewsLlama-1.1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use h4rz3rk4s3/TinyNewsLlama-1.1B with Transformers:

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

pipe = pipeline("text-generation", model="h4rz3rk4s3/TinyNewsLlama-1.1B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("h4rz3rk4s3/TinyNewsLlama-1.1B")
model = AutoModelForCausalLM.from_pretrained("h4rz3rk4s3/TinyNewsLlama-1.1B")
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 h4rz3rk4s3/TinyNewsLlama-1.1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "h4rz3rk4s3/TinyNewsLlama-1.1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "h4rz3rk4s3/TinyNewsLlama-1.1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/h4rz3rk4s3/TinyNewsLlama-1.1B

SGLang

How to use h4rz3rk4s3/TinyNewsLlama-1.1B 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 "h4rz3rk4s3/TinyNewsLlama-1.1B" \
    --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": "h4rz3rk4s3/TinyNewsLlama-1.1B",
		"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 "h4rz3rk4s3/TinyNewsLlama-1.1B" \
        --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": "h4rz3rk4s3/TinyNewsLlama-1.1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use h4rz3rk4s3/TinyNewsLlama-1.1B with Docker Model Runner:
```
docker model run hf.co/h4rz3rk4s3/TinyNewsLlama-1.1B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

UPDATE March, 17th: Changed quantization for the merge of the adapter and the original model.

TinyNewsLlama-1.1B

TinyNewsLlama-1.1B is a QLoRA SFT fine-tune of TinyLlama/TinyLlama-1.1B-Chat-v1.0 using a sample of a concentrated version of the [bigNews] (https://paperswithcode.com/dataset/bignews) Dataset. The model was fine-tuned for ~12h on one A100 40GB on ~125M tokens.

The goal of this project is to study the potential for improving the domain-specific (in this case political) knowledge of small (<3B) LLMs by concentrating the training datasets TF-IDF in respect to the underlying Topics found in the origianl Dataset.

The used training data contains political news articles from The New York Times, USA Today and The Washington Times. The concentrated BigNews Dataset as well as more information about the used sample will soon be added.

💻 Usage

!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch

model = "h4rz3rk4s3/TinyNewsLlama-1.1B"
messages = [
    {
        "role": "system",
        "content": "You are a an experienced journalist.",
    },
    {"role": "user", "content": "Write a short article on Brexit and it's impact on the European Union."},
]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Downloads last month: 13

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for h4rz3rk4s3/TinyNewsLlama-1.1B

Base model

TinyLlama/TinyLlama-1.1B-Chat-v1.0

Finetuned

(554)

this model

Merges

3 models

Quantizations

1 model