Instructions to use theocolf/Vora-Math-10.4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theocolf/Vora-Math-10.4B with Transformers:

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

pipe = pipeline("text-generation", model="theocolf/Vora-Math-10.4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("theocolf/Vora-Math-10.4B")
model = AutoModelForCausalLM.from_pretrained("theocolf/Vora-Math-10.4B", 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 theocolf/Vora-Math-10.4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "theocolf/Vora-Math-10.4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "theocolf/Vora-Math-10.4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/theocolf/Vora-Math-10.4B

SGLang

How to use theocolf/Vora-Math-10.4B 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 "theocolf/Vora-Math-10.4B" \
    --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": "theocolf/Vora-Math-10.4B",
		"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 "theocolf/Vora-Math-10.4B" \
        --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": "theocolf/Vora-Math-10.4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use theocolf/Vora-Math-10.4B with Docker Model Runner:
```
docker model run hf.co/theocolf/Vora-Math-10.4B
```

Vora-Math-10.4B / README.md

theocolf

feat: fusion officielle stable 10.4B (80% Vora / 20% Math)

bf14ba9 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

1.28 kB

	---
	base_model:
	- theocolf/Vora-X-10B
	- TIGER-Lab/MAmmoTH2-8B
	library_name: transformers
	tags:
	- mergekit
	- merge

	---
	# Vora-Math-10.4B-Output

	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 [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [theocolf/Vora-X-10B](https://huggingface.co/theocolf/Vora-X-10B) as a base.

	### Models Merged

	The following models were included in the merge:
	* [TIGER-Lab/MAmmoTH2-8B](https://huggingface.co/TIGER-Lab/MAmmoTH2-8B)

	### Configuration

	The following YAML configuration was used to produce this model:

	```yaml
	merge_method: dare_ties
	base_model: theocolf/Vora-X-10B
	dtype: bfloat16

	parameters:
	intweight: 1.0
	normalize: true

	slices:
	- sources:
	- model: theocolf/Vora-X-10B
	layer_range: [0, 32]
	parameters:
	density: 0.75
	weight: 0.80
	- model: TIGER-Lab/MAmmoTH2-8B
	layer_range: [0, 32]
	parameters:
	density: 0.60
	weight: 0.20
	- sources:
	- model: theocolf/Vora-X-10B
	layer_range: [32, 40]
	parameters:
	density: 1.0
	weight: 1.0

	tokenizer_source: base
	```