Instructions to use Alelcv27/Llama3.2-3B-TIES-Math-Code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Alelcv27/Llama3.2-3B-TIES-Math-Code with Transformers:

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

pipe = pipeline("text-generation", model="Alelcv27/Llama3.2-3B-TIES-Math-Code")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Alelcv27/Llama3.2-3B-TIES-Math-Code")
model = AutoModelForCausalLM.from_pretrained("Alelcv27/Llama3.2-3B-TIES-Math-Code")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Alelcv27/Llama3.2-3B-TIES-Math-Code with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Alelcv27/Llama3.2-3B-TIES-Math-Code"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Alelcv27/Llama3.2-3B-TIES-Math-Code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Alelcv27/Llama3.2-3B-TIES-Math-Code

SGLang

How to use Alelcv27/Llama3.2-3B-TIES-Math-Code 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 "Alelcv27/Llama3.2-3B-TIES-Math-Code" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Alelcv27/Llama3.2-3B-TIES-Math-Code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Alelcv27/Llama3.2-3B-TIES-Math-Code" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Alelcv27/Llama3.2-3B-TIES-Math-Code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Alelcv27/Llama3.2-3B-TIES-Math-Code with Docker Model Runner:
```
docker model run hf.co/Alelcv27/Llama3.2-3B-TIES-Math-Code
```

Llama3.2-3B-TIES-Math-Code / mergekit_config.yml

Alelcv27

Upload folder using huggingface_hub

503c739 verified about 1 month ago

raw

history blame contribute delete

493 Bytes

	base_model: meta-llama/Llama-3.2-3B
	dtype: float16
	merge_method: ties
	modules:
	default:
	slices:
	- sources:
	- layer_range: [0, 28]
	model: Alelcv27/Llama3.2-3B-Base-Math
	parameters:
	density: 0.8
	weight: 0.8
	- layer_range: [0, 28]
	model: Alelcv27/Llama3.2-3B-Base-Code
	parameters:
	density: 0.8
	weight: 0.7
	- layer_range: [0, 28]
	model: meta-llama/Llama-3.2-3B
	parameters:
	normalize: 1.0