Instructions to use uzlm/alloma-8B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use uzlm/alloma-8B-Base with Transformers:

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

pipe = pipeline("text-generation", model="uzlm/alloma-8B-Base")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("uzlm/alloma-8B-Base")
model = AutoModelForCausalLM.from_pretrained("uzlm/alloma-8B-Base")
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 uzlm/alloma-8B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "uzlm/alloma-8B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "uzlm/alloma-8B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/uzlm/alloma-8B-Base

SGLang

How to use uzlm/alloma-8B-Base 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 "uzlm/alloma-8B-Base" \
    --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": "uzlm/alloma-8B-Base",
		"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 "uzlm/alloma-8B-Base" \
        --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": "uzlm/alloma-8B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use uzlm/alloma-8B-Base with Docker Model Runner:
```
docker model run hf.co/uzlm/alloma-8B-Base
```

Model Description

This is the 8B Base (continual pretrained) version of our Uzbek-optimized Llama 8B Instruct model. For instruction following capability, check out our other models:

Our 8B Base model has been continually pretrained with context length of 4096 tokens, on 3.6B tokens (67% English, 33% Uzbek). Our customized tokenizer averages 1.7 tokens per Uzbek word vs. ~3.5 in the original Llama models, meaning 2x faster inference and longer effective context length on Uzbek text.

Methodology: Efficient Vocabulary Adaptation for Uzbek

The primary motivation for our technical approach is to create a model with a more efficient tokenizer for the Uzbek language. This ensures both faster inference speeds and a longer effective context length when processing Uzbek text, as fewer tokens are needed to represent the same amount of information.

Acknowledgements

This project was developed by the teams at Examy.me and Teamwork.uz. Their collaboration and resources were essential to the creation and success of the alloma model series.

Downloads last month: 6

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for uzlm/alloma-8B-Base

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Finetuned

(2752)

this model

uzlm
/

alloma-8B-Base

Model Description

Methodology: Efficient Vocabulary Adaptation for Uzbek

Acknowledgements

Model tree for uzlm/alloma-8B-Base

Datasets used to train uzlm/alloma-8B-Base